• Corpus ID: 19018933

Image Feature Extraction Techniques and Their Applications for CBIR and Biometrics Systems

  title={Image Feature Extraction Techniques and Their Applications for CBIR and Biometrics Systems},
  author={Ryszard S. Choras},
In CBIR (Content-Based Image Retrieval), visual features such as shape, color and texture are extracted to characterize images. Each of the features is represented using one or more feature descriptors. During the retrieval, features and descriptors of the query are compared to those of the images in the database in order to rank each indexed image according to its distance to the query. In biometrics systems images used as patterns (e.g. fingerprint, iris, hand etc.) are also represente d by… 
Content Based Image Retrieval using Color , Shape and Texture Extraction Techniques
Images contain information in a very dense and complex form, which a human eye only after years of training can extract and understand. In Content-Based Image Retrieval (CBIR), visual features such
The image retrieval problem encountered when searching and retrieving images that is relevant to a user’s request from a database. To solve this problem, Text based image retrieval and Content based
Content Based Image Retrieval by Multi Features using Image Blocks
Content based image retrieval (CBIR) is an effective method of retrieving images from large image resources. CBIR is a technique in which images are indexed by extracting their low level features
Comparative Study on Content-Based Image Retrieval (CBIR)
  • S. Khan, A. Hussain, I. Alshaikhli
  • Computer Science
    2012 International Conference on Advanced Computer Science Applications and Technologies (ACSAT)
  • 2012
Comparison of three different approaches of CBIR based on image features and similarity measures taken for finding the similarity between two images shows that selecting an important image feature and calculating that through a meaningful way is of great importance in image retrieval.
Efficient Cbir Using Color Histogram Processing
It is found that further modifications are needed to produce better performance in searching images, and cross correlation value & image descriptor attributes are calculated prior histogram implementation to make CBIR system more efficient.
Feature-based Intelligent Image Retrieval Algorithms : A Comparison
Due to the development of Internet and photographic technology the numbers of digital images have been increasing rapidly. In this scenario, maintaining the database of images and retrieval of
Content-based image retrieval approach for biometric security using colour, texture and shape features controlled by fuzzy heuristics
A new content-based image retrieval approach for biometric security, which is based on colour, texture and shape features and controlled by fuzzy heuristics, based on the three well-known algorithms: colour histogram, texture, moment invariants.
Similarity of Image Multiple Feature Extraction and Retrieval Perspectives
Retrieval of images based on ocular qualities such as color, texture and shape have proven to essential its own set of limitations under different conditions. The other area in the Image mining
An Efficient Content based Image Retrieval: CBIR
This paper aims to develop a new efficient tool for CBIR based on above mention parameters using MATLAB to develop an image retrieval based on content properties such as shape, color, texture etc.
An Efficient Content based Image Retrieval : CBIR 1
Due to the exponential growth of image data there is a dire need for innovative tools which can easily manage, retrieve images and images from the large image database. The most common approach which


Integration of color, edge, shape, and texture features for automatic region-based image annotation and retrieval
The proposed multifeature integration algorithms are designed to offer the user a wide range of options and flex- ibilities in order to enhance the outcome of the search and retrieval operations, and provide a compromise between accuracy and computational complexity.
A region-based shape descriptor using Zernike moments
The experimental results conducted on a database of about 6,000 images in terms of exact matching under various transformations and the similarity-based retrieval show that the proposed shape descriptor is very effective in representing shapes.
Rotation invariant pattern recognition using Zernike moments
  • A. Khotanzad, Yaw Hua Hong
  • Mathematics, Computer Science
    [1988 Proceedings] 9th International Conference on Pattern Recognition
  • 1988
A novel synthesis-based approach for selection of rotation-invariant features of an image based on a mapping of the image onto a set of orthogonal basis functions, which gives them many useful properties.
Feature extraction methods for character recognition-A survey
This paper presents an overview of feature extraction methods for off-line recognition of segmented (isolated) characters in terms of invariance properties, reconstructability and expected distortions and variability of the characters.
Invariant Image Recognition by Zernike Moments
A systematic reconstruction-based method for deciding the highest-order ZERNike moments required in a classification problem is developed and the superiority of Zernike moment features over regular moments and moment invariants was experimentally verified.
Local Grayvalue Invariants for Image Retrieval
This paper addresses the problem of retrieving images from large image databases with a method based on local grayvalue invariants which are computed at automatically detected interest points and allows for efficient retrieval from a database of more than 1,000 images.
Moment Functions in Image Analysis: Theory and Applications
A comprehensive treaty on the theory and applications of moment functions in image analysis. Moment functions are widely-used in various realms of computer vision and image processing. Numerous
Image analysis via the general theory of moments
Two-dimensional image moments with respect to Zernike polynomials are defined, and it is shown how to construct an arbitrarily large number of independent, algebraic combinations of Zernike moments
High Confidence Visual Recognition of Persons by a Test of Statistical Independence
  • J. Daugman
  • Computer Science
    IEEE Trans. Pattern Anal. Mach. Intell.
  • 1993
A method for rapid visual recognition of personal identity is described, based on the failure of a statistical test of independence, which implies a theoretical "cross-over" error rate of one in 131000 when a decision criterion is adopted that would equalize the false accept and false reject error rates.
Statistical Textural Features for Detection of Microcalcifications in Digitized Mammograms
The surrounding region-dependence method is shown to be superior to the conventional texture-analysis methods with respect to classification accuracy and computational complexity.