Similarity Measure Based Retrieval System Using Color and Texture Descriptors: An Experimental Analysis

  IJRES-book-cover  International Journal of Recent Engineering Science (IJRES)         
  
© 2014 by IJRES Journal
Volume-1 Issue-1
Year of Publication : 2014
Authors : Dr.P.Sumathi, C.Sudha
DOI : 10.14445/23497157/IJRES-V1I1P102

How to Cite?

Dr.P.Sumathi, C.Sudha, "Similarity Measure Based Retrieval System Using Color and Texture Descriptors: An Experimental Analysis," International Journal of Recent Engineering Science, vol. 1, no. 1, pp. 7-11, 2014. Crossref, https://doi.org/10.14445/23497157/IJRES-V1I1P102

Abstract
Content Based Image Retrieval aims at searching image libraries for specific features such as Color, Texture and Shape. We compare image retrieval systems based on the combination of two complementary features: on one hand, we propose a method to find the dominant colors in images to better capture the color properties of the original images; on the other hand, to increase the retrieval rate, we make use of Edge Histogram descriptor to acquire the texture features. It was seen that the proposed methodology surpasses other methods in terms of not only the quantitative measure (similarity metric), but also retrieval capabilities. This methodology finds its use in image retrieval, online shopping and object recognition.

Keywords
Color and Texture Features, Similarity metrics, Retrieval Rate

Reference
[1] James Z.Wang, Donald Geman, Jiebo Luo,”Real World Image Annotation and Retrieval: An introduction to the special section”, IEEE Trans. Pattern Analysis and Machine Intelligence, Vol.30, No.11, November 2008.
[2] Lior Wolf, Tal Hassner,”Descriptor Based Methods in the Wild”, published in Workshop on Faces in Real Life Images: Detection, Alignment and Recognition, Marsille: France 2007.
[3] Seung Ho Baeg,Jae Han Park,Jaehan Koh, ”An Object Recognition System for a smart Home Environment on the Basis of Color and Texture Descriptors”, Proceedings of the 2007 IEEE International Conference on Intelligent Robots and Systems, an Diego,USA ,October 29- November 2,2007.
[4] Michael Hahnel, Daniel Klunder and Karl Friedrich Kraiss,”Color and Texture Features for Person Recognition”, 2004.
[5] Topi Maenpaa, Matti Pietikaien,”Classification with Color and Texture: Jointly or separately”, published by Elsevier Ltd on behalf of Pattern Recognition society in 2004.
[6] DONG Kwon Park, Yoon Seok Jeon, Chee Sun Won, “Efficient Use of Local Edge Histogram Descriptor”, ACM Multimedia Workshop Marina Del Rey CA USA, 2001.
[7] Arnold W.M.Smeulders, Marcel Worring, Simone Santini, Amarnath Gupta, Ramesh Jain, ”Content Based Image Retrieval at the end of the early years”, IEEE Transaction on Pattern Analysis and Machine Intelligence, Vol.22, No.12, December 2000,Page No (1349-1380).
[8] MARKO Tkalcic, Jurji F. Tasic,”Color Spaces- perceptual, historical and application background”, Lecture notes, December 2000.