In this paper, we propose a new technique to perform figure-ground segmentation in image sequences of moving objects under varying illumination conditions. Unlike most of the alg...
Francesc Moreno-Noguer, Alberto Sanfeliu, Dimitris...
Abstract. Illumination variation is one of intractable yet crucial problems in face recognition and many lighting normalization approaches have been proposed in the past decades. N...
Hu Han, Shiguang Shan, Laiyun Qing, Xilin Chen, We...
This paper describes a skeletonization process for grayscale or color images based on the diffusion of the color gradient vectors by using a simple iterative regularization scheme...
Human superiority over computers in identifying natural objects like clouds, water, grass etc. comes from two capabilities: the capability to maintain a growing knowledge base per...
Abstract. Segmentation is an important step to obtain quantitative information from tomographic data sets. To this end, global thresholding is often used in practice. However, it i...