2-D direction histogram based entropic thresholding

Local image features are effective descriptors for image analysis and are also important cues for image segmentation. In this paper, we propose a novel entropic thresholding approach. This approach incorporates local features into a conventional entropic method to implement the thresholding. The local features are obtained from an orientation histogram to describe the edge property of the local neighborhood. To verify the performance of our method, thresholding was carried out on different types of images and compared with some well-known entropic approaches. Experimental results show that using the local edge property can give a better thresholding result.