This paper presents crack detection in concrete structure based on fuzzy logic. Safety inspection of concrete structures is very important since it is closely related with the structural health and reliability. Automated structural health monitoring system becomes necessity in recent years that encourages various researches to be going on in this area. Cheap availability of digital cameras makes research work in this field easier. This paper presents digital image processing and fuzzy logic based efficient crack detection technique in concrete structure. Here features from digital image of concrete structure are extracted by using morphological image processing technique and then extracted features are fed to fuzzy logic to accurately identify the crack.
Cracks on the concrete surface are one of the earliest symptoms of degradation of the structure which isfundamental for the upkeep as properly the non-stop publicity will lead to the severe injury to the environment.Manual inspection is the acclaimed approach for the crack inspection. In the guide inspection, the diagram of thecrack is organized manually, and the conditions of the irregularities are noted. Since the guide strategy absolutelyrelies upon on the specialist’s expertise and experience, it lacks objectivity in the quantitative analysis. So,automated image-based crack detection is proposed as a replacement. The proposed gadget comprises pictureprocessing and facts acquisition methodologies for crack detection and evaluation of surface degradation. Theacquired outcomes exhibit that the deployment of image processing in an nice way is a key step towards theinspection of giant infrastructures
Face recognition is a type of biometric system that uses analysis and comparison of facial patterns to identify individuals from digital images. It works by detecting distinct nodal points on the face and measuring relationships between features like eye separation, nose width, and jaw line. The process involves image acquisition, processing, locating distinguishing characteristics, and template matching. Some advantages are its ability to identify from photos and operate without cooperation, while weaknesses include reduced accuracy from environmental changes or aging. Applications include security, child pickup verification, and banking authentication.
The slide was prepared on the purpose of presentation of our project face detection highlighting the basics of theory used and project details like goal, approach. Hope it's helpful.
This document discusses object recognition by computers. It notes that while object recognition is easy for humans, it is difficult for computers because they cannot rely on appearance alone. Key challenges for computers include variations in scale, shape, occlusion, lighting and background clutter. The document then discusses techniques used for object recognition, including feature detection methods like SIFT and SURF that extract keypoints, descriptors that describe regions around keypoints, and feature matching to identify corresponding regions between images. It also covers bag-of-words models, visual vocabularies and inverted indexing to allow large scale image retrieval. Finally, it lists applications of object recognition like digital watermarking, face detection and robot navigation.
Attendance system based on face recognition using python by Raihan Sikdarraihansikdar
The document discusses face recognition technology for use in an automatic attendance system. It first defines biometrics and face recognition, explaining that face recognition identifies individuals using facial features. It then covers how face recognition systems work by detecting nodal points on faces to create unique face prints. The document proposes using such a system to take student attendance in online classes during the pandemic, noting advantages like ease of use, increased security, and cost effectiveness. It provides examples of how the system would capture images, analyze features, and recognize enrolled students to record attendance automatically.
Detection and recognition of face using neural networkSmriti Tikoo
This document describes research on face detection and recognition using neural networks. It discusses using the Viola-Jones algorithm for face detection and a backpropagation neural network for face recognition. The Viola-Jones algorithm uses haar features, integral images, AdaBoost training, and cascading classifiers for real-time face detection. A backpropagation network with sigmoid activation functions is trained on facial images for recognition. Results show the network can accurately recognize faces after training. The document concludes the approach allows face recognition from an input image and discusses limitations and potential improvements.
Cracks on the concrete surface are one of the earliest symptoms of degradation of the structure which isfundamental for the upkeep as properly the non-stop publicity will lead to the severe injury to the environment.Manual inspection is the acclaimed approach for the crack inspection. In the guide inspection, the diagram of thecrack is organized manually, and the conditions of the irregularities are noted. Since the guide strategy absolutelyrelies upon on the specialist’s expertise and experience, it lacks objectivity in the quantitative analysis. So,automated image-based crack detection is proposed as a replacement. The proposed gadget comprises pictureprocessing and facts acquisition methodologies for crack detection and evaluation of surface degradation. Theacquired outcomes exhibit that the deployment of image processing in an nice way is a key step towards theinspection of giant infrastructures
Face recognition is a type of biometric system that uses analysis and comparison of facial patterns to identify individuals from digital images. It works by detecting distinct nodal points on the face and measuring relationships between features like eye separation, nose width, and jaw line. The process involves image acquisition, processing, locating distinguishing characteristics, and template matching. Some advantages are its ability to identify from photos and operate without cooperation, while weaknesses include reduced accuracy from environmental changes or aging. Applications include security, child pickup verification, and banking authentication.
The slide was prepared on the purpose of presentation of our project face detection highlighting the basics of theory used and project details like goal, approach. Hope it's helpful.
This document discusses object recognition by computers. It notes that while object recognition is easy for humans, it is difficult for computers because they cannot rely on appearance alone. Key challenges for computers include variations in scale, shape, occlusion, lighting and background clutter. The document then discusses techniques used for object recognition, including feature detection methods like SIFT and SURF that extract keypoints, descriptors that describe regions around keypoints, and feature matching to identify corresponding regions between images. It also covers bag-of-words models, visual vocabularies and inverted indexing to allow large scale image retrieval. Finally, it lists applications of object recognition like digital watermarking, face detection and robot navigation.
Attendance system based on face recognition using python by Raihan Sikdarraihansikdar
The document discusses face recognition technology for use in an automatic attendance system. It first defines biometrics and face recognition, explaining that face recognition identifies individuals using facial features. It then covers how face recognition systems work by detecting nodal points on faces to create unique face prints. The document proposes using such a system to take student attendance in online classes during the pandemic, noting advantages like ease of use, increased security, and cost effectiveness. It provides examples of how the system would capture images, analyze features, and recognize enrolled students to record attendance automatically.
Detection and recognition of face using neural networkSmriti Tikoo
This document describes research on face detection and recognition using neural networks. It discusses using the Viola-Jones algorithm for face detection and a backpropagation neural network for face recognition. The Viola-Jones algorithm uses haar features, integral images, AdaBoost training, and cascading classifiers for real-time face detection. A backpropagation network with sigmoid activation functions is trained on facial images for recognition. Results show the network can accurately recognize faces after training. The document concludes the approach allows face recognition from an input image and discusses limitations and potential improvements.
The document discusses image segmentation techniques. It describes image segmentation as partitioning a digital image into multiple regions based on characteristics like color or texture. Common applications of image segmentation include industrial inspection, optical character recognition, and medical imaging. The techniques discussed are fixed thresholding, iterative thresholding, and fuzzy c-means clustering. Fuzzy c-means clustering is identified as the most suitable for pest image segmentation based on its lower entropy and normalized mutual information values. Simulated annealing is also proposed to improve upon the limitations of fuzzy c-means clustering.
EDGE DETECTION USING SOBEL OPERATOR.pptxkolaruboys
This document summarizes edge detection using the Sobel operator. It begins by defining edges as areas of significant intensity change between objects in an image. There are three main steps to edge detection: image smoothing to remove noise; edge point detection to identify areas of intensity change; and edge localization to precisely locate the edges. The document then explains how the Sobel operator uses two 3x3 kernels to detect horizontal and vertical edges by approximating the image gradient. It provides code to demonstrate Sobel edge detection in MATLAB. The advantages of the Sobel operator are its simplicity and ability to detect edges and their orientations.
Building Information Modeling (BIM) is a design methodology that uses coordinated, high-quality information stored in a single building model to enable design and construction teams to consistently and reliably manage project information across the entire scope. BIM supports large team workflows to improve project understanding and enable more predictable outcomes through increased coordination, accuracy, and earlier informed decisions. Software like Revit Structure uses intelligent, parametric objects and elements with associated information stored in a single model to automatically coordinate changes across any views of the model.
Presentation on Face detection and recognition - Credits goes to Mr Shriram, "https://www.hackster.io/sriram17ei/facial-recognition-opencv-python-9bc724"
This document summarizes a presentation on image processing. It introduces image processing and discusses acquiring images in digital formats. It covers various aspects of image processing like enhancement, restoration, and geometry transformations. Image processing techniques discussed include histograms, compression, analysis, and computer-aided detection. Color imaging and different image types are also introduced. The document concludes with mentioning some common image processing software.
This document provides an overview of polygonal modelling techniques used in 3D computer graphics. It discusses how polygon meshes are constructed using vertices, edges, and faces. Common operations for constructing meshes like box modelling and extrusion modelling are described. Refining models by manipulating individual vertices is also covered. The document emphasizes the importance of using reference materials when building 3D models.
This document provides an overview of digital image fundamentals and operations. It defines what a digital image is, how it is represented as a matrix, and common image types like RGB, grayscale, and binary. Pixels, resolution, neighborhoods, and basic relationships between pixels are discussed. The document also covers different types of image operations including point, local, and global operations as well as examples like arithmetic, logical, and geometric transformations. Finally, it introduces concepts of linear and nonlinear operations and announces the topic of the next lecture on image enhancement in the spatial domain.
1. The document discusses the key elements of digital image processing including image acquisition, enhancement, restoration, segmentation, representation and description, recognition, and knowledge bases.
2. It also covers fundamentals of human visual perception such as the anatomy of the eye, image formation, brightness adaptation, color fundamentals, and color models like RGB and HSI.
3. The principles of video cameras are explained including the construction and working of the vidicon camera tube.
This document discusses object detection using the Single Shot Detector (SSD) algorithm with the MobileNet V1 architecture. It begins with an introduction to object detection and a literature review of common techniques. It then describes the basic architecture of convolutional neural networks and how they are used for feature extraction in SSD. The SSD framework uses multi-scale feature maps for detection and convolutional predictors. MobileNet V1 reduces model size and complexity through depthwise separable convolutions. This allows SSD with MobileNet V1 to perform real-time object detection with reduced parameters and computations compared to other models.
Here are the key steps to convert a color image to a binary image in LabVIEW:
1. Read in the color image using the Read PNG or Read JPEG VI. This will return an image structure.
2. Use the Color To Gray VI to convert the color image to grayscale. This removes the color information and leaves only the luminance.
3. Apply a threshold to convert the grayscale image to binary. Use the Threshold VI and choose an appropriate threshold value (usually 128 for 8-bit images).
4. The output of the Threshold VI will be a binary image, where pixels above the threshold are white (255) and pixels below are black (0).
