Abdelhamid Abdesselam

Work place: Department of Computer Science, Sultan Qaboos University, Oman

E-mail: ahamid@squ.edu.com

Website:

Research Interests: Information Retrieval, Medical Image Computing, Image Processing, Image Manipulation, Image Compression, Medical Informatics

Biography

Dr. Abdelhamid Abdesselam received his MSc. From Universite Paul Sabatier, Toulouse, France and his PhD in Computer Vision from Ecole National Polytechnique de Touloue, France. He worked in Universiti Malaysia Sarawak and Qatar University before joining Sultan Qaboos University. He is currently an Asst. Professor of Computer Science. His research interests include content-based image retrieval, biometrics, medical image analysis and machine learning.

Author Articles
Edge Information for Boosting Discriminating Power of Texture Retrieval Techniques

By Abdelhamid Abdesselam

DOI: https://doi.org/10.5815/ijigsp.2016.04.03, Pub. Date: 8 Apr. 2016

Texture is a powerful image property for object and scene characterization, consequently, a large number of techniques has been developed for describing, classifying and retrieving texture images. On the other hand, edge information is proven to be an important cue used by the human visual system. Several physiological experiments have shown that, when looking at an object, human eyes explore different locations of that object through saccadic eye movements but they spend more time fixating edge regions. Based on this result, we hypothesize that a better performance could be obtained when analyzing an image (texture images in this case) if the visual features extracted from edge regions are given higher weights than those extracted from uniform regions. To check the validity of this hypothesis, we have modified several existing texture retrieval techniques in a way that incorporates the proposed idea and compared their performance with that of the original techniques. The results of the experiments that have been conducted on three common datasets confirmed the effectiveness of the proposed approach, since a significant improvement in the retrieval rate is obtained for all tested techniques. The experiments have also shown an improvement in the robustness to noise. 

[...] Read more.
Other Articles