January 2015 Issue Vol.5 No.1



An Enhanced Technique for Image Retrieval Using Texture Features http://archive.org/download/vol5no1/v5no101.pdf
R.N.Muhammad Ilyas
Ph.D (Research Scholar), Manonmaniam Sundaranar University, Tirunelveli, Tamil Nadu, India
Dr.S.Pannirselvam
Research Supervisor & Head
Department of Computer Science, Erode Arts & Science College (Autonomous), Erode, Tamil Nadu, India.


Abstract: Content-Based Image Retrieval (CBIR) uses the visual contents of an image such as color, shape, texture and spatial layout to represent and index the image. The CBIR is the process of retrieving images from a database or library of digital images according to the visual content of the images. Image retrieval is the most essential process in the real world web application where the most of the user attempting to retrieve the images by submitting the label keywords. The image retrieval process is enhanced to improve the retrieval accuracy by retrieving the contents based on visual information present in the images instead of the labelling information. Then feature extraction on image retrieval is to be accomplished. The segmentation is the process of partitioning an image into multiple images. Content based image retrieval is done efficiently by using the combination of the texture and the shape features. Gustafson-kessel algorithm is used for segmentation to improve the retrieval accuracy of the images. The texture features are extracted from the segmented images to calculate the Hausdroff distance for similarity measures. Based on the similarity value, the images in the data bases are retrieved and the performance is evaluated with Corel database of images. The high accuracy, precision and recall are compared with the existing models and are implemented with Mat lab.

Keywords: CBIR, TBIR, RBIR, SPCA, CAD, FCM

Read complete January 2015