Paper Title
Local Tri Directional Tetra Pattern (TDTP) For Texture Classification

Abstract
In this paper, we proposed a technique for Texture based Image classification based on Local tri-directional Tetra pattern (TDTP). Texture is a prominent feature of image and very useful in feature extraction for image retrieval application. The proposed method uses local intensity of pixels based on three directions of the neighbourhood and three patterns are generated from local tri-directions. A magnitude patternis merged with the generated patterns for feature extraction. Hence tetra pattern is obtained. This method is tested on Brodatz texture image database, a texture image database. The efficacy of the proposed method is proven by comparing it with existing algorithms for image retrieval.