K. Kaur, C. Singh, Ekta Walia
Dec 14, 2014
Proceedings of the 2014 Indian Conference on Computer Vision Graphics and Image Processing
Color, texture, and shape are the low level features required for an effective image retrieval system. In this paper, we propose a hybrid approach which performs the fusion of color and texture features for image retrieval. The color features are extracted by using the well known color histogram technique, while the texture features are captured using recently proposed features, known as orthogonal combination of linear binary pattern (OCLBP). The performance of the proposed approach is compared with a recently developed method, color difference histogram (CDH). Performance evaluation through extensive experiments reveals the superiority of the proposed approach over the state-of-the-art technique.