5. You can now process the binary
Image segmentation refers to partitioning a digital image into multiple regions or sets of pixels based on characteristics like color or texture. The goal is to simplify the image representation to make it easier to analyze. Some applications in medical imaging include locating tumors, measuring tissue volumes, and computer-guided surgery. Common segmentation techniques include thresholding, edge detection, region growing, and split-and-merge approaches.
Lec11: Active Contour and Level Set for Medical Image SegmentationUlaş Bağcı
ActiveContour(Snake) • LevelSet
• Applications
Enhancement, Noise Reduction, and Signal Processing • MedicalImageRegistration • MedicalImageSegmentation • MedicalImageVisualization • Machine Learning in Medical Imaging • Shape Modeling/Analysis of Medical Images Deep Learning in Radiology Fuzzy Connectivity (FC) – Affinity functions • Absolute FC • Relative FC (and Iterative Relative FC) • Successful example applications of FC in medical imaging • Segmentation of Airway and Airway Walls using RFC based method Energyfunctional – Data and Smoothness terms • GraphCut – Min cut – Max Flow • ApplicationsinRadiologyImages
The document discusses edge detection methods including gradient based approaches like Sobel and zero crossing based techniques like Laplacian of Gaussian. It proposes a new algorithm that applies fuzzy logic to the results of gradient and zero crossing edge detection on an image to more accurately identify edges. The algorithm calculates gradient and zero crossings, applies fuzzy rules to classify pixels, and thresholds to determine final edge pixels.
The document outlines topics to discuss regarding 3D vision technology, including a brief history. It covers early patents from 1880 and the first 3D movie from 1922. Methods of capturing 3D images are discussed as well as techniques for projection, such as anaglyph, polarization, interference filters, and Dolby 3D. The document also touches on classifying 3D formats and modern technologies that enable 3D without glasses, like autostereoscopic screens and holograms. References are provided at the end.
This document summarizes a seminar presentation on multimodal biometric systems. It discusses the limitations of unimodal biometric systems and how combining multiple biometric traits can improve accuracy. It covers classification of multimodal systems based on architecture, sources, fusion level, and methodology. Score normalization and different fusion techniques at the sensor, feature, matching score, and decision levels are also summarized. The conclusion states that multimodal biometrics provides higher security than unimodal systems through appropriate normalization and fusion methods.
This document describes an emotion-based music player that generates playlists based on a user's detected mood. It uses three main modules: an emotion extraction module that analyzes facial expressions from webcam images to determine mood, an audio feature extraction module that extracts data from songs, and an emotion-audio recognition module that maps the facial and audio features to select songs for the playlist. The system aims to reduce the effort of manually creating playlists by automatically generating ones tailored to the user's current emotional state. It works by classifying facial expressions and songs into categories like happy, sad, and angry to create playlists that match or influence the user's detected mood.
This is the basic introductory presentation for beginners. It gives you the idea about what is image processing means. The presentation consists of introduction to digital image processing, image enhancement, image filtering, finding an image edge, image analysis, tools for image processing and finally some application of digital image processing.
This document discusses topological features in digital images. It defines digital topology as dealing with the topological properties of digital images, providing a mathematical basis for image processing operations. It describes several topological descriptors that are invariant to deformations, including the number of holes (H), number of connected components (C), and Euler number (E=C-H). These descriptors can be used to characterize shapes and regions in images.
1) 2D geometric transformations include translations, scaling, and rotations. They can be represented by transformation matrices.
2) Translation moves an object by adding offsets to x and y coordinates. It can be represented by a 3x3 matrix with 1s on the diagonal and offsets as the last column.
3) Scaling enlarges or shrinks an object by multiplying x and y coordinates by scaling factors. It can be represented by a 2x2 diagonal matrix with scaling factors.
4) Rotation rotates an object by applying a trigonometric transformation to x and y coordinates. It can be represented by a 2x2 rotation matrix containing cosine and sine of the rotation angle.
The document discusses RFID (radio-frequency identification) technology and its applications. It describes what RFID is, how RFID tags work, and examples of RFID being used for identification of objects, tracking objects in supply chains, access control, contactless payment, and inferring human activities through interactions with tagged objects. The document also provides an example of using an RFID reader and tags in a Java program to detect tagged objects.
The document discusses image segmentation techniques. It describes image segmentation as partitioning a digital image into multiple regions based on characteristics like color or texture. Common applications of image segmentation include industrial inspection, optical character recognition, and medical imaging. The techniques discussed are fixed thresholding, iterative thresholding, and fuzzy c-means clustering. Fuzzy c-means clustering is identified as the most suitable for pest image segmentation based on its lower entropy and normalized mutual information values. Simulated annealing is also proposed to improve upon the limitations of fuzzy c-means clustering.
EDGE DETECTION USING SOBEL OPERATOR.pptxkolaruboys
This document summarizes edge detection using the Sobel operator. It begins by defining edges as areas of significant intensity change between objects in an image. There are three main steps to edge detection: image smoothing to remove noise; edge point detection to identify areas of intensity change; and edge localization to precisely locate the edges. The document then explains how the Sobel operator uses two 3x3 kernels to detect horizontal and vertical edges by approximating the image gradient. It provides code to demonstrate Sobel edge detection in MATLAB. The advantages of the Sobel operator are its simplicity and ability to detect edges and their orientations.
Building Information Modeling (BIM) is a design methodology that uses coordinated, high-quality information stored in a single building model to enable design and construction teams to consistently and reliably manage project information across the entire scope. BIM supports large team workflows to improve project understanding and enable more predictable outcomes through increased coordination, accuracy, and earlier informed decisions. Software like Revit Structure uses intelligent, parametric objects and elements with associated information stored in a single model to automatically coordinate changes across any views of the model.
Presentation on Face detection and recognition - Credits goes to Mr Shriram, "https://www.hackster.io/sriram17ei/facial-recognition-opencv-python-9bc724"
This document summarizes a presentation on image processing. It introduces image processing and discusses acquiring images in digital formats. It covers various aspects of image processing like enhancement, restoration, and geometry transformations. Image processing techniques discussed include histograms, compression, analysis, and computer-aided detection. Color imaging and different image types are also introduced. The document concludes with mentioning some common image processing software.
This document provides an overview of polygonal modelling techniques used in 3D computer graphics. It discusses how polygon meshes are constructed using vertices, edges, and faces. Common operations for constructing meshes like box modelling and extrusion modelling are described. Refining models by manipulating individual vertices is also covered. The document emphasizes the importance of using reference materials when building 3D models.
This document provides an overview of digital image fundamentals and operations. It defines what a digital image is, how it is represented as a matrix, and common image types like RGB, grayscale, and binary. Pixels, resolution, neighborhoods, and basic relationships between pixels are discussed. The document also covers different types of image operations including point, local, and global operations as well as examples like arithmetic, logical, and geometric transformations. Finally, it introduces concepts of linear and nonlinear operations and announces the topic of the next lecture on image enhancement in the spatial domain.
1. The document discusses the key elements of digital image processing including image acquisition, enhancement, restoration, segmentation, representation and description, recognition, and knowledge bases.
2. It also covers fundamentals of human visual perception such as the anatomy of the eye, image formation, brightness adaptation, color fundamentals, and color models like RGB and HSI.
3. The principles of video cameras are explained including the construction and working of the vidicon camera tube.
This document discusses object detection using the Single Shot Detector (SSD) algorithm with the MobileNet V1 architecture. It begins with an introduction to object detection and a literature review of common techniques. It then describes the basic architecture of convolutional neural networks and how they are used for feature extraction in SSD. The SSD framework uses multi-scale feature maps for detection and convolutional predictors. MobileNet V1 reduces model size and complexity through depthwise separable convolutions. This allows SSD with MobileNet V1 to perform real-time object detection with reduced parameters and computations compared to other models.
Here are the key steps to convert a color image to a binary image in LabVIEW:
1. Read in the color image using the Read PNG or Read JPEG VI. This will return an image structure.
2. Use the Color To Gray VI to convert the color image to grayscale. This removes the color information and leaves only the luminance.
3. Apply a threshold to convert the grayscale image to binary. Use the Threshold VI and choose an appropriate threshold value (usually 128 for 8-bit images).
4. The output of the Threshold VI will be a binary image, where pixels above the threshold are white (255) and pixels below are black (0).
5. You can now process the binary
Image segmentation refers to partitioning a digital image into multiple regions or sets of pixels based on characteristics like color or texture. The goal is to simplify the image representation to make it easier to analyze. Some applications in medical imaging include locating tumors, measuring tissue volumes, and computer-guided surgery. Common segmentation techniques include thresholding, edge detection, region growing, and split-and-merge approaches.
Lec11: Active Contour and Level Set for Medical Image SegmentationUlaş Bağcı
ActiveContour(Snake) • LevelSet
• Applications
Enhancement, Noise Reduction, and Signal Processing • MedicalImageRegistration • MedicalImageSegmentation • MedicalImageVisualization • Machine Learning in Medical Imaging • Shape Modeling/Analysis of Medical Images Deep Learning in Radiology Fuzzy Connectivity (FC) – Affinity functions • Absolute FC • Relative FC (and Iterative Relative FC) • Successful example applications of FC in medical imaging • Segmentation of Airway and Airway Walls using RFC based method Energyfunctional – Data and Smoothness terms • GraphCut – Min cut – Max Flow • ApplicationsinRadiologyImages
The document discusses edge detection methods including gradient based approaches like Sobel and zero crossing based techniques like Laplacian of Gaussian. It proposes a new algorithm that applies fuzzy logic to the results of gradient and zero crossing edge detection on an image to more accurately identify edges. The algorithm calculates gradient and zero crossings, applies fuzzy rules to classify pixels, and thresholds to determine final edge pixels.
The document outlines topics to discuss regarding 3D vision technology, including a brief history. It covers early patents from 1880 and the first 3D movie from 1922. Methods of capturing 3D images are discussed as well as techniques for projection, such as anaglyph, polarization, interference filters, and Dolby 3D. The document also touches on classifying 3D formats and modern technologies that enable 3D without glasses, like autostereoscopic screens and holograms. References are provided at the end.
