Novel Approach to Color Texture Retrieval Based on GLCM
Miroslav Benčo, Róbert Hudec, Martina Zachariášová, Patrik Kamencay, Slavomír Matúška · Communications - Scientific letters of the University of Zilina · 2013
The color and texture are very important features in image analysis. In this paper, the combination of these features is presented. Several approaches for color texture features extraction are researched. The improvement of the one-dimensional version of GLCM (Gray Level Co-occurrence Matrix) for color textures was designed. We named this method as Color Level Co-occurrence Matrix (1D-CLCM). The experiments on database of 2600 color images are provided. Finally, the evaluation and comparison of image retrieval results for separate methods are presented.