My presentation on conference ELITECH 2011. It is on tracking colored objects. Presentation and paper won the award for best contribution in area of computer science from Slovak IT SAV society.
Saliency-based Models of Image Content and their Application to Auto-Annotati...Jonathon Hare
Multimedia and the Semantic Web / European Semantic Web Conference 2005, Heraklion, Crete. 29th May 2005.
http://eprints.soton.ac.uk/260954/
In this paper, we propose a model of automatic image annotation based on propagation of keywords. The model works on the premise that visually similar image content is likely to have similar semantic content. Image content is extracted using local descriptors at salient points within the image and quantising the feature-vectors into visual terms. The visual terms for each image are modelled using techniques taken from the information retrieval community. The modelled information from an unlabelled query image is compared to the models of a corpus of labelled images and labels are propagated from the most similar labelled images to the query image
Scale Saliency: Applications in Visual Matching,Tracking and View-Based Objec...Jonathon Hare
Distributed Multimedia Systems 2003 / Visual Information Systems 2003, Florida International University, Miami, Florida, USA, 24 - 26 Sep 2003.
http://eprints.soton.ac.uk/258295/
In this paper, we introduce a novel technique for image matching and feature-based tracking. The technique is based on the idea of using the Scale-Saliency algorithm to pick a sparse number of ‘interesting’ or ‘salient’ features. Feature vectors for each of the salient regions are generated and used in the matching process. Due to the nature of the sparse representation of feature vectors generated by the technique, sub-image matching is also accomplished. We demonstrate the techniques robustness to geometric transformations in the query image and suggest that the technique would be suitable for view-based object recognition. We also apply the matching technique to the problem of feature tracking across multiple video frames by matching salient regions across frame pairs. We show that our tracking algorithm is able to explicitly extract the 3D motion vector of each salient region during the tracking process, using a single uncalibrated camera. We illustrate the functionality of our tracking algorithm by showing results from tracking a single salient region in near real-time with a live camera input.
Content-based image retrieval using a mobile device as a novel interfaceJonathon Hare
Storage and Retrieval Methods and Applications for Multimedia 2005, San Jose, California, USA, 18 - 19 Jan 2005.
http://eprints.soton.ac.uk/260419/
This paper presents an investigation into the use of a mobile device as a novel interface to a content-based image retrieval system. The initial development has been based on the concept of using the mobile device in an art gallery for mining data about the exhibits, although a number of other applications are envisaged. The paper presents a novel methodology for performing content-based image retrieval and object recognition from query images that have been degraded by noise and subjected to transformations through the imaging system. The methodology uses techniques inspired from the information retrieval community in order to aid efficient indexing and retrieval. In particular, a vector-space model is used in the efficient indexing of each image, and a two-stage pruning/ranking procedure is used to determine the correct matching image. The retrieval algorithm is shown to outperform a number of existing algorithms when used with query images from the mobile device.
Bridging the Semantic Gap in Multimedia Information Retrieval: Top-down and B...Jonathon Hare
Mastering the Gap: From Information Extraction to Semantic Representation / 3rd European Semantic Web Conference, Budva, Montenegro. May 2006.
http://eprints.soton.ac.uk/262737/
Semantic representation of multimedia information is vital for enabling the kind of multimedia search capabilities that professional searchers require. Manual annotation is often not possible because of the shear scale of the multimedia information that needs indexing. This paper explores the ways in which we are using both top-down, ontologically driven approaches and bottom-up, automatic-annotation approaches to provide retrieval facilities to users. We also discuss many of the current techniques that we are investigating to combine these top-down and bottom-up approaches.
Mind the Gap: Another look at the problem of the semantic gap in image retrievalJonathon Hare
Multimedia Content Analysis, Management and Retrieval 2006, San Jose, California, USA, 17 - 19 Jan 2006
http://eprints.soton.ac.uk/261887/
This paper attempts to review and characterise the problem of the semantic gap in image retrieval and the attempts being made to bridge it. In particular, we draw from our own experience in user queries, automatic annotation and ontological techniques. The first section of the paper describes a characterisation of the semantic gap as a hierarchy between the raw media and full semantic understanding of the media's content. The second section discusses real users' queries with respect to the semantic gap. The final sections of the paper describe our own experience in attempting to bridge the semantic gap. In particular we discuss our work on auto-annotation and semantic-space models of image retrieval in order to bridge the gap from the bottom up, and the use of ontologies, which capture more semantics than keyword object labels alone, as a technique for bridging the gap from the top down.
Parking detection system using background subtraction and HSV color segmentationjournalBEEI
Manual system vehicle parking makes finding vacant parking lots difficult, so it has to check directly to the vacant space. If many people do parking, then the time needed for it is very much or requires many people to handle it. This research develops a real-time parking system to detect parking. The system is designed using the HSV color segmentation method in determining the background image. In addition, the detection process uses the background subtraction method. Applying these two methods requires image preprocessing using several methods such as grayscaling, blurring (low-pass filter). In addition, it is followed by a thresholding and filtering process to get the best image in the detection process. In the process, there is a determination of the ROI to determine the focus area of the object identified as empty parking. The parking detection process produces the best average accuracy of 95.76%. The minimum threshold value of 255 pixels is 0.4. This value is the best value from 33 test data in several criteria, such as the time of capture, composition and color of the vehicle, the shape of the shadow of the object’s environment, and the intensity of light. This parking detection system can be implemented in real-time to determine the position of an empty place.
Searching Images: Recent research at SouthamptonJonathon Hare
Knowledge Media Institute seminar series. The Open University. 23rd March 2011.
Southampton has a long history of research in the areas of multimedia information analysis. This talk will focus on some of the recent work we have been involved with in the area of image search. The talk will start by looking at how image content can be represented in ways analogous to textual information and how techniques developed for indexing text can be adapted to images. In particular, the talk will introduce ImageTerrier, a research platform for image retrieval that is built around the University of Glasgow's Terrier text retrieval software. The talk will also cover some of our recent work on image classification and image search result diversification.
Multimodal Searching and Semantic Spaces: ...or how to find images of Dalmati...Jonathon Hare
Tutorial at the "Reality of the Semantic Gap in Image Retrieval" tutorial at the first international conference on Semantics And digital Media Technology (SAMT 2006). 6th December 2006.