This document summarizes a seminar presentation on multimodal biometric systems. It discusses the limitations of unimodal biometric systems and how combining multiple biometric traits can improve accuracy. It covers classification of multimodal systems based on architecture, sources, fusion level, and methodology. Score normalization and different fusion techniques at the sensor, feature, matching score, and decision levels are also summarized. The conclusion states that multimodal biometrics provides higher security than unimodal systems through appropriate normalization and fusion methods.
This document describes an emotion-based music player that generates playlists based on a user's detected mood. It uses three main modules: an emotion extraction module that analyzes facial expressions from webcam images to determine mood, an audio feature extraction module that extracts data from songs, and an emotion-audio recognition module that maps the facial and audio features to select songs for the playlist. The system aims to reduce the effort of manually creating playlists by automatically generating ones tailored to the user's current emotional state. It works by classifying facial expressions and songs into categories like happy, sad, and angry to create playlists that match or influence the user's detected mood.
This is the basic introductory presentation for beginners. It gives you the idea about what is image processing means. The presentation consists of introduction to digital image processing, image enhancement, image filtering, finding an image edge, image analysis, tools for image processing and finally some application of digital image processing.
This document discusses topological features in digital images. It defines digital topology as dealing with the topological properties of digital images, providing a mathematical basis for image processing operations. It describes several topological descriptors that are invariant to deformations, including the number of holes (H), number of connected components (C), and Euler number (E=C-H). These descriptors can be used to characterize shapes and regions in images.
1) 2D geometric transformations include translations, scaling, and rotations. They can be represented by transformation matrices.
2) Translation moves an object by adding offsets to x and y coordinates. It can be represented by a 3x3 matrix with 1s on the diagonal and offsets as the last column.
3) Scaling enlarges or shrinks an object by multiplying x and y coordinates by scaling factors. It can be represented by a 2x2 diagonal matrix with scaling factors.
4) Rotation rotates an object by applying a trigonometric transformation to x and y coordinates. It can be represented by a 2x2 rotation matrix containing cosine and sine of the rotation angle.
The document discusses RFID (radio-frequency identification) technology and its applications. It describes what RFID is, how RFID tags work, and examples of RFID being used for identification of objects, tracking objects in supply chains, access control, contactless payment, and inferring human activities through interactions with tagged objects. The document also provides an example of using an RFID reader and tags in a Java program to detect tagged objects.
RFID technology allows for automatic identification of movable items using radio waves. BCDS is an Australian company that has implemented various RFID solutions including asset tracking, visitor tracking, animal tracking, healthcare solutions, and more. RFID systems consist of tags that can be attached to items and readers that can read tag data remotely without line of sight. RFID finds many uses including tracking animals, manufacturing/warehousing, defense applications, and document tracking. The presentation discusses these applications and how RFID is playing a role in smart technologies.
Reasons and solution to cracks in buildings.
<div dir="ltr"><br>Reasons and solution to cracks in buildings.<br><blockquote style="margin: 1.5em 0pt;"></blockquote></div>
This PowerPoint presentation provides an overview of radio frequency identification (RFID) technology. It discusses how RFID works, the benefits of RFID, and some concerns around implementing RFID technology. The presentation concludes that while RFID is being adopted in many industries and locations, concerns around privacy and security still need to be addressed for successful widespread implementation. However, RFID has the potential to significantly improve efficiency and change how we manage things in both our personal and work lives.
This presentation discusses digital image processing. It begins with definitions of digital images and digital image processing. Digital image processing focuses on improving images for human interpretation and processing images for machine perception. The history of digital image processing is then reviewed from the 1920s to today. Key examples of applications like medical imaging, satellite imagery, and industrial inspection are provided. The main stages of digital image processing are outlined, including image acquisition, enhancement, restoration, segmentation, and compression. The document concludes with an overview of a system for automatic face recognition using color-based segmentation.
This document discusses crack detection in concrete structures using deep learning techniques. It begins by describing traditional manual inspection and image processing methods for crack detection, noting limitations such as being time-consuming, inaccurate, and unable to handle complex image data. The document then introduces convolutional neural networks (CNNs) as a deep learning technique for crack detection, which can automatically learn features from image data without predefined feature extraction. It provides details on common CNN architecture components like convolution, activation and pooling layers. The document concludes by outlining the process of developing a CNN model for crack detection, including collecting a dataset, training the model, and evaluating the trained model's performance using classification metrics.
Identification and Rejection of Defective Ceramic Tile using Image Processing...IJMTST Journal
Manual Ceramic Tile inspection process is tedious if human operator is employed to look for defective tiles and their elimination. The plain ceramic tiles often have the following types of defects viz Cracks, Blobs and pin holes [1]. The fatigue of human operator deteriorates the quality of the tile being produced. In this paper a novel and simple automatic tile defect identification and elimination system is proposed. The proposed system is built around MATLAB and ARDUINO. The systems performance is evaluated in terms of accuracy and time taken for detection. The Proposed system promises superior performance when compared to the other existing system
AUTOMATED MANAGEMENT OF POTHOLE RELATED DISASTERS USING IMAGE PROCESSING AND ...ijcsit
Potholes though seem inconsequential, may cause accidents resulting in loss of human life. In this paper, we present an automated system to efficiently manage the potholes in a ward by deploying geotagging and image processing techniques that overcomes the drawbacks associated with the existing
survey-oriented systems. Image processing is used for identification of target pothole regions in the 2D
images using edge detection and morphological image processing operations. A method is developed to
accurately estimate the dimensions of the potholes from their images, analyze their area and depth,estimate the quantity of filling material required and therefore enabling pothole attendance on a priority basis. This will further enable the government official to have a fully automated system for e f f e c t i v e l y ma n a g i ng pothole related disasters.
Crack Detection in Ceramic Tiles using Zoning and Edge Detection Methodsijtsrd
The quality control process in ceramic tile industry plays crucial role to enhance the quality standards. At present the quality analysis is mostly done manually. Manual inspection is not so efficient and it is labour intensive. Defect detection accuracy is lower due to human mistakes and unforgiving mechanical condition. To vanquish these issues, an automated inspection system for crack tiles that depends on image processing methods is presented. The tiles are examined using image processing concept using matlab software. The processing is very less compared to that of manual inspection. The automated inspection system can replace the manual ceramic tile detection system more efficiently and with better accuracy. Bhagyashree R K | S. A. Angadi"Crack Detection in Ceramic Tiles using Zoning and Edge Detection Methods" Published in International Journal of Trend in Scientific Research and Development (ijtsrd), ISSN: 2456-6470, Volume-2 | Issue-4 , June 2018, URL: http://www.ijtsrd.com/papers/ijtsrd15724.pdf http://www.ijtsrd.com/computer-science/other/15724/crack-detection-in-ceramic-tiles-using-zoning-and-edge-detection-methods/bhagyashree-r-k
IRJET- Image Feature Extraction using Hough Transformation PrincipleIRJET Journal
The document describes an image processing technique that uses Hough transformation and contour detection to extract features from images and count objects. It proposes an integrated method to detect circular objects, detach overlapping objects, and count objects of any shape. The method applies Canny edge detection, contour detection, and circular Hough transform to segment overlapping circular objects. It then uses contour detection to count all objects regardless of shape. Experimental results show the method can successfully segment and count overlapping circular and non-circular objects in test images.
A DEEP LEARNING APPROACH FOR DEFECT DETECTION AND SEGMENTATION IN X-RAY COMPU...gerogepatton
Additive manufacturing is an emerging and crucial technology that can overcome the limitations of
traditional manufacturing techniques to accurately manufacture highly complex parts. X-ray Computed
Tomography (XCT) is a widely used method for non-destructive testing of AM parts. However, detection
and segmentation of defects in XCT images of AM have many challenges due to contrast, size, and
appearance of defects. This study developed deep learning techniques for detecting and segmenting defects
in XCT images of AM. Due to a large number of required defect annotations, this paper applied image
processing techniques to automate the defect labeling process. A single-stage object detection algorithm
(YOLOv5) was applied to the problem of defect detection in image data. Three different variants of
YOLOv5 were implemented and their performances were compared. U-Net was applied for defect
segmentation in XCT slices. Finally, this research demonstrates that deep learning techniques can improve
the automatic defect detection and segmentation in XCT data of AM
Application of Digital Image Correlation: A ReviewIRJET Journal
This document reviews the application of digital image correlation (DIC) technique. DIC is a non-contact optical method used to measure full-field surface deformations and strains. It works by tracking random speckle patterns on a material's surface between images taken before and after deformation. The document discusses how DIC can be used to detect crack initiation in concrete, measure strain maps, and determine material properties like elastic modulus without being destructive. It also reviews several past studies where DIC was used to analyze strain in materials like gypsum, composites, and concrete. The document concludes that DIC provides an accurate alternative to conventional techniques and its use could be expanded in civil engineering.
A New Deep Learning Based Technique To Detect Copy Move Forgery In Digital Im...IRJET Journal
This document proposes a new deep learning technique to detect copy move forgery in digital images. It uses a VGG16 CNN model to extract feature vectors from image blocks. Euclidean distance is used to measure similarity between feature vectors and detect matching blocks, indicating potential forgery. The proposed method is evaluated on the CoMoFoD dataset and achieves higher F1-scores than ResNet50 and EfficientNet models, detecting forged regions more accurately.
IMAGE RECOGNITION USING MATLAB SIMULINK BLOCKSETIJCSEA Journal
The world over, image recognition are essential players in promoting quality object recognition especially in emergency and search-rescue operation. In this paper precise image recognition system using Matlab Simulink Blockset to detect selected object from crowd is presented. The process involves extracting object
features and then recognizes it considering illumination, direction and pose. A Simulink model has been developed to eliminate the tiny elements from the image, then creating segments for precise object recognition. Furthermore, the simulation explores image recognition from the coloured and gray-scale images through image processing techniques in Simulink environment. The tool employed for computation
and simulation is the Matlab image processing blockset. The process comprises morphological operation method which is effective for captured images and video. The results of extensive simulations indicate that this method is suitable for application identifying a person from a crow. The model can be used in emergency and search-rescue operation as well as in medicine, information security, access control, law enforcement, surveillance system, microscopy etc.
Road network such as bridges, culverts have vital role before, during and after extreme events to reduce the vulnerability of the community being served. The bridge may be damaged due to severe accidents occurring over it. The bridge may be damaged fully or partially due to heavy and unexpected gale. The cost for the maintenance may be high enough and still no one can ensure us about safety of the bridges or any other structure in future. Whenever there is disaster, there is damage to the public property.
