We can retrieve images based on texture and we getting matched images in targeted path, when we want partical images on condition we are using texture image retrieval system to getting 100% accurate output on the targeted system,
3. ABSTRACT
The main aim of this project is to retrieve images based on their texture
properties.
The current content based image retrieval system deals with facial recognition
with few draw backs.
Thus it improves the efficiency of the system with the help of textures.
Our Texture based image retrieval system analyses the given input image by
means of texture present in it which generally deals with the background or the
contents in the image.
The system also provides an efficient process for retrieval of images.
4. INTRODUCTION
With the rapid increase in digital images , the problem in finding a desired
image in the web becomes a hard task
The most common way of doing this is by textual descriptions and categorizing
of images.
An image is given as input query and the system identifies its texture features.
The system automatically identifies texture based features and descriptors of
each image in the image database
Features of the query specification are compared with features from the image
database to determine which images match similarly with given features.
The relevant images are provided to the user.
5. Contd…
OPENCV
OpenCV (Open Source Computer Vision Library) is a library of programming
functions.
It focuses mainly on real-time image processing.
Primary interface is in C++
Other interfaces include python , java and MATLAB .
6. EXISTING SYSTEM
The existing commercial and research image retrieval systems are based on:
o Search by color
o search by text
o random browsing
o search by sketch
The current content based image retrieval system deals with facial recognition.
7. PROPOSED SYSTEM
The proposed system is texture based image retrieval system that uses texture as its
basic criteria.
Texture Based Image Retrieval (TBIR) is a technique which uses texture features of
image to search user required image from large image database according to user's
requests in the form of a query image.
An image texture is a set of metrics calculated in image processing designed to
quantify the perceived texture of an image
Texture includes the visual patterns of an image:
-Coarsness: unrefined or unpolished
-Contrast: difference in luminance
-Roughness
8. Contd…
The image databases are indexed with descriptors derived from the visual content of
the images.
The similarities /distances between the descriptor vectors of the query and images in
the database are identified.
The output will be the similar images having same or very closest features as that of
the query image.
.
12. INTERFACE MODULE
This module is for Image acquisition and to provide output of the search.
Acquires a digital image as input query image from the user.
Presents the results after processing the query image.
.
13. Feature Extraction Module
The image is first processed in order to extract the features, which describe its
contents.
The texture features are extracted from the image using the speeded up robust feature
-SURF algorithm.
SURF algorithm: used for feature detection , description and matching.
In this visual information is extracted from the image and generates features vectors
.For each pixel, the image description is found in the form of feature value by using
the feature extraction
14. Feature Matching
This is the main module that matches the texture features of the input image with all
the images in the database.
The feature vectors of images are matched with the feature vectors of query image.
If the distance between the two vectors is sufficently small then match is generated.
The SURF algorithm speeds up the matching which helps in measuring the
similarity.
Retrieves all the relevant images to the user.
15. Features Storage Module
Image Database: It consists of the collection of n number of images depends on
the user range and choice.
SQL methods are implemented for storing and updating of images and their
features in the image database.
.
16. SOFTWARE REQUIREMENTS
OPENCV 2.4.2
Microsoft Visual Studio 2010 C++ express
Operating Systems: Windows xp/vista7/8.
HARDWARE REQUIREMENTS
HARD DISK Space: 2 GB RAM,
80 GB disk space
17. MERITS
More accurate results
Reduces the semantic gap
Retrieves images based on logical features
Efficient image searching
display the images from database which are the more interest to
the user
19. Applications:
Crime force for picture recognition in crime prevention.
Medical diagnosis
Architectural and engineering design
Fashion and publishing
Geographical information and remote sensing systems
Home entertainment