Robust Image Segmentation Using LBP Embedded Region Merging

Abstract

This paper is under in-depth investigation due to suspicion of possible plagiarism on a high similarity index. The region merging algorithm by the maximal similarity with color histogram has been applied successfully in color image segmentation. However, only using color histogram information is not sufficient and effective for superior segmentation. We propose a novel color image segmentation method based on region merging by using joint color-texture histogram in this paper. The proposed method incorporates both color histogram and texture histogram information to measure the similarity of different regions and thus to guide the region merging process. Experiments show that our method is more accurate and robust than traditional image segmentation methods based on region merging.