International Journal of Engineering and Science Invention (IJESI)inventionjournals
This document discusses a method for detecting defects in oil pipelines using image analysis and processing. A camera is sent through the pipeline to capture images, which are then analyzed using an unsupervised learning algorithm. The images are converted to raster images and the pixel groups are read. Blurred or unclear pixel groups would indicate defects in the pipeline at that location. The unsupervised algorithm clusters pixels into foreground and background to assess intensity values and more accurately detect defects, even in spots with imperfections. This method provides a way to automatically detect pipeline cracks and holes using computer vision to avoid costly manual inspections.
IRJET - A Systematic Observation in Digital Image Forgery Detection using MATLABIRJET Journal
This document summarizes a research paper that proposes a new method for detecting digital image forgeries using analysis of illumination inconsistencies. The method extracts texture and edge-based features from illuminant maps of face regions in an image. These features are then classified using machine learning to detect if faces are illuminated inconsistently, indicating tampering. The approach requires only minimal user interaction by specifying bounding boxes around faces. Evaluation shows the method achieves a 86% detection rate of spliced images, outperforming existing illumination-based approaches. The work presents an important step in reducing human interaction for illumination-based forgery detection.
This document summarizes a thesis presentation on an autonomous robotic system for nondestructive evaluation of asphalt pavement using deep learning. The system uses a robot equipped with vision sensors and an impact echo sensor. Deep learning models are used to detect cracks from images and classify crack severity from impact echo signals. The robot can autonomously collect data, perform real-time crack detection using onboard processing, and present severity maps quantifying the cracks. The system provides a low-cost way to inspect roads and quantify cracking issues. Future work could improve low-light crack detection, evaluate subsurface conditions, and integrate additional sensors to cover more area faster.
A CONCERT EVALUATION OF EXEMPLAR BASED IMAGE INPAINTING ALGORITHMS FOR NATURA...cscpconf
Image inpainting derives from restoration of art works, and has been applied to repair ancient
art works. Inpainting is a technique of restoring a partially damaged or occluded image in an
undetectable way. It fills the damaged part of an image by employing information of the
undamaged part according to some rules to make it look “reasonable” to human eyes. Digital
image inpainting is relatively new area of research, but numerous and different approaches to
tackle the inpainting problem have been proposed since the concept was first introduced. This
paper analyzes and compares the recent exemplar based inpainting algorithms by Minqin Wang
and Hao Guo et al. A number of examples on real images are demonstrated to evaluate the
results of algorithms using Peak Signal to Noise Ratio (PSNR)
Automatic 3D view Generation from a Single 2D Image for both Indoor and Outdo...ijcsa
This document discusses algorithms for automatically generating 3D video views from a single 2D image of both indoor and outdoor scenes. For indoor scenes, it segments the floor to determine the termination point for video generation. For outdoor scenes, it detects the vanishing point, which is used to calculate the distance to the termination point. The algorithms crop the input image to generate frames as it navigates up to the termination point, creating the effect of a 3D video view from a single 2D image with no need for human intervention. Experimental results on over 250 images demonstrated the effectiveness of the proposed methods.
The document describes a study that develops a program to obtain 3D point clouds from digital images without requiring specialized camera setup. The program analyzes images pixel-by-pixel within a user-defined area of interest. Reference points in the image area allow processing a limited region, reducing computation time. The program uses color values and edge detection to identify object pixels and represent them as point clouds. Sample images and their converted 3D models demonstrate the technique.
Fuzzy Logic Based Decision System For PCB Defects CorrectionIJERA Editor
he size, ease of automation, increasing durability and reliability of any circuit being developed. Defect & errors while developments are much obvious. Detecting them is primary part but taking decision for correction of same in testing specimen will be effective or not is much more crucial. Sometimes defect correction in the PCB is much more efficient then reprinting, in terms of time, resource and cost with respect to production. Making decision manually is tiresome & less efficient. So in this paper a novel method of decision making system based on fuzzy logic is proposed which takes decision whether the testing specimen should undergo correction or reprinting. Fuzzy based system takes decision in the way humans do. Results shown for the proposed system are quite promising in decision making.
Detection of a user-defined object in an image using feature extraction- Trai...IRJET Journal
The document proposes a method for detecting user-defined objects in images using feature extraction and training. The method combines contour detection, edge detection, k-means clustering, color identification, and image segmentation. It uses an original "source" object image to train the system to recognize and identify the target object in other images based on a feature set. The key steps include pre-processing images, extracting features like contours and edges, using k-means clustering to identify colors, and analyzing color and shape features to detect matching objects. The results demonstrate the ability to accurately detect target objects against complex backgrounds.
Identify Defects in Gears Using Digital Image ProcessingIJERD Editor
International Journal of Engineering Research and Development is an international premier peer reviewed open access engineering and technology journal promoting the discovery, innovation, advancement and dissemination of basic and transitional knowledge in engineering, technology and related disciplines.
Analysis of Digital Image Forgery Detection using Adaptive Over-Segmentation ...IRJET Journal
This document proposes two methods for detecting forged regions in digital images: adaptive over-segmentation and feature point matching. Adaptive over-segmentation divides the host image into irregular, non-overlapping blocks to reduce computational complexity compared to overlapping blocks. Feature points are then extracted from each block using SIFT and matched between blocks to identify labeled feature points that indicate suspected forgery regions. Finally, a forgery region extraction algorithm processes the labeled feature points and applies morphological operations to detect the forged regions in the host image. The proposed methods aim to address limitations of prior blocked-based forgery detection techniques by improving efficiency and ability to handle geometric transformations of forged areas.
Similar to CRACK DETECTION AND CLASSIFICATION IN CONCRETE STRUCTURE (20)
Design and Analysis of Hydraulic Actuator in a Typical Aerospace vehicle | J4...Journal For Research
An Aerospace Vehicle is capable of flight both within and outside the sensible atmosphere. An Actuation System is one of the most important Systems of an Aerospace vehicle. This paper study involves detailed study of various controls Actuation System and Design of a typical Hydraulic Actuation Systems. An actuator control system concerned with electrical, electronic or electro mechanical. Actuator control systems may take the form of extremely simple, manually-operated start-and-stop stations, or sophisticated, programmable computer systems. Hydraulic Actuation System contains Electro Hydraulic Actuators, Servo Valves, Feedback Sensing elements, Pump Motor package, Hydraulic Reservoir, Accumulator, various safety valves, Filters etc. The main objective of this study involves design of Hydraulic Actuator and selection of various other components for the Actuation Systems of an Aerospace Vehicle. Design of the system includes design of Hydraulic actuator and also the Modeling and Analysis of actuator using sophisticated Software.
Experimental Verification and Validation of Stress Distribution of Composite ...Journal For Research
This document summarizes an experimental study on the stress distribution of composite beams compared to metal beams under different support conditions. The study aims to analyze and compare the stress distribution of composite and metal beams using finite element analysis software and experimental testing with strain gauges and other tools. Based on a literature review, composite materials offer advantages over metals like lower weight and improved properties. The experimental results on stress distribution of composite and metal beams under different support conditions will be analyzed and compared to the finite element analysis results.
Image Binarization for the uses of Preprocessing to Detect Brain Abnormality ...Journal For Research
Computerized MR of brain image binarization for the uses of preprocessing of features extraction and brain abnormality identification of brain has been described. Binarization is used as intermediate steps of many MR of brain normal and abnormal tissues detection. One of the main problems of MRI binarization is that many pixels of brain part cannot be correctly binarized due to the extensive black background or the large variation in contrast between background and foreground of MRI. Proposed binarization determines a threshold value using mean, variance, standard deviation and entropy followed by a non-gamut enhancement that can overcome the binarization problem. The proposed binarization technique is extensively tested with a variety of MRI and generates good binarization with improved accuracy and reduced error.
A Research Paper on BFO and PSO Based Movie Recommendation System | J4RV4I1016Journal For Research
The objective of this work is to assess the utility of personalized recommendation system (PRS) in the field of movie recommendation using a new model based on neural network classification and hybrid optimization algorithm. We have used advantages of both the evolutionary optimization algorithms which are Particle swarm optimization (PSO) and Bacteria foraging optimization (BFO). In its implementation a NN classification model is used to obtain a movie recommendation which predict ratings of movie. Parameters or attributes on which movie ratings are dependent are supplied by user's demographic details and movie content information. The efficiency and accuracy of proposed method is verified by multiple experiments based on the Movie Lens benchmark dataset. Hybrid optimization algorithm selects best attributes from total supplied attributes of recommendation system and gives more accurate rating with less time taken. In present scenario movie database is becoming larger so we need an optimized recommendation system for better performance in terms of time and accuracy.
IoT based Digital Agriculture Monitoring System and Their Impact on Optimal U...Journal For Research
Although precision agriculture has been adopted in few countries, the greenhouse based modern agriculture industry in India still needs to be modernized with the involvement of technology for better production and cost control. In this paper we proposed a multifunction model for smart agriculture based on IoT. Due to variable atmospheric circumstances these conditions sometimes may vary from place to place in large farmhouse, which makes very difficult to maintain the uniform condition at all the places in the farmhouse manually. Soil and environment properties are sensed and periodically sent to cloud network through IoT. Analysis on cloud data is done for water requirement, total production and maintaining uniform environment conditions throughout greenhouse farm. Proposed model is beneficial for increase in agricultural production and for cost control and real time monitoring of farm.
A REVIEW PAPER ON BFO AND PSO BASED MOVIE RECOMMENDATION SYSTEM | J4RV4I1015Journal For Research
Recommendation system plays important role in Internet world and used in many applications. It has created the collection of many application, created global village and growth for numerous information. This paper represents the overview of Approaches and techniques generated in recommendation system. Recommendation system is categorized in three classes: Collaborative Filtering, Content based and hybrid based Approach. This paper classifies collaborative filtering in two types: Memory based and Model based Recommendation .The paper elaborates these approaches and their techniques with their limitations. The result of our system provides much better recommendations to users because it enables the users to understand the relation between their emotional states and the recommended movies.