Saliency-based Models of Image Content and their Application to Auto-Annotati...Jonathon Hare
Multimedia and the Semantic Web / European Semantic Web Conference 2005, Heraklion, Crete. 29th May 2005.
http://eprints.soton.ac.uk/260954/
In this paper, we propose a model of automatic image annotation based on propagation of keywords. The model works on the premise that visually similar image content is likely to have similar semantic content. Image content is extracted using local descriptors at salient points within the image and quantising the feature-vectors into visual terms. The visual terms for each image are modelled using techniques taken from the information retrieval community. The modelled information from an unlabelled query image is compared to the models of a corpus of labelled images and labels are propagated from the most similar labelled images to the query image
Scale Saliency: Applications in Visual Matching,Tracking and View-Based Objec...Jonathon Hare
Distributed Multimedia Systems 2003 / Visual Information Systems 2003, Florida International University, Miami, Florida, USA, 24 - 26 Sep 2003.
http://eprints.soton.ac.uk/258295/
In this paper, we introduce a novel technique for image matching and feature-based tracking. The technique is based on the idea of using the Scale-Saliency algorithm to pick a sparse number of ‘interesting’ or ‘salient’ features. Feature vectors for each of the salient regions are generated and used in the matching process. Due to the nature of the sparse representation of feature vectors generated by the technique, sub-image matching is also accomplished. We demonstrate the techniques robustness to geometric transformations in the query image and suggest that the technique would be suitable for view-based object recognition. We also apply the matching technique to the problem of feature tracking across multiple video frames by matching salient regions across frame pairs. We show that our tracking algorithm is able to explicitly extract the 3D motion vector of each salient region during the tracking process, using a single uncalibrated camera. We illustrate the functionality of our tracking algorithm by showing results from tracking a single salient region in near real-time with a live camera input.
Content-based image retrieval using a mobile device as a novel interfaceJonathon Hare
Storage and Retrieval Methods and Applications for Multimedia 2005, San Jose, California, USA, 18 - 19 Jan 2005.
http://eprints.soton.ac.uk/260419/
This paper presents an investigation into the use of a mobile device as a novel interface to a content-based image retrieval system. The initial development has been based on the concept of using the mobile device in an art gallery for mining data about the exhibits, although a number of other applications are envisaged. The paper presents a novel methodology for performing content-based image retrieval and object recognition from query images that have been degraded by noise and subjected to transformations through the imaging system. The methodology uses techniques inspired from the information retrieval community in order to aid efficient indexing and retrieval. In particular, a vector-space model is used in the efficient indexing of each image, and a two-stage pruning/ranking procedure is used to determine the correct matching image. The retrieval algorithm is shown to outperform a number of existing algorithms when used with query images from the mobile device.
Bridging the Semantic Gap in Multimedia Information Retrieval: Top-down and B...Jonathon Hare
Mastering the Gap: From Information Extraction to Semantic Representation / 3rd European Semantic Web Conference, Budva, Montenegro. May 2006.
http://eprints.soton.ac.uk/262737/
Semantic representation of multimedia information is vital for enabling the kind of multimedia search capabilities that professional searchers require. Manual annotation is often not possible because of the shear scale of the multimedia information that needs indexing. This paper explores the ways in which we are using both top-down, ontologically driven approaches and bottom-up, automatic-annotation approaches to provide retrieval facilities to users. We also discuss many of the current techniques that we are investigating to combine these top-down and bottom-up approaches.
Mind the Gap: Another look at the problem of the semantic gap in image retrievalJonathon Hare
Multimedia Content Analysis, Management and Retrieval 2006, San Jose, California, USA, 17 - 19 Jan 2006
http://eprints.soton.ac.uk/261887/
This paper attempts to review and characterise the problem of the semantic gap in image retrieval and the attempts being made to bridge it. In particular, we draw from our own experience in user queries, automatic annotation and ontological techniques. The first section of the paper describes a characterisation of the semantic gap as a hierarchy between the raw media and full semantic understanding of the media's content. The second section discusses real users' queries with respect to the semantic gap. The final sections of the paper describe our own experience in attempting to bridge the semantic gap. In particular we discuss our work on auto-annotation and semantic-space models of image retrieval in order to bridge the gap from the bottom up, and the use of ontologies, which capture more semantics than keyword object labels alone, as a technique for bridging the gap from the top down.
Parking detection system using background subtraction and HSV color segmentationjournalBEEI
Manual system vehicle parking makes finding vacant parking lots difficult, so it has to check directly to the vacant space. If many people do parking, then the time needed for it is very much or requires many people to handle it. This research develops a real-time parking system to detect parking. The system is designed using the HSV color segmentation method in determining the background image. In addition, the detection process uses the background subtraction method. Applying these two methods requires image preprocessing using several methods such as grayscaling, blurring (low-pass filter). In addition, it is followed by a thresholding and filtering process to get the best image in the detection process. In the process, there is a determination of the ROI to determine the focus area of the object identified as empty parking. The parking detection process produces the best average accuracy of 95.76%. The minimum threshold value of 255 pixels is 0.4. This value is the best value from 33 test data in several criteria, such as the time of capture, composition and color of the vehicle, the shape of the shadow of the object’s environment, and the intensity of light. This parking detection system can be implemented in real-time to determine the position of an empty place.
Searching Images: Recent research at SouthamptonJonathon Hare
Knowledge Media Institute seminar series. The Open University. 23rd March 2011.
Southampton has a long history of research in the areas of multimedia information analysis. This talk will focus on some of the recent work we have been involved with in the area of image search. The talk will start by looking at how image content can be represented in ways analogous to textual information and how techniques developed for indexing text can be adapted to images. In particular, the talk will introduce ImageTerrier, a research platform for image retrieval that is built around the University of Glasgow's Terrier text retrieval software. The talk will also cover some of our recent work on image classification and image search result diversification.
Multimodal Searching and Semantic Spaces: ...or how to find images of Dalmati...Jonathon Hare
Tutorial at the "Reality of the Semantic Gap in Image Retrieval" tutorial at the first international conference on Semantics And digital Media Technology (SAMT 2006). 6th December 2006.
