We studied a method using support vector machines (SVMs) with walk-based graph kernels for the high-level feature extraction (HLF) task. In this method, each image is first segmen...
We present a Bayesian approach to color constancy which utilizes a nonGaussian probabilistic model of the image formation process. The parameters of this model are estimated direc...
Charles R. Rosenberg, Thomas P. Minka, Alok Ladsar...
We present a novel technique for segmentation of a JPEGcompressed documentbased on block activity. The activity is measured as the number of bits spent to encode each block. Each ...
This paper introduces a novel convex kernel based method for color constancy computation with explicit illuminant parameter estimation. A simple linear render model is adopted and ...
Abstract. Distribution of object colors has been used in computer vision for recognition and indexing. Most of the recent approaches to this problem have been focused on de ning op...