HCI BASED APPLICATION FOR PLAYING COMPUTER GAMES | J4RV4I1014Journal For Research
This paper describes a command interface for games based on hand gestures and voice command defined by postures, movement and location. The system uses computer vision requiring no sensors or markers by the user. In voice command the speech recognizer, recognize the input from the user. It stores and passes command to the game, action takes place. We propose a simple architecture for performing real time colour detection and motion tracking using a webcam. The next step is to track the motion of the specified colours and the resulting actions are given as input commands to the system. We specify blue colour for motion tracking and green colour for mouse pointer. The speech recognition is the process of automatically recognizing a certain word spoken by a particular speaker based on individual information included in speech waves. This application will help in reduction in hardware requirement and can be implemented in other electronic devices also.
A REVIEW ON DESIGN OF PUBLIC TRANSPORTATION SYSTEM IN CHANDRAPUR CITY | J4RV4...Journal For Research
As we know the population of Chandrapur City has increased so far in this years and with that has increased the vehicles causing high traffic volume & rise in pollution. But the transportation system in Chandrapur City is still the same. To reduce the traffic volume & pollution, we have to study & design the new transportation system in Chandrapur City. The system would be as similar to Nagpur City with the implementation of Star City Buses. In this Study we would first compare the speed of various vehicles. Collection of population details of Chandrapur City, approximate number of vehicles running on road, collection of data with respect to Ticket fares in Nagpur City- whether it is according to Kilometers or places to be reached, calculation of Ticket Fares for Chandrapur City on the basis data collected. By all these, the best mode of transport in City can be studied. On the basis of above data collected from various respected fields, we will then proceed for the Design part of urban transport system in Chandrapur City. For Design purpose, firstly we have to mark the centre of the City, when the centre is decided; we will then select the Bus Terminus. From centre of the city, we would prefer to select the routes of the Buses. One route will be for the city side like Jatpura Gate, Pathanpura Gate. One route will be for Ballarpur going road. The other one for Mul going road, then next for Nagpur road. We could decide as many routes once we get the clear idea about all data. By getting all this details, the next step is to design the destination points of Buses. Then we have to design about the Bus bays, to reduce congestion in the particular intersections or Stops of bus. After the design also can suggest for Bus lanes. Implementation of Bus Rapid Transit System (BRT system) is the main aim behind to develop transportation mode of City. The design of the Transport System can be designed with the help of various software’s like AutoCAD and Revit.
A REVIEW ON LIFTING AND ASSEMBLY OF ROTARY KILN TYRE WITH SHELL BY FLEXIBLE G...Journal For Research
This document reviews different techniques for lifting and assembling rotary kiln tyres with shells. It discusses the current manual process using heavy cranes and labor, which is time-consuming and poses safety risks due to the heavy weights involved. The literature review covers various gripping techniques, cost-effective handling procedures, and analyses that can help design a safe lifting suspender for rotary kiln tyres. The conclusion indicates that lifting and assembly approaches as well as grasping principles need further study to develop improved solutions for safely handling the kiln components.
LABORATORY STUDY OF STRONG, MODERATE AND WEAK SANDSTONES | J4RV4I1012Journal For Research
Sandstones from seven different hydroelectric projects have been assessed to compare their water-related properties and engineering parameters and the comprehensive analysis has been presented. The study has been done by categorizing the sandstones in to three categories i.e. weak, moderate & strong sandstones. The study leads to four broad inferences: (1), there could be very large variation between two sandstones; e.g., here, sandstone S2, S4 & S5, vis-à-vis other two strong sandstones, is superior in all respects. (2), the four weak sandstones differ in respect of some – not all – properties and parameters. (3), none of the four weak sandstones is better than the other two in respect of all properties and parameters. (4), moderate sandstone shows higher values of shear strength parameters in comparison to all the sandstones (including stronger sandstones also) except S3 strong sandstone. In respect of individual properties, the grain density of all sandstones is similar, though their bulk densities, apparent porosity and water content show great variation. The weak, moderate and strong sandstones show qualitative difference in their uniaxial compressive strength and wave velocity (compression and shear, both); and the two are directly proportional. The study clearly demonstrates that there is no one-to-one correspondence between any two properties and parameters, but there is a diffused and/ or qualitative relationship between different sandstones, or certain properties and parameters of a particular variant.
DESIGN ANALYSIS AND FABRICATION OF MANUAL RICE TRANSPLANTING MACHINE | J4RV4I...Journal For Research
Need of rice transplanting machine is growing nowadays because of unique feature seeding in well sequence and well manners. This will save too much efforts of human being. Class of people who uses this kind of machine is farmers and they are having poor economic background. To feed growing population is a huge challenge. Importation of rice will lead to drain out the economy of the country. Mechanization of paddy sector will lead to higher productivity with releasing of work force to other sectors. The objective of this project is to design a paddy transplanting mechanism to transplant paddy seedling by small scale farmers in the country. Hence, this is considered as an activity that needed mechanization. For mechanization the modeling and simulation evaluated for hand operated rice seeding machine, which is help the farmers to planting more and more amount of rice in good quality with low energy consumption and less harm to the environment. India is predominately an agricultural country with rice as one of its main food crop. It Produce about 80 million tons rice annually which is about 22% of the world rice production. Culturally transplanting of young seeding is preferred over direct seeding for better yield and better crop management practice. But this operation requires large amount of manpower (about 400 Man-Hour/ha) and task is very laborious involving working in stopping posture and moving in muddy field.
AN OVERVIEW: DAKNET TECHNOLOGY - BROADBAND AD-HOC CONNECTIVITY | J4RV4I1009Journal For Research
DakNet, is an ad hoc network and an internet service planted on the applied science, which uses wireless technology to provide an asynchronous digital connectivity, it is the intermediate of wireless and asynchronous service that is the beginning of a technical way to universal broadband connectivity. The major process is it provides the broadband connectivity as wider. This paper broadly describes about the technology, architecture behind and its working principles.
Line following is one of the most important aspects of Robotics. A Line Follower Robot is an autonomous robot which is able to follow either a black or white line that is drawn on the surface consisting of a contrasting color. It is designed to move automatically and follow the made plot line. The path can be visible like a black line on a white surface or it can be invisible like a magnetic field. It will move in a particular direction Specified by the user and avoids the obstacle which is coming in the path. Autonomous Intelligent Robots are robot that can perform desired tasks in unstructured environments without continuous human guidance. It is an integrated design from the knowledge of Mechanical, Electrical, and Computer Engineering. LDR sensors based line follower robot design and Fabrication procedure which always direct along the black mark on the white surface. The robot uses several sensors to identify the line thus assisting the bot to stay on the track. The robot is driven by DC motors to control the movements of the wheels.
The project is to ask college related queries and get the responses through a chatbot an Artificial Conversational Entity. This System is a web application which provides answer to the query of the student. Students just have to query through the bot which is used for chatting. Students can chat using any format there is no specific format the user has to follow. This system helps the student to be updated about the college activities.
AN INTEGRATED APPROACH TO REDUCE INTRA CITY TRAFFIC AT COIMBATORE | J4RV4I1002Journal For Research
Coimbatore (11.0168°N,76.9558°E) is a fast developing cosmopolitan city with large number of industries and educational institutions. The development has lead to a large number of vehicles causing heavy traffic. The traffic congestion at Coimbatore has been a major problem which causes traffic jams and accidents. The major reason for traffic has been the mofussil buses that operate in the city. Around 1300 mofussil buses enter into the city, these buses play an important role in traffic congestion. The best solution is to construct a centralized bus stand at the outskirts of the city. This would reduce the traffic, accidents and also leads to development of the outskirts of the city. A suitable location near the city with sufficient road access to connecting cities has been chosen and the bus terminus has been designed, modeled with all facilities and features.
A REVIEW STUDY ON GAS-SOLID CYCLONE SEPARATOR USING LAPPLE MODEL | J4RV4I1001Journal For Research
Cyclone is the most commonly used device to separate dust particles from gas and dust flow. The performance of cyclone separator can be measured in terms of collection efficiency and pressure drop. Parameters like Inlet Flow velocity, the particle size distribution in feed, dimensions of inlet and outlet ducts and cyclone affects the performance of cyclone significantly. Various Mathematical models used for calculation of cut off diameter of separator, flow rate, target efficiency and no. of vortex inside the cyclone to design and study to check the performance of existing cyclone separator. Also new dimensions can be design with help of models. Here, in this study the efficiency achieved with Lapple model cumulatively 86.47%.
During past few years, brain tumor segmentation in CT has become an emergent research area in the field of medical imaging system. Brain tumor detection helps in finding the exact size and location of tumor. An efficient algorithm is proposed in this project for tumor detection based on segmentation and morphological operators. Firstly quality of scanned image is enhanced and then morphological operators are applied to detect the tumor in the scanned image. The problem with biopsy is that the patient has to be hospitalized and also the results (around 15%) give false negative. Scan images are read by radiologist but it's a subjective analysis which requires more experience. In the proposed work we segment the renal region and then classify the tumors as benign or malignant by using ANFIS, which is a non-invasive automated process. This approach reduces the waiting time of the patient.
USE OF GALVANIZED STEELS FOR AUTOMOTIVE BODY- CAR SURVEY RESULTS AT COASTAL A...Journal For Research
An extensive study of automotive body corrosion was conducted in Mumbai area to track corrosion performance of currently used materials of construction for automotive, especially cars with low end cost. The study consisted of a wide range of areas, starting from a closed car parking to several coastal and other humid regions such as Juhu Beach, Varsova beach and other adjoining areas. Data such as visible perforations, paint blisters, and surface rust were seen especially at vulnerable areas such as doors, mudguards, bonnet areas etc. Also, a comparison was done with low cost cars built with normal steel with those built using galvanized steels.
The main objective of our work is to deliver the goods at proper time by an unmanned drone. An Autonomous drone for delivering the goods such as bombs, medical kids, and foods mainly for military uses. This drone was used for dispatching the bombs and armed guns in battle field. And it is also used for delivering the medicines and foods for soldiers in our country borders.