APPLYING R-SPATIOGRAM IN OBJECT TRACKING FOR OCCLUSION HANDLINGsipij
Object tracking is one of the most important problems in computer vision. The aim of video tracking is to extract the trajectories of a target or object of interest, i.e. accurately locate a moving target in a video sequence and discriminate target from non-targets in the feature space of the sequence. So, feature descriptors can have significant effects on such discrimination. In this paper, we use the basic idea of many trackers which consists of three main components of the reference model, i.e., object modeling, object detection and localization, and model updating. However, there are major improvements in our system. Our forth component, occlusion handling, utilizes the r-spatiogram to detect the best target candidate. While spatiogram contains some moments upon the coordinates of the pixels, r-spatiogram computes region-based compactness on the distribution of the given feature in the image that captures richer features to represent the objects. The proposed research develops an efficient and robust way to keep tracking the object throughout video sequences in the presence of significant appearance variations and severe occlusions. The proposed method is evaluated on the Princeton RGBD tracking dataset considering sequences with different challenges and the obtained results demonstrate the effectiveness of the proposed method.
GEOGRAPHIC MAPS CLASSIFICATION BASED ON L*A*B COLOR SYSTEMIJCNCJournal
Today any geographic information system (GIS) layers became vital part of any GIS system , and
consequently , the need for developing automatic approaches to extract GIS layers from different image
maps like digital maps or satellite images is very important.
Map classification can be defined as an image processing technique which creates thematic maps from
scanned paper maps or remotely sensed images. Each resultant theme will represent a GIS layer of the
images.
A new proposed approach to extract GIS layers (classes) automatically based on L*A*B colorsystem
selected from ( A and B ) is proposed in this paper, our experiments shows that the hsi color space gives
better than L*A*B.
This document discusses object removal from digital photographs through exemplar-based inpainting. It describes Criminisi's algorithm which combines texture synthesis and inpainting to remove objects while preserving linear structures and avoiding blurring. The algorithm works by assigning priority values to pixels based on proximity to linear structures, and then propagates texture patterns from surrounding regions into the removed object area. Experimental results show Criminisi's approach produces better outcomes than either texture synthesis or inpainting alone. Future work areas include improving curved structure propagation and applying the method to video.
JPM1407 Exposing Digital Image Forgeries by Illumination Color Classificationchennaijp
This document summarizes a research paper that proposes a new method for detecting digital image forgeries by analyzing inconsistencies in the color of illumination across image regions. Existing illumination-based forgery detection methods have limitations like requiring manual interaction or not handling specular regions well. The proposed method extracts texture and edge-based features from illuminant estimates of similar image regions using physics and statistics-based models. These features are then classified using a machine learning approach to detect forgeries with minimal user interaction. The method achieved detection rates of 86% on a benchmark dataset and 83% on images collected from the internet.
A Linear-Algebraic Technique with an Application in Semantic Image RetrievalJonathon Hare
Image and Video Retrieval: 5th International Conference, CIVR 2006, Tempe, AZ, USA, July 2006.
http://eprints.soton.ac.uk/262870/
This paper presents a novel technique for learning the underlying structure that links visual observations with semantics. The technique, inspired by a text-retrieval technique known as cross-language latent semantic indexing uses linear algebra to learn the semantic structure linking image features and keywords from a training set of annotated images. This structure can then be applied to unannotated images, thus providing the ability to search the unannotated images based on keyword. This factorisation approach is shown to perform well, even when using only simple global image features.
This document summarizes an algorithm for novel text detection based on character and link energies. The algorithm can detect text in various lighting conditions and complex backgrounds. It analyzes candidate text objects by calculating character energy based on parallel edge similarity and non-noise pairs. Link energy is also computed to measure the probability that connected candidate parts are both characters. Text unit energy is then calculated using character and link energies to refine detected text objects. Evaluation on ICDAR datasets shows the algorithm achieves higher precision and recall than other text detection methods.
This document summarizes an eCognition image analysis system. It discusses the eCognition processing chain which takes in input data and performs segmentation, classification, and context analysis to output results as raster, vector, point cloud, or statistics. It describes the eCognition software suite including Developer, Architect, and Server products. It outlines a scalable processing system with centralized data storage, processing units, and thin clients to connect field offices via terminal servers. Finally, it discusses eCognition technology layers from custom to off-the-shelf applications and the underlying eCognition software suite.
eCognition Developer is an image analysis software that enables users to automatically analyze remote sensing data through object-based image analysis. It allows users to design feature extraction and change detection solutions to transform geospatial data into geographic information. The software works by first segmenting images into homogeneous objects using spatial, spectral, and texture features, which can then be classified. Users develop rule sets, modify and calibrate the rules, process the data, review and export the results.
A brief introduction to extracting information from imagesJonathon Hare
This document provides an introduction to extracting information from images. It discusses how images are represented digitally in computers and various techniques for extracting features from images, including lower-level features like color histograms and higher-level features like faces. Examples are given of feature extraction algorithms for faces and image composition. The document also discusses representing images using "bags of visual words" modeled after text analysis and introduces two open-source tools, OpenIMAJ and ImageTerrier, for image analysis.
Automatic Building detection for satellite Images using IGV and DSMAmit Raikar
This document presents a method for automatic building detection from satellite images using internal gray variance (IGV) and digital surface model (DSM). The proposed method aims to detect low-rising buildings and buildings with partially bright and partially dark rooftops more accurately than existing methods. The key steps include image enhancement, IGV feature extraction, seed point detection using the enhanced image and IGV, clustering using DSM data, binarization, thinning, shadow detection, and segmentation. Results on test satellite images show the method achieves higher detection percentages and lower branch factors than an existing method.
The document discusses content-based image retrieval (CBIR) systems. It describes how CBIR systems use feature extraction to search large image databases based on visual content. The key components of CBIR systems are feature extraction, indexing, and system design. Feature extraction involves extracting information about images' colors, textures, shapes, and spatial locations. Effective features and indexing techniques are needed to make CBIR scalable for large image collections. Performance is evaluated based on how well systems return relevant images.
Spot the Dog: An overview of semantic retrieval of unannotated images in the ...Jonathon Hare
This document discusses using computational techniques to semantically retrieve unannotated images by enabling textual search of imagery without metadata. It describes:
1) Using exemplar image/metadata pairs to learn relationships between visual features and metadata, then projecting this to retrieve unannotated images.
