Image Retrieval Based on Content Using Color Feature. (15th March 2012)

• Record Type: Journal Article
• Authors: Afifi, Ahmed J.; Ashour, Wesam M.
• Other Names: Calvert T. Academic Editor.; Yokoi S. Academic Editor.
• Is Part Of: ISRN computer graphics. Volume 2012(2012)
• Publication Date: 2012-03-15
• Subjects: Computer graphics -- Periodicals; Computer graphics; Periodicals; 006.6
• DOI: 10.5402/2012/248285
• Languages: English
• ISSNs: 2090-7869

Abstract

Abstract : Content-based image retrieval from large resources has become an area of wide interest in many applications. In this paper we present a CBIR system that uses Ranklet Transform and the color feature as a visual feature to represent the images. Ranklet Transform is proposed as a preprocessing step to make the image invariant to rotation and any image enhancement operations. To speed up the retrieval time, images are clustered according to their features using k -means clustering algorithm.