SURVEY ON A MODERN MEDICARE SYSTEM USING INTERNET OF THINGS | J4RV3I12024Journal For Research
Since the population of the world is aging rapidly, how to provide appropriate health care to the elderly and unwell people becomes an important issue and draws high attention from medical, academic and industrial fields of the society. The Internet of Things (IoT) drives the evolution of the Internet and is regarded as a great potential to improve quality of life for the surging number of elderly people, significantly. As Android operating system gains immense popularity nowadays, it is a trend to make use of it for the wider access of IoT utility. This project presents a health monitoring system prototype based on IoT, with the increasing use of sensors by medical devices, remote and continuous monitoring of a patient’s health. This network of sensors and other mobile communication devices referred to as the Internet of Things for Medical Devices (IoT-MD), is poised to revolutionize the functioning of the healthcare industry. Untimed medicine administration can always show adverse effects on the health of the patients. The proposed system is designed to help these patients to take the required medicine in the right proportion at the right time. The basic ideology is integrating the principle of IoT with weight-based slot sensing on a normal pillbox. To make it more state-of-the-art, it is inbuilt with a Wi-Fi module for alerting the patient and also the chemist at the needed instant using IoT.
How to Make a Field Mandatory in Odoo 17Celine George
In Odoo, making a field required can be done through both Python code and XML views. When you set the required attribute to True in Python code, it makes the field required across all views where it's used. Conversely, when you set the required attribute in XML views, it makes the field required only in the context of that particular view.
Walmart Business+ and Spark Good for Nonprofits.pdfTechSoup
"Learn about all the ways Walmart supports nonprofit organizations.
You will hear from Liz Willett, the Head of Nonprofits, and hear about what Walmart is doing to help nonprofits, including Walmart Business and Spark Good. Walmart Business+ is a new offer for nonprofits that offers discounts and also streamlines nonprofits order and expense tracking, saving time and money.
The webinar may also give some examples on how nonprofits can best leverage Walmart Business+.
The event will cover the following::
Walmart Business + (https://business.walmart.com/plus) is a new shopping experience for nonprofits, schools, and local business customers that connects an exclusive online shopping experience to stores. Benefits include free delivery and shipping, a 'Spend Analytics” feature, special discounts, deals and tax-exempt shopping.
Special TechSoup offer for a free 180 days membership, and up to $150 in discounts on eligible orders.
Spark Good (walmart.com/sparkgood) is a charitable platform that enables nonprofits to receive donations directly from customers and associates.
Answers about how you can do more with Walmart!"
This document provides an overview of wound healing, its functions, stages, mechanisms, factors affecting it, and complications.
A wound is a break in the integrity of the skin or tissues, which may be associated with disruption of the structure and function.
Healing is the body’s response to injury in an attempt to restore normal structure and functions.
Healing can occur in two ways: Regeneration and Repair
There are 4 phases of wound healing: hemostasis, inflammation, proliferation, and remodeling. This document also describes the mechanism of wound healing. Factors that affect healing include infection, uncontrolled diabetes, poor nutrition, age, anemia, the presence of foreign bodies, etc.
Complications of wound healing like infection, hyperpigmentation of scar, contractures, and keloid formation.
Beyond Degrees - Empowering the Workforce in the Context of Skills-First.pptxEduSkills OECD
Iván Bornacelly, Policy Analyst at the OECD Centre for Skills, OECD, presents at the webinar 'Tackling job market gaps with a skills-first approach' on 12 June 2024
The chapter Lifelines of National Economy in Class 10 Geography focuses on the various modes of transportation and communication that play a vital role in the economic development of a country. These lifelines are crucial for the movement of goods, services, and people, thereby connecting different regions and promoting economic activities.
This presentation was provided by Racquel Jemison, Ph.D., Christina MacLaughlin, Ph.D., and Paulomi Majumder. Ph.D., all of the American Chemical Society, for the second session of NISO's 2024 Training Series "DEIA in the Scholarly Landscape." Session Two: 'Expanding Pathways to Publishing Careers,' was held June 13, 2024.
ISO/IEC 27001, ISO/IEC 42001, and GDPR: Best Practices for Implementation and...PECB
Denis is a dynamic and results-driven Chief Information Officer (CIO) with a distinguished career spanning information systems analysis and technical project management. With a proven track record of spearheading the design and delivery of cutting-edge Information Management solutions, he has consistently elevated business operations, streamlined reporting functions, and maximized process efficiency.
Certified as an ISO/IEC 27001: Information Security Management Systems (ISMS) Lead Implementer, Data Protection Officer, and Cyber Risks Analyst, Denis brings a heightened focus on data security, privacy, and cyber resilience to every endeavor.
His expertise extends across a diverse spectrum of reporting, database, and web development applications, underpinned by an exceptional grasp of data storage and virtualization technologies. His proficiency in application testing, database administration, and data cleansing ensures seamless execution of complex projects.
What sets Denis apart is his comprehensive understanding of Business and Systems Analysis technologies, honed through involvement in all phases of the Software Development Lifecycle (SDLC). From meticulous requirements gathering to precise analysis, innovative design, rigorous development, thorough testing, and successful implementation, he has consistently delivered exceptional results.
Throughout his career, he has taken on multifaceted roles, from leading technical project management teams to owning solutions that drive operational excellence. His conscientious and proactive approach is unwavering, whether he is working independently or collaboratively within a team. His ability to connect with colleagues on a personal level underscores his commitment to fostering a harmonious and productive workplace environment.
Date: May 29, 2024
Tags: Information Security, ISO/IEC 27001, ISO/IEC 42001, Artificial Intelligence, GDPR
-------------------------------------------------------------------------------
Find out more about ISO training and certification services
Training: ISO/IEC 27001 Information Security Management System - EN | PECB
ISO/IEC 42001 Artificial Intelligence Management System - EN | PECB
General Data Protection Regulation (GDPR) - Training Courses - EN | PECB
Webinars: https://pecb.com/webinars
Article: https://pecb.com/article
-------------------------------------------------------------------------------
For more information about PECB:
Website: https://pecb.com/
LinkedIn: https://www.linkedin.com/company/pecb/
Facebook: https://www.facebook.com/PECBInternational/
Slideshare: http://www.slideshare.net/PECBCERTIFICATION
ISO/IEC 27001, ISO/IEC 42001, and GDPR: Best Practices for Implementation and...
CRACK DETECTION AND CLASSIFICATION IN CONCRETE STRUCTURE
1. Journal for Research | Volume 02 | Issue 04 | June 2016
ISSN: 2395-7549
All rights reserved by www.journalforresearch.org 29
Crack Detection and Classification in Concrete
Structure
Kaushik Bose Prof.(Dr.) Samir Kumar Bandyopadhyay
Department of Computer Science & Engineering Department of Computer Science & Engineering
University of Calcutta, India University of Calcutta, India
Abstract
This paper presents crack detection in concrete structure based on fuzzy logic. Safety inspection of concrete structures is very
important since it is closely related with the structural health and reliability. Automated structural health monitoring system
becomes necessity in recent years that encourages various researches to be going on in this area. Cheap availability of digital
cameras makes research work in this field easier. This paper presents digital image processing and fuzzy logic based efficient
crack detection technique in concrete structure. Here features from digital image of concrete structure are extracted by using
morphological image processing technique and then extracted features are fed to fuzzy logic to accurately identify the crack.
Keywords: Cracks, Crack detection, Crack filling, Restoration, Texture synthesis
_______________________________________________________________________________________________________
I. INTRODUCTION
Crack is a line on the surface of something along which it has split without breaking apart. All concrete is vulnerable to cracking,
both in the plastic state and in the hardened state. All concrete has a natural tendency to crack due to either internal or external
factors, generally influenced by materials, design, construction, service loads and exposure conditions either individually or in
combination. Cracks in concrete structure can be broadly classified into two categories structural cracks and non-structural
cracks. Structural cracks are caused by applied loads, whereas non-structural cracks are influenced by the result the constituent
materials of the concrete, and other factors such as ambient temperature, humidity, overall exposure conditions, construction
practices and restraint effects of either internal or external nature.
Crack detection is very important in concrete structure because it is directly related to the threat of human beings. We can
judge the condition of the structural health objectively by acquiring and processing the concrete structure‘s image. One of the
way in judging the structural health is to examine a crack on the surface of the structure. Since the condition of a concrete
structure can be easily and directly identified by inspecting the surface crack, the crack assessment should be done on a regular
basis to ensure durability and safety. So many researchers have studied the automated concrete crack detecting method. Concrete
structure images are acquired by using CMOS line scan digital cameras, laser scanner, and microwave. So, by applying the
image processing technique to detect crack in concrete structure is our documents main goal. So an automated crack detection
method can also reduce the cost of maintenance and time consumed for structural health inspection and monitoring by a large
margin. Crack detection based on image processing can also provide maintenance easily in the inaccessible regions of concrete
structure.
II. RELATED WORKS
There are multiple previous research works on Crack detection on concrete structure as well digitized paintings. A brief
description of some most recent researches are given here.
Yamaguchi and Hashimoto [1] proposed a fast crack detection method for large-size concrete surface images using
percolation-based image processing. The percolation process is based on the physical model of liquid permeation, is started from
each pixel. Depending on the shape of the percolated region, the pixel is considered as a crack pixel or not. The process proposed
provide good result for detecting cracks but the computation time is very large as percolation process starts from each pixels and
huge computation power is also needed.
Giakoumis, Nikolaidis and Pitas [2], proposed a method to detect cracks in digitized paintings. They use morphological
operation on images to detect cracks and the misidentified thin dark strokes are excluded by hue and saturation as well as neural
network. Still, many irrelevant objects are misidentified as cracks. They also described different methods for crack filling.
Wenyu Zhang, Zhenjiang Zhang, Dapeng Qi, and Yun Liu [3] proposed automatic crack detection and classification method
for subway tunnel safety monitoring system. To eliminate the unnecessary local small valleys, they applied an average image-
smoothing filter to pre-process the original gray-scale images. They applied top-hat transformation to detect cracks and they also
perform an extensive crack classification.
Gavilán, Balcones, Marcos, O Llorca, Sotelo, Parra, Ocaña, Aliseda, Yarza, Amírola [4] proposed an adaptive Road Crack
Detection System by Pavement Classification. A vehicle equipped with line scan cameras is used to store the digital images that
will be further processed to identify road cracks. They proposed Non-crack features detection method to mask areas of the
2. Crack Detection and Classification in Concrete Structure
(J4R/ Volume 02 / Issue 04 / 07)
All rights reserved by www.journalforresearch.org 30
images with joints, sealed cracks and white painting that usually generate false positive cracking and provide a seed-based
approach to deal with road crack detection combining Multiple Directional Non-Minimum Suppression (MDNMS) with a
symmetry check. The system performs well for road crack detection.