2) Representing images as "visual terms" like words in text.
3) Creating a multidimensional "semantic space" where related images, terms and keywords are placed closely together based on training. This allows retrieving unannotated images that lie near descriptive keywords.
4) Experimental retrieval results on a Corel dataset, showing the approach works better for keywords associated with colors than others. The approach takes progress but significant challenges remain.
International Journal of Engineering Research and Applications (IJERA) is an open access online peer reviewed international journal that publishes research and review articles in the fields of Computer Science, Neural Networks, Electrical Engineering, Software Engineering, Information Technology, Mechanical Engineering, Chemical Engineering, Plastic Engineering, Food Technology, Textile Engineering, Nano Technology & science, Power Electronics, Electronics & Communication Engineering, Computational mathematics, Image processing, Civil Engineering, Structural Engineering, Environmental Engineering, VLSI Testing & Low Power VLSI Design etc.
The document proposes improving object detection and recognition capabilities. It discusses challenges with current methods like different object sizes and color variations. The objectives are to build a module that can learn and detect objects without a sliding box or datastore. A high-level design approach is outlined using techniques like contouring, BING, sliding box, and feature selection methods. The design considers optimal feature selection, dimensionality reduction, and classification algorithms to function in real-time.
Automated features extraction from satellite images.HimanshuGupta1081
This is the final year civil engineering project presentation in which different features i.e. Buildings, Road Network, Vegetation and Water are extracted automatically from satellite images with the help of Ecognition software. We have done our analysis on satellite images of sikar, rajasthan. In this project object based image analysis (OBIA) approach are used.
This document discusses analyzing cognitive load to classify learning systems for special needs education using data mining.
It begins by introducing the need for special education systems to accommodate individual learning challenges. The paper then aims to observe six types of cognitive load (mental, physical, temporal, performance, effort, frustration) across ten different memory and learning systems.
The key points are:
1) Cognitive load is observed for long term, short term, working, instant, responsive, process, recollect, reference, instruction and action memory systems.
2) Classification analysis is used to predict patterns for specific learning challenges based on generalized and specialized cognitive load properties.
3) The goal is to classify learning systems according to
Invention of digital technology has lead to increase in the number of images that can be stored in digital format. So searching and retrieving images in large image databases has become more challenging. From the last few years, Content Based Image Retrieval (CBIR) gained increasing attention from researcher. CBIR is a system which uses visual features of image to search user required image from large image
database and user’s requests in the form of a query image. Important features of images are colour, texture and shape which give detailed information about the image. CBIR techniques using different feature extraction techniques are discussed in this paper.
Content-based image retrieval (CBIR) uses visual image content to search large image databases according to user needs. CBIR systems represent images by extracting features related to color, shape, texture, and spatial layout. Features are extracted from regions of the image and compared to features of images in the database to find the most similar matches. CBIR has applications in medical imaging, fingerprints, photo collections, and more. Techniques include representing images with histograms of color and texture features extracted through transforms.
Remotely Sensed Image (RSI) Analysis for feature extraction using Color map I...ijdmtaiir
Remote Sensing is the science and art of acquiring
information (spectral, spatial, and temporal) about material
objects, area, or phenomenon, without coming into physical
contact with them ad plays a significant role in feature
extraction. In the present paper, implementation of color
mapping index method is analyzed to extract features from RSI
in spectral domain. Color indexing is applied after fixing the
index value to the pixels of selected ROI (Region of Interest)
of RSI and there by clustering based on these index values.
Color mapping, which is also called tone mapping can be used
to apply color transformations on the final image colors of the
ROI. The process of color map indexing is a color map
approximation approach on RSI for feature extraction includes
designing appropriate algorithm, its implementation and
discussion on the results of such implementation on ROI.
Dilation and erosion are two fundamental morphological operations used to modify binary images. Dilation adds pixels to object boundaries in an image, while erosion removes pixels from object boundaries. The number of pixels added or removed depends on the size and shape of the structuring element, which is a matrix of 1's and 0's used to probe the image and determine changes.
This document describes the design of a color tracking robot project. It uses a webcam and image processing software to detect a target color on a human. An ultrasonic sensor helps avoid obstacles. A microcontroller controls DC motors and receives input from sensors. The robot can follow and carry loads for a soldier to lighten their burden. Future extensions could improve identification through face or body recognition and use IR cameras for better accuracy. The goal is a low-cost robot for applications like military transport or assistance for the elderly.
APPLYING R-SPATIOGRAM IN OBJECT TRACKING FOR OCCLUSION HANDLINGsipij
Object tracking is one of the most important problems in computer vision. The aim of video tracking is to extract the trajectories of a target or object of interest, i.e. accurately locate a moving target in a video sequence and discriminate target from non-targets in the feature space of the sequence. So, feature descriptors can have significant effects on such discrimination. In this paper, we use the basic idea of many trackers which consists of three main components of the reference model, i.e., object modeling, object detection and localization, and model updating. However, there are major improvements in our system. Our forth component, occlusion handling, utilizes the r-spatiogram to detect the best target candidate. While spatiogram contains some moments upon the coordinates of the pixels, r-spatiogram computes region-based compactness on the distribution of the given feature in the image that captures richer features to represent the objects. The proposed research develops an efficient and robust way to keep tracking the object throughout video sequences in the presence of significant appearance variations and severe occlusions. The proposed method is evaluated on the Princeton RGBD tracking dataset considering sequences with different challenges and the obtained results demonstrate the effectiveness of the proposed method.
GEOGRAPHIC MAPS CLASSIFICATION BASED ON L*A*B COLOR SYSTEMIJCNCJournal
Today any geographic information system (GIS) layers became vital part of any GIS system , and
consequently , the need for developing automatic approaches to extract GIS layers from different image
maps like digital maps or satellite images is very important.
Map classification can be defined as an image processing technique which creates thematic maps from
scanned paper maps or remotely sensed images. Each resultant theme will represent a GIS layer of the
images.
A new proposed approach to extract GIS layers (classes) automatically based on L*A*B colorsystem
selected from ( A and B ) is proposed in this paper, our experiments shows that the hsi color space gives
better than L*A*B.
This document discusses object removal from digital photographs through exemplar-based inpainting. It describes Criminisi's algorithm which combines texture synthesis and inpainting to remove objects while preserving linear structures and avoiding blurring. The algorithm works by assigning priority values to pixels based on proximity to linear structures, and then propagates texture patterns from surrounding regions into the removed object area. Experimental results show Criminisi's approach produces better outcomes than either texture synthesis or inpainting alone. Future work areas include improving curved structure propagation and applying the method to video.
JPM1407 Exposing Digital Image Forgeries by Illumination Color Classificationchennaijp
This document summarizes a research paper that proposes a new method for detecting digital image forgeries by analyzing inconsistencies in the color of illumination across image regions. Existing illumination-based forgery detection methods have limitations like requiring manual interaction or not handling specular regions well. The proposed method extracts texture and edge-based features from illuminant estimates of similar image regions using physics and statistics-based models. These features are then classified using a machine learning approach to detect forgeries with minimal user interaction. The method achieved detection rates of 86% on a benchmark dataset and 83% on images collected from the internet.
A Linear-Algebraic Technique with an Application in Semantic Image RetrievalJonathon Hare
Image and Video Retrieval: 5th International Conference, CIVR 2006, Tempe, AZ, USA, July 2006.
http://eprints.soton.ac.uk/262870/
This paper presents a novel technique for learning the underlying structure that links visual observations with semantics. The technique, inspired by a text-retrieval technique known as cross-language latent semantic indexing uses linear algebra to learn the semantic structure linking image features and keywords from a training set of annotated images. This structure can then be applied to unannotated images, thus providing the ability to search the unannotated images based on keyword. This factorisation approach is shown to perform well, even when using only simple global image features.
This document summarizes an algorithm for novel text detection based on character and link energies. The algorithm can detect text in various lighting conditions and complex backgrounds. It analyzes candidate text objects by calculating character energy based on parallel edge similarity and non-noise pairs. Link energy is also computed to measure the probability that connected candidate parts are both characters. Text unit energy is then calculated using character and link energies to refine detected text objects. Evaluation on ICDAR datasets shows the algorithm achieves higher precision and recall than other text detection methods.
This document summarizes an eCognition image analysis system. It discusses the eCognition processing chain which takes in input data and performs segmentation, classification, and context analysis to output results as raster, vector, point cloud, or statistics. It describes the eCognition software suite including Developer, Architect, and Server products. It outlines a scalable processing system with centralized data storage, processing units, and thin clients to connect field offices via terminal servers. Finally, it discusses eCognition technology layers from custom to off-the-shelf applications and the underlying eCognition software suite.
eCognition Developer is an image analysis software that enables users to automatically analyze remote sensing data through object-based image analysis. It allows users to design feature extraction and change detection solutions to transform geospatial data into geographic information. The software works by first segmenting images into homogeneous objects using spatial, spectral, and texture features, which can then be classified. Users develop rule sets, modify and calibrate the rules, process the data, review and export the results.
A brief introduction to extracting information from imagesJonathon Hare
This document provides an introduction to extracting information from images. It discusses how images are represented digitally in computers and various techniques for extracting features from images, including lower-level features like color histograms and higher-level features like faces. Examples are given of feature extraction algorithms for faces and image composition. The document also discusses representing images using "bags of visual words" modeled after text analysis and introduces two open-source tools, OpenIMAJ and ImageTerrier, for image analysis.
Automatic Building detection for satellite Images using IGV and DSMAmit Raikar
This document presents a method for automatic building detection from satellite images using internal gray variance (IGV) and digital surface model (DSM). The proposed method aims to detect low-rising buildings and buildings with partially bright and partially dark rooftops more accurately than existing methods. The key steps include image enhancement, IGV feature extraction, seed point detection using the enhanced image and IGV, clustering using DSM data, binarization, thinning, shadow detection, and segmentation. Results on test satellite images show the method achieves higher detection percentages and lower branch factors than an existing method.
The document discusses content-based image retrieval (CBIR) systems. It describes how CBIR systems use feature extraction to search large image databases based on visual content. The key components of CBIR systems are feature extraction, indexing, and system design. Feature extraction involves extracting information about images' colors, textures, shapes, and spatial locations. Effective features and indexing techniques are needed to make CBIR scalable for large image collections. Performance is evaluated based on how well systems return relevant images.
Spot the Dog: An overview of semantic retrieval of unannotated images in the ...Jonathon Hare
This document discusses using computational techniques to semantically retrieve unannotated images by enabling textual search of imagery without metadata. It describes:
1) Using exemplar image/metadata pairs to learn relationships between visual features and metadata, then projecting this to retrieve unannotated images.
2) Representing images as "visual terms" like words in text.
3) Creating a multidimensional "semantic space" where related images, terms and keywords are placed closely together based on training. This allows retrieving unannotated images that lie near descriptive keywords.
4) Experimental retrieval results on a Corel dataset, showing the approach works better for keywords associated with colors than others. The approach takes progress but significant challenges remain.
International Journal of Engineering Research and Applications (IJERA) is an open access online peer reviewed international journal that publishes research and review articles in the fields of Computer Science, Neural Networks, Electrical Engineering, Software Engineering, Information Technology, Mechanical Engineering, Chemical Engineering, Plastic Engineering, Food Technology, Textile Engineering, Nano Technology & science, Power Electronics, Electronics & Communication Engineering, Computational mathematics, Image processing, Civil Engineering, Structural Engineering, Environmental Engineering, VLSI Testing & Low Power VLSI Design etc.
The document proposes improving object detection and recognition capabilities. It discusses challenges with current methods like different object sizes and color variations. The objectives are to build a module that can learn and detect objects without a sliding box or datastore. A high-level design approach is outlined using techniques like contouring, BING, sliding box, and feature selection methods. The design considers optimal feature selection, dimensionality reduction, and classification algorithms to function in real-time.
Automated features extraction from satellite images.HimanshuGupta1081
This is the final year civil engineering project presentation in which different features i.e. Buildings, Road Network, Vegetation and Water are extracted automatically from satellite images with the help of Ecognition software. We have done our analysis on satellite images of sikar, rajasthan. In this project object based image analysis (OBIA) approach are used.