Miss Vidya Vinayak Khandare and Prof. Mr. Nitin B. Sambre [5] proposed a crack detection and removal method in digitized
painting. The cracks are identified and detected by Gabor which is an integrated methodology for removal of cracks. First, they
filter the selected crack image using 8 differently oriented Gabor filters for the purpose of feature extraction to represent a crack
network from sets of local orientation features. They used resultant features for crack filling with median filter and weighted
median filter. Their methodology has been shown to perform well on digitized paintings suffering from cracks.
Gajanan K.Choudhary and Sayan Dey [6] proposed crack detection in concrete surface using image processing based on fuzzy
logic and neural network. They use feature extraction that is crack like regions detection based on edge detection procedure and
then apply fuzzy and neural network approach to classify crack and noise.
Fujita et al. [7] proposed a method which involves image pre-processing using subtraction of smooth images and a hessian
matrix based line filter then cracks are detected by applying a threshold operation.
III. PROPOSED METHOD
The total procedure of crack detection and classification consists of five steps as shown in figure 1
Fig. 1: Flowchart of the proposed method
Image Acquisition:A.
Images of concrete structure can be acquired by using CMOS line scan digital cameras. For image acquisition purpose a machine
that can roll on with built in cameras can be used such that when machine moves on the concrete surface it captures images for
detection purpose. In case of huge concrete structure or historical buildings of concrete, picture taken from satellite can also be
used.
In our research work total 30 images are used and most of them were downloaded from different sources by searching internet.
In the process of image collection for our work we only considered the images that do not have any other object other than
concrete structure because if images contain other objects then that object can be considered as crack. Also cracks has to be at
least visible by human eye though there may be huge amount of noises else no crack will be detected by this method.
Image Pre-processing:B.
The original image may contain some useless details that can be removed by using some basic image processing that we consider
here as image pre-processing. Various steps of image pre-processing used here, all of which are given below.
Image Resizing:1)
First all the images are resized to the width of 512 pixels and the height was adjusted such that original image aspect ratio
maintained to maintain uniformity of the system such that all images have same criteria for crack detection procedure.
Maintaining uniformity is necessary in image classification stage where fuzzy logic is used.
RGB to Grayscale Image Conversion:2)
For pre-processing of image, the RGB image first of all is converted into grayscale image which makes the process much easier,
because here we need not to maintain three matrixes for three colour component red(R), green(G), Blue(B). In grayscale image
each pixel is represented by a single value between 0 to 255. This value is called luminance or intensity of that pixel. The
standard NTSC conversion formula that is used for calculating the effective luminance of a pixel:
Image Smoothing:3)
Original image may contain some useless details. Images can also be affected by some extent of noise, that is unexplained
variation in data disturbances in image intensity which are either uninterpretable or not of interest. Simply by applying linear
averaging filter for image smoothing a huge percentage of these unintended or useless details and noise can be removed.
3. Crack Detection and Classification in Concrete Structure
(J4R/ Volume 02 / Issue 04 / 07)
All rights reserved by www.journalforresearch.org 31
Although we cannot remove all unintended details that is why we need to classify detected local dim region as either crack or not
by using fuzzy logic. We use a 5x5 moving average filter to replace each pixel by the average of pixel values in a 5x5 square, or
window centred on that pixel. The result is to reduce noise in the image, but also to blur the edges of the objects in the image.
Figure-2 and Figure-3 shows 3D graph of original image and smoothed image respectively. The original image has many needle-
like peaks and valleys, which are caused by isolated pixels with high or low gray levels. The peaks are very sharp in original
image because maximum amount of noises are of one or two pixels. So an averaging filter will effectively remove these noises.
Fig. 2: Original image's intensity graph Fig. 3: Smoothed image's intensity graph
IV. DETECTION OF LOCAL DIM REGIONS
The process we used to detect local dim regions is based on the property that the Brightness in the crack regions is dimmer than
background.
The method proposed here is based on the previously said property. So cracks with same brightness as of the background of
the image are very difficult to detect. By the above property of crack, we can say that cracks have low luminance that is intensity
values of the crack pixels are minimum. So crack detection process is applied on the intensity component of the image. A crack
detection procedure based on bottom-hat transformation is proposed here. Bottom-hat transformation is morphological image
processing which is used to extract image components such as the shape of cracks. The bottom-hat transformation is based on
another morphological operation ‗closing‘ of an image. Thus bottom-hat transform, is defined as the residual of a closing
compared to the original image, i.e.
( )
Where denotes morphological closing of the image f and b is the structuring element.
The closing of a grayscale or binary image A by a structuring element B is the erosion of the dilation of that image,
( )
Where and denotes dilation and erosion respectively.
The bottom-hat transform returns an image, containing the objects or elements that are smaller than or equal to the structuring
element, and are darker than their surroundings. The structuring element plays key role in detecting cracks properly. Selection of
structuring element is based on two parameters:
Type of the structuring element i.e. diamond, disk, line, rectangle, square etc.
Size of the structuring element e.g. specifying the width of the square type element
The size of the structuring element is chosen such that it can cover the width of the widest crack in the image. As we resized
original image to maintain uniformity of the process here we are using a square type structuring element with width of 15 pixels.
Figure 4: Smoothed Grayscale Image Figure 5: Bottom-Hat Transformed Image
4. Crack Detection and Classification in Concrete Structure
(J4R/ Volume 02 / Issue 04 / 07)
All rights reserved by www.journalforresearch.org 32
V. CRACK SEPARATION
The output of the bottom-hat transform is a grayscale image where pixels with higher intensity value are considered as crack
pixels. So to separate crack from rest of the image thresholding operation on bottom-hat transformed grayscale image in done.
For thresholding operation is done based one the global image threshold level value using Otsu's method which chooses the
threshold value to minimize the intra-class variance of the thresholded black and white pixels. This turns out to be the same as
maximizing the between-class variance. Operates directly on the graylevel histogram, so it‘s fast (once the histogram is
computed). The output image replaces all pixels in the input image with luminance greater than threshold level obtained by using
Otsu‘s [8] method with the value 1 (white) and replaces all other pixels with the value 0 (black).
OTSU: ASSUMPTIONS:A.
Histogram (and the image) is bimodal.
No use of spatial coherence, nor any other notion of object structure.
Assumes stationary statistics, but can be modified to be locally adaptive. (exercises)
Assumes uniform illumination (implicitly), so the bimodal brightness behavior arises from object appearance differences only.
The weighted within-class variance is:
Where the class probabilities are estimated as:
And the class means are given by:
Finally, the individual class variances are:
Now, we could actually stop here. All we need to do is just run through the full range of t values [1,256] and pick the value
that minimizes .
But the relationship between the within-class and between-class variances can be exploited to generate a recursion relation that
permits a much faster calculation.
After some algebra, we can express the total variance as:
Since the total is constant and independent of t, the effect of changing the threshold is merely to move the contributions of the
two terms back and forth.
Thus Otsu shows us that minimizing the intra-class variance is the same as maximizing inter-class variance.
Figure 6: Bottom-Hat Thresholded image
w
2
(t) q1
(t) 1
2
(t) q2
(t) 2
2
(t)
1
2
( t) [i 1
(t)]
2 P( i)
q1
(t)i1
t
2
2
( t) [i 2
(t)]
2 P (i)
q2
(t)i t 1
I
5. Crack Detection and Classification in Concrete Structure
(J4R/ Volume 02 / Issue 04 / 07)
All rights reserved by www.journalforresearch.org 33
Crack Identification:B.
After the thresholding operation in the previous section we are able to remove most of the miss-identified regions but still some
irrelevant unintended image details which we call as noise are preserved as cracks. All the connected regions of the image are
considered as an object. So an object can be either crack or noise. So crack identification is very important and final step of our
process. This crack identification consists of three stages:
Detection of objects and its necessary properties
Creation of Fuzzy Model and finding fuzzy output value for each object
Convert the fuzzy output value to crisp output value
Detection of Objects with its Necessary Properties:C.
Objects of an image are basically connected components found in the binary image. Connected-component labelling is used to
detect connected regions in binary digital image. In image processing and image recognition, pixel connectivity is the way in
which pixels in 2-dimensional images relate to their neighbours. Here we use 8-connected neighbourhood technique to find
connected components in an image. In an 8-connected neighbourhood, all of the pixels that touch the pixel of interest are
considered, including those on the diagonals. This means that if two adjoining pixels are on, they are part of the same object,
regardless of whether they are connected along the horizontal, vertical, or diagonal direction.
Fig. 7: A 8-Connected Neighbourhood model Fig. 8: Image With Identified Objects
Now we need to identify some object properties which will form the basis to the fuzzy model of crack detection. So the
properties must be chosen such that they all together provide substantial difference between crack and noise. So only one or two
properties may not be sufficient to differentiate between crack or noise that all the three properties need to be considered
together. In our model we use three properties to detect crack which are given below:
Area:1)
Area is a scalar value which specifies total number of pixels in a particular object. Area is chosen because in general number of
pixels in crack i.e. area is higher than noise.
Ratio of Major and Minor Axis:2)
‗MajorAxisLength‘ is a scalar value that specifies the length (in pixels) of the major axis of the ellipse that has the same
normalized second central moments as the region where as ‗MinorAxisLength‘ is a scalar value that specifies the length (in
pixels) of the minor axis of the ellipse that has the same normalized second central moments as the region. We use the ratio of
‗MajorAxisLength‘ and ‗MinorAxisLength‘. This property is chosen such that in general cracks elongated structure so the ratio
of major and minor axes lengths should be higher compared to noise.
Ratio of Boundingbox-area and object-area:3)
'Bounding Box' is the smallest rectangle containing the object. So the bounding box-area is the scaler value which specifies the
number of pixel can have in that bounding box, we will get this easily by multiplying the width and height of the bounding box.
Object-area is the area specified above that is the number of pixel in an object. We use this property because though in general
cracks are elongated structure but in some cases cracks may have branches in that cases ratio of major and minor axes will be
lower and also in some cases noises can also have higher area, so in these situation ratio of boundingbox-area and object-area
will be higher in case of crack than noise.
Fuzzy Logic Model:D.