This document discusses analyzing cognitive load to classify learning systems for special needs education using data mining.
It begins by introducing the need for special education systems to accommodate individual learning challenges. The paper then aims to observe six types of cognitive load (mental, physical, temporal, performance, effort, frustration) across ten different memory and learning systems.
The key points are:
1) Cognitive load is observed for long term, short term, working, instant, responsive, process, recollect, reference, instruction and action memory systems.
2) Classification analysis is used to predict patterns for specific learning challenges based on generalized and specialized cognitive load properties.
3) The goal is to classify learning systems according to
Invention of digital technology has lead to increase in the number of images that can be stored in digital format. So searching and retrieving images in large image databases has become more challenging. From the last few years, Content Based Image Retrieval (CBIR) gained increasing attention from researcher. CBIR is a system which uses visual features of image to search user required image from large image
database and user’s requests in the form of a query image. Important features of images are colour, texture and shape which give detailed information about the image. CBIR techniques using different feature extraction techniques are discussed in this paper.
Content-based image retrieval (CBIR) uses visual image content to search large image databases according to user needs. CBIR systems represent images by extracting features related to color, shape, texture, and spatial layout. Features are extracted from regions of the image and compared to features of images in the database to find the most similar matches. CBIR has applications in medical imaging, fingerprints, photo collections, and more. Techniques include representing images with histograms of color and texture features extracted through transforms.
Remotely Sensed Image (RSI) Analysis for feature extraction using Color map I...ijdmtaiir
Remote Sensing is the science and art of acquiring
information (spectral, spatial, and temporal) about material
objects, area, or phenomenon, without coming into physical
contact with them ad plays a significant role in feature
extraction. In the present paper, implementation of color
mapping index method is analyzed to extract features from RSI
in spectral domain. Color indexing is applied after fixing the
index value to the pixels of selected ROI (Region of Interest)
of RSI and there by clustering based on these index values.
Color mapping, which is also called tone mapping can be used
to apply color transformations on the final image colors of the
ROI. The process of color map indexing is a color map
approximation approach on RSI for feature extraction includes
designing appropriate algorithm, its implementation and
discussion on the results of such implementation on ROI.
Dilation and erosion are two fundamental morphological operations used to modify binary images. Dilation adds pixels to object boundaries in an image, while erosion removes pixels from object boundaries. The number of pixels added or removed depends on the size and shape of the structuring element, which is a matrix of 1's and 0's used to probe the image and determine changes.
This document describes the design of a color tracking robot project. It uses a webcam and image processing software to detect a target color on a human. An ultrasonic sensor helps avoid obstacles. A microcontroller controls DC motors and receives input from sensors. The robot can follow and carry loads for a soldier to lighten their burden. Future extensions could improve identification through face or body recognition and use IR cameras for better accuracy. The goal is a low-cost robot for applications like military transport or assistance for the elderly.
Design and implementation of color tracking method on Chess Robot Using CameraDaniel Adrian
This thesis aims to test whether the color tracking system can be implemented on a chess robot. Color tracking aims to locate the position of chess. This identification process using color as a reference. Each chess piece has a different color. Input from the image in the form of a camera that is placed on a chessboard. Testing is done by changing the light and the angle of the camera. Then tested whether the input can detect and recognize chess. The results of this test, the computer can recognize chess. This input will be implemented on the robot chess.
Glas Trösch - Challenges of using glass in the Alpine regionsBenjamin Schulz
High up in the Alps, the architecture is often characterized by a traditional method of construction that has few transparent surfaces and, in order to provide protection against the extreme weather conditions, tends to be of rather reserved nature. This is where contemporary façade glazing opens up new opportunities: The transparent material not only offers greater creative freedom but also enables designers to realise bright and inviting rooms which allow for far-reaching views of the mountains and create the optimum conditions for the successful use of the buildings from the tourism aspect. As a Swiss company, Glas Trösch has extensive experience in the use of glass at extreme altitudes and knows the special requirements demanded of the material at these exposed locations.
The document proposes a novel approach to simulate mouse functions using only a webcam and computer vision techniques. Two colored tapes would be worn on the fingers to detect hand gestures for controlling mouse movements and clicks. The yellow tape on the index finger would control cursor position while the distance between the yellow and red tapes would determine click events. Left clicks would occur when the thumb tape nears the index finger tape, right clicks from pausing in position, and double clicks from pausing both tapes in position. This vision-based mouse simulation could revolutionize human-computer interaction by eliminating physical devices.
Slide for Multi Object Tracking by Md. Minhazul Haque, Rajshahi University of Engineering and Technology
* Objectives
* Object Tracking
* Applications
* Methodology
* Implementation
* Experiment Result
* Performance Analysis
* Future Work
* References
Slide for Multi Object Tracking by Md. Minhazul Haque, Rajshahi University of Engineering and Technology
* Object
* Object Tracking
* Application
* Background Study
* How it works
* Multi-Object Tracking
* Solution
* Future Works
This document provides an overview of colour theory and models for application in multimedia. It describes how colour is perceived and named, then covers the RGB, CMYK, and HSV colour models. It discusses additive and subtractive colour synthesis. The document also addresses colour palettes, web colours, and colour wheels. Colour matching between RGB and CMYK is examined along with references for further information.
Color based image processing , tracking and automation using matlabKamal Pradhan
Image processing is a form of signal processing in which the input is an image, such as a photograph or video frame. The output of image processing may be either an image or, a set of characteristics or parameters related to the image. Most image-processing techniques involve treating the image as a two-dimensional signal and applying standard signal-processing techniques to it. This project aims at processing the real time images captured by a Webcam for motion detection and Color Recognition and system automation using MATLAB programming.
In color based image processing we work with colors instead of object. Color provides powerful information for object recognition. A simple and effective recognition scheme is to represent and match images on the basis of color histograms.
Tracking refers to detection of the path of the color once the color based processing is done the color becomes the object to be tracked this can be very helpful in security purposes.
Automation refers to an automated system is any system that does not require human intervention. In this project I’ve automated the mouse that work with our gesture and do the desired tasks.
This document summarizes several methods for real-time object detection and tracking in video sequences. Traditional methods like absolute differences and census transforms are compared to modern methods like KLT (Lucas-Kanade Technique) and Meanshift. Hardware requirements for real-time tracking like memory, frame rate, and processors are also discussed. The document provides examples of applications for object detection and tracking in traffic monitoring, surveillance, and mobile robotics.
The document discusses object tracking in computer vision. It begins with an introduction and overview of applications of object tracking. It then discusses object representation, detection, tracking algorithms and methodologies. It compares different tracking methods and provides an example of object tracking in MATLAB. Key steps in object tracking include object detection, tracking the detected objects across frames using algorithms like point tracking, kernel tracking and silhouette tracking. Common challenges with object tracking are also summarized.
Object tracking involves tracing the movement of objects in a video sequence. There are various object representation methods like points, shapes, and skeletons. Popular tracking algorithms include point tracking, kernel tracking, and silhouette tracking. Key steps are object detection, feature extraction, segmentation, and tracking. Common challenges are illumination changes, occlusions, and complex motions. The document compares methods like optical flow, mean shift, and feature-based tracking. In conclusion, object tracking has advanced but challenges remain like handling occlusions.
1. The document discusses 2D/multi-view segmentation and tracking techniques for video analysis including spatial segmentation, object tracking across multiple views, and detecting unusual events based on trajectory analysis.
2. It describes applying segmentation to extract regions and objects from video frames then tracking them across multiple views using correspondence between views.
3. Techniques for detecting unusual events include modeling normal trajectories, extracting features from trajectories, and using SVM classification to detect deviations from normal behavior. Experiments show the approach can detect unusual events on new video sequences.
Flag segmentation, feature extraction & identification using support vector m...R M Shahidul Islam Shahed
Develop a system that can identify flags embedded in photos of natural scenes.
Develop a system that can segment a flag portion automatically accurately.
Reduce the identification time and produce a good result.
Apply Support Vector Machine(SVM) to generate the correct Result.
This document summarizes a research paper that presents a framework for detecting and tracking objects in real-time video based on color. The proposed methodology uses a webcam to capture video, performs color-based filtering and image processing to isolate the target object, and analyzes the object's motion over time to track its path. Key steps include Euclidean filtering to isolate the object's color, converting to grayscale for faster processing, contour extraction to delineate the object's shape, and analyzing metrics like the Hurst exponent and Lyapunov exponent to detect chaos in the object's motion over time. The goal is to develop an efficient and real-time system for color-based object detection and tracking.
International Journal of Engineering Research and DevelopmentIJERD Editor
Electrical, Electronics and Computer Engineering,
Information Engineering and Technology,
Mechanical, Industrial and Manufacturing Engineering,
Automation and Mechatronics Engineering,
Material and Chemical Engineering,
Civil and Architecture Engineering,
Biotechnology and Bio Engineering,
Environmental Engineering,
Petroleum and Mining Engineering,
Marine and Agriculture engineering,
Aerospace Engineering.
This document discusses object tracking techniques in computer vision. It begins by defining object tracking as segmenting an object from video frames and observing its motion and position over time. There are several challenges to object tracking, including illumination changes, object occlusion, and camera motion. The document then describes two main approaches to object tracking: feature-based methods which extract image features to track objects, and kernel-based methods which represent objects using shapes and track their motion. It provides examples of kernel tracking methods like mean shift and discusses challenges like overlapping objects. In conclusion, the document implemented and compared mean shift, CAMShift and contour tracking algorithms for object tracking.
DEVELOPMENT OF AN ANDROID APPLICATION FOR OBJECT DETECTION BASED ON COLOR, SH...ijma
Object detection and recognition is an important task in many computer vision applications. In this paper
an Android application was developed using Eclipse IDE and OpenCV3 Library. This application is able to
detect objects in an image that is loaded from the mobile gallery, based on its color, shape, or local
features. The image is processed in the HSV color domain for better color detection. Circular shapes are
detected using Circular Hough Transform and other shapes are detected using Douglas-Peucker
algorithm. BRISK (binary robust invariant scalable keypoints) local features were applied in the developed
Android application for matching an object image in another scene image. The steps of the proposed
detection algorithms are described, and the interfaces of the application are illustrated. The application is
ported and tested on Galaxy S3, S6, and Note1 Smartphones. Based on the experimental results, the
application is capable of detecting eleven different colors, detecting two dimensional geometrical shapes
including circles, rectangles, triangles, and squares, and correctly match local features of object and scene
images for different conditions. The application could be used as a standalone application, or as a part of
another application such as Robot systems, traffic systems, e-learning applications, information retrieval
and many others.
The document presents a hybrid approach for detecting and recognizing text in images. It consists of three main steps:
1) Image partition using k-means clustering to segment text regions based on color information.
2) Character grouping to detect text characters within each text string based on character size differences and distance between characters.
3) Text recognition of detected characters using a neural network.
The proposed method was evaluated on a street view text dataset, achieving a precision of 0.83, recall of 0.93, and f-measure of 0.25 for text recognition. The approach efficiently and accurately detects and recognizes text with low false positives.
Object detection involves identifying and locatingmahendrarm2112
1. The document discusses object tracking and moving object detection, including algorithms for tracking objects through successive image frames.
2. Object representation and feature selection are important for tracking, with common representations being points, shapes, silhouettes. Common features include color, edges, optical flow, and texture.
3. Moving object detection algorithms discussed include background subtraction, frame differencing, and edge detection. Advantages and disadvantages of these algorithms are also presented.
A Survey on Approaches for Object Trackingjournal ijrtem
This document summarizes various approaches for object tracking in video sequences. It discusses common object detection methods like temporal differencing, optical flow and background subtraction. For object representation, it describes shape-based, motion-based, color-based and texture-based approaches. For object tracking, it analyzes target representation and localization methods like blob tracking and mean shift, as well as filtering and data association approaches like the Kalman filter and particle filter. It provides comparisons between Kalman and particle filters, and between contour tracking and visual feature matching methods. The document concludes that further research could improve computational efficiency and decrease tracking time for diverse video content.