Fuzzy logic, introduced by L. A. Zadeh [9] in 1965. Fuzzy logic had however been studied since the 1920s, as infinite-valued
logic—notably by Łukasiewicz and Tarski. Over the past few decades, fuzzy logic has been used in a wide range of problem
domains such as process control, management and decision making, operations research, economies and, for this paper the most
important, pattern recognition and classification. The natural description of problems, in linguistic terms, rather than in terms of
relationships between precise numerical values is the major advantage of this theory.
6. Crack Detection and Classification in Concrete Structure
(J4R/ Volume 02 / Issue 04 / 07)
All rights reserved by www.journalforresearch.org 34
Fuzzy logic is almost synonymous with the theory of fuzzy sets, a theory which relates to classes of objects with un-sharp
boundaries in which membership is a matter of degree that is a fuzzy set is a set without a crisp, clearly defined boundary. It can
contain elements with only a partial degree of membership. Fuzzy logic includes 0 and 1 as extreme cases of truth (or "fact") but
also includes the various states of truth in between so that, for example, fuzzy logic also permits in-between values like 0.4 and
0.56 etc.
We use MATLAB‘s fuzzy logic toolbox to create Mamdani-type fuzzy logic model to classify crack and noise. Mamdani's
fuzzy inference method expects the output membership functions to be fuzzy sets. After the aggregation process, there is a fuzzy
set for each output variable that needs defuzzification. For our fuzzy logic model the input variables are ‗Area‘, ‗Major-Minor
Axes Ratio‘ and ‗Bounding box Area-Object Area Ratio‘. So each object‘s these three properties are feed to fuzzy model to get
fuzzy output. The range of each variable is given in the table. The input variables ‗Area‘, ‗Major-Minor Axes Ratio‘ and
‗Bounding box Area-Object Area Ratio‘ have three, two and two subsets respectively where the output has two subsets. Each
subset needs one single membership function. The membership functions used here for all the input variables and output variable
are trapezoidal-type. Trapezoidal membership function is defined by a lower limit a, an upper limit d, a lower support limit b,
and an upper support limit c, where a < b < c < d.
Fig. 9: Trapezoidal membership Function Representation
Table – 1
Membership function values For the fuzzy logic Model
Variables Variable Range Membership Function
Trapezoidal Value
a b c d
‘Area’ [0-20000]
Low 0 0 200 400
Medium 200 400 600 2000
High 600 20000 20000 20000
‘Major-Minor Axes Ratio’ [0-200]
Low 0 0 4.5 5.5
High 4.5 5.5 200 200
‘BoundingboxArea-ObjectArea Ratio’ [0-500]
Low 0 0 5 6
High 5 6 500 500
‘Output’ [0-1]
Noise 0 0 0.45 0.55
Crack 0.45 0.55 1 1
Fuzzy sets and fuzzy operators are the subjects and verbs of fuzzy logics. If x is A Then y is B where x and y are fuzzy
variables and A and B are fuzzy values. The if-part of the rule "x is A" is called the antecedent or premise, while the then-part of
the rule "y is B" is called the consequent or conclusion. Statements in the antecedent (or consequent) parts of the rules may well
involve fuzzy logical connectives such as ‗AND ‗OR‘ and ‗NOT‘. For our Fuzzy model we only use ‗AND‘ operator. The rules
have been given in table-2.
Table – 2
Fuzzy Inference Rule Set
Rule No. Area Major-Minor Axes Ratio BoundingboxArea-ObjectArea Ratio Output
1 High High Crack
2 High Low High Crack
3 Medium High Crack
4 Medium Low High Crack
5 Low High Noise
6 Low High Noise
7. Crack Detection and Classification in Concrete Structure
(J4R/ Volume 02 / Issue 04 / 07)
All rights reserved by www.journalforresearch.org 35
Fuzzy output value to crisp output value Conversion
As we are using Mamdani's fuzzy inference method for our system we will get fuzzy output value that is output value can be
any value from 0 to 1 this means output value can be fraction type. But we need crisp output that is 1 for crack and 0 for noise.
For this defuzzification process we need a threshold value such that below that value output means objet is noise else crack. To
obtain the threshold value we need to consider two criteria.
We want to increase the detection rate to 1 and decrease detection error to 0. But Detection Rate and Detection error are
disproportional to each other. But we need to give priority to high detection rate over reduced detection error because if some
cracks are not detected it may bring casualties for human being. So taking both the criteria in concern we are getting best
performance at threshold value of 0.74 which gives 99.2% accuracy in detection rate with 1.95% detection error. Now one thing
we must be consider that if some very small portion of a bigger crack is not detected we are neglecting this because as main
crack is detected then it will go for the manual inspection to civil engineering department.
Algorithm:E.
1) STEP 1: Read the image.
2) STEP 2: If the image is not grayscale than convert it to grayscale image. Resize the image to maintain uniformity and
perform image smoothing by applying linear averaging filter.
3) STEP 3: Define the structural element by specifying structural element type and size. In most of the cases square type
structural element is beneficial for crack detection and defines its size approximately as the size of the widest crack width.
4) STEP 4: Perform the bottom-hat transformation using the defined structural element in step-3.
5) STEP 5: Compute the global image threshold level value using Otsu‘s [8] method which chooses the threshold value to
minimize the intra-class variance of the thresholded black and white pixels.
6) STEP 6: Convert the bottom-hat transformed image into binary image by thresholding using the threshold level value from
step-5.
7) STEP 7: Identify each objects that is each connected component in the image and find its properties like ‗Area‘, ‗Major-
Minor Axes Ratio‘ and ‗BoundingboxArea-ObjectArea Ratio‘.
8) STEP 8: Use the properties stated in step-7 as the input variables to create a fuzzy model based on membership function
value shown in table-1 and ‗if-then-else‘ inference rule set in table-2.
9) STEP 9: Feed each objects properties to the fuzzy model created in step-8 to get fuzzy output.
10) STEP 10: Convert to fuzzy output to crisp output based on the threshold value 0.74 to identify which is crack and which is
noise.
VI. EXPERIMENTAL RESULTS
Result Set 1:A.
Fig. 10: Original Image Fig. 11: Grayscale Image
8. Crack Detection and Classification in Concrete Structure
(J4R/ Volume 02 / Issue 04 / 07)
All rights reserved by www.journalforresearch.org 36
Fig. 12: Smoothed Grayscale image Fig. 13: Bottom-Hat Transformed image
Fig. 14: Bottom-Hat Thresholded Image Fig. 15: Image With Identified Objects
Fig. 16: Image with Identified Cracks
Result Set -2:B.
Fig. 17: Original Image Fig. 18: Grayscale Image
9. Crack Detection and Classification in Concrete Structure
(J4R/ Volume 02 / Issue 04 / 07)
All rights reserved by www.journalforresearch.org 37
Fig. 19: Smoothed Grayscale image Fig. 20: Bottom-Hat Transformed image
Fig. 21: Bottom-Hat Thresholded Image Fig. 22: Image With Identified Objects
Fig. 23: Image with Identified Cracks
VII.CONCLUSIONS
This paper presents a crack detection and classification technique for concrete structure based on the images of the concrete
surface. Images are analyzed by applying several images processing technique and finally crack classification is done by
applying fuzzy logic. This method of crack detection and classification can also be applied on several different situations other
than concrete surface like cracks on paintings. In the image classification process, we are not considering whole image at a time
to classify all the cracks in the image instead we apply object approach that is each connected component in the image has been
checked individually, by doing this we are getting more accurate result though it is little more time consuming than identifying
all the cracks in the image at a time.
REFERENCES
[1] Yamaguchi, T.; Hashimoto, S. ―Fast crack detection method for large-size concrete surface images using percolation-based image processing‖. Mach. Vis.
Appl. 2010, 21, 797–809.
[2] Giakoumis, I.; Nikolaidis, N.; Pitas, I. ―Digital image processing techniques for the detection and removal of cracks in digitized paintings‖. IEEE Trans.
Image Process. 2006, 15, 178–188.
[3] Wenyu Zhang; Zhenjiang Zhang; Dapeng Qi; and Yun Liu. ―Automatic Crack Detection and Classification Method for Subway Tunnel Safety
Monitoring‖. Sensors 2014, 14, 19307-19328
[4] Gavilán, M.; Balcones, D.; Marcos, O.; Llorca, D.F.; Sotelo, M.A.; Parra, I.; Ocaña, M.; Aliseda, P.; Yarza, P.; Amírola, A. ―Adaptive Road Crack
Detection System by Pavement Classification‖. Sensors 2011, 11, 9628–9657.
[5] Khandare Vidya Vinayak Khandare; Sambre Nitin B. ―Detection & Removal of Cracks in Digitized Paintings Based on Image Processing‖. International
Journal of Engineering Research & Technology (IJERT)2014 ISSN: 2278-0181 Vol. 3 Issue 1, 2014
10. Crack Detection and Classification in Concrete Structure
(J4R/ Volume 02 / Issue 04 / 07)
All rights reserved by www.journalforresearch.org 38
[6] Gajanan K. Choudhary and Sayan Dey. ―Crack Detection in Concrete Surfaces using Image Processing, Fuzzy Logic, and Neural Networks‖. 2012 IEEE
fifth International Conference on Advanced Computational Intelligence(ICACI) October 18-20, 2012
[7] Byoung Jik Lee, and Hosin ―David‖ Lee, ―Position-Invariant Neural Network for Digital Pavement Crack Analysis,‖ Computer-Aided Civil and
Infrastructure Engineering, Volume 19, Issue 2, pages 105–118, March 2004.
[8] N.Otsu (1979) ―A threshold selection method form gray-level histograms‖. Proceedings of the 1986 IEEE Transactions Systems, Man and Cybernetics,
Vol.9, No. 1, 62-66
[9] L. A. Zadeh, "Fuzzy sets," Information and Control, vol. 8, pp. 338-353, 1965.
[10] Y. Fujita, and Y. Hamamoto, ―A robust method for automatically detecting cracks on noisy concrete surfaces,‖ Next-Generation Applied Intelligence. 22nd
International Conference on Industrial, Engineering and Other Applications of Applied Intelligent Systems IEA/AIE 2009, pp. 76–85, June 2009, Tainan,
Taiwan.
[11] Rafael C. Gonzalez, Richard E. Woods and Steven L.Eddins ―Digital Image Processing Using Matlab,‖ Pearson Education, Second Impression,2007.
[12] MATLAB Functions in Fuzzy Logic Toolbox, www.mathworks.in/help/fuzzy/functionlist.html