AUTOMATIC DOMINANT REGION SEGMENTATION FOR NATURAL IMAGES cscpconf
The document proposes an automatic dominant region segmentation algorithm for natural images. It begins with an introduction to image segmentation and its applications. A literature review covers previous work on color image segmentation techniques. The proposed algorithm first converts the input RGB image to grayscale, applies preprocessing like filtering, and performs edge detection. It then separates the foreground object from the background using thresholding. Dominant regions are identified and the segmented color image with boundaries is produced. Experimental results on benchmark datasets show the algorithm avoids over-segmentation compared to previous methods like JSEG. The conclusions state that color and texture are important for segmentation and the proposed method simple implements dominant region extraction.
Automatic dominant region segmentation for natural imagescsandit
Image Segmentation segments an image into different homogenous regions. An efficient
semantic based image retrieval system divides the image into different regions separated by
color or texture sometimes even both. Features are extracted from the segmented regions and
are annotated automatically. Relevant images are retrieved from the database based on the
keywords of the segmented region In this paper, automatic image segmentation is proposed to
obtained dominant region of the input natural images. Dominant region are segmented and
results are obtained . Results are also recorded in comparison to JSEG algorithm
The efficiency and quality of a feature descriptor are critical to the user experience of many computer vision applications. However, the existing descriptors are either too computationally expensive to achieve real-time performance, or not sufficiently distinctive to identify correct matches from a large database with various transformations. In this paper, we propose a highly efficient and distinctive binary descriptor, called local difference binary (LDB). LDB directly computes a binary string for an image patch using simple intensity and gradient difference tests on pair wise grid cells within the patch. A multiple-gridding strategy and a salient bit-selection method are applied to capture the distinct patterns of the patch at different spatial granularities. Experimental results demonstrate that compared to the existing state-of-the-art binary descriptors, primarily designed for speed, LDB has similar construction efficiency, while achieving a greater accuracy and faster speed for mobile object recognition and tracking tasks.
This document presents a methodology for real-time object tracking using a webcam. It combines Prewitt edge detection for object detection and Kalman filtering for tracking. Prewitt edge detection is used to detect the edges of the moving object in each video frame. Then, Kalman filtering is used to track the detected object across subsequent frames by predicting its location. Experiments show the approach can efficiently track objects under deformation, occlusion, and can track multiple objects simultaneously. The combination of Prewitt edge detection and Kalman filtering provides an effective method for real-time object tracking.
Content based image retrieval based on shape with texture featuresAlexander Decker
This document describes a content-based image retrieval system that extracts shape and texture features from images. It uses the HSV color space and wavelet transform for feature extraction. Color features are extracted by quantizing the H, S, and V components of HSV into unequal intervals based on human color perception. Texture features are extracted using wavelet transforms. The color and texture features are then combined to form a feature vector for each image. During retrieval, the similarity between a query image and images in the database is measured using the Euclidean distance between their feature vectors. The results show that retrieving images using HSV color features provides more accurate results and faster retrieval times compared to using RGB color features.
OBJECT DETECTION FOR SERVICE ROBOT USING RANGE AND COLOR FEATURES OF AN IMAGEIJCSEA Journal
This document summarizes an approach for object detection using both range and color image features. The proposed method first generates hypotheses for objects in a range image using a generative model (pLSA) applied to bag-of-visual-words representing 3D shape. It then verifies the hypotheses using an SVM classifier combining 3D shape features from the range image and color appearance features from the corresponding area of the color image. The approach was tested on images containing multiple objects acquired using both a range sensor and color camera.
Object Detection for Service Robot Using Range and Color Features of an ImageIJCSEA Journal
In real-world applications, service robots need to locate and identify objects in a scene. A range sensor provides a robust estimate of depth information, which is useful to accurately locate objects in a scene. On the other hand, color information is an important property for object recognition task. The objective of this paper is to detect and localize multiple objects within an image using both range and color features. The proposed method uses 3D shape features to generate promising hypotheses within range images and verifies these hypotheses by using features obtained from both range and color images.
Similar to Tracking of objects with known color signature - ELITECH 20 (20)
ICRA: Intelligent Platform for Collaboration and InteractionLukas Tencer
Presentation for a class at Polytechnique Montreal. First halve focuses on presentation of the platform, second halve focuses on presentation of algorithms.
This document introduces fundamental concepts in probability that are important for computer vision models, including:
1) Random variables represent uncertain quantities that can take on different values, described by probability distributions.
2) Joint, marginal, and conditional probabilities describe the relationships between multiple random variables and allow computing the probability of one variable given information about others.
3) Bayes' rule provides a way to calculate conditional probabilities and invert relationships between cause and effect.
4) Independence and expectation define how variables interact and allow calculating average values over probability distributions. These concepts form the basis for probabilistic models in computer vision.
This document discusses common probability distributions used in computer vision. It introduces the Bernoulli, beta, categorical, and Dirichlet distributions which model useful quantities like binary outcomes and categorical variables. It then presents conjugate distributions that model the parameters of the first four distributions, such as the normal inverse gamma distribution for the univariate normal. The document explains that these conjugate pairs have a special relationship where the posterior takes the same form as the prior, allowing for efficient calculation in learning models.
Web-based framework for online sketch-based image retrievalLukas Tencer
My presentation for course SYS821 "Pattern recognition and inspection" at ETS. This describes implementation of my project on topic "Web-based framework for online sketch-based image retrieval".
Supervised Learning of Semantic Classes for Image Annotation and RetrievalLukas Tencer
This is presentation done by me for ECSE626 "Statistical Computer Vision" at McGill University. It is presentation of a project inspired by paper "Supervised Learning of Semantic Classes for Image Annotation and Retrieval" from PAMI 2007. It presents my implementation of the paper and my achieved results.
Personal Career,Education and skills presentation, 2011Lukas Tencer
Lukas Tencer has worked as a test engineer, software engineer, lead programmer, and researcher between 2006-2011. He has a Bachelor's, Master's, and PhD in computer science and has worked on projects for universities and companies in Slovakia, Ireland, Netherlands, and Canada. His programming experience includes C++, Java, JavaScript, and other languages.
Computer graphics on web and in mobile devicesLukas Tencer
Presentation on computer graphics systems used in mobile devices and on web. Overview of techniques with details and capabilities, with aim on 2D and 3D graphics. Presentation is in Slovak language.
Presentation from my early school time on telnet and SSH. Basic overview of techniques and technical details. In cooperation with Lukas Apalovic. Presentation is in slovak