Abstract. Matching of rigid shapes is an important problem in numerous applications across the boundary of computer vision, pattern recognition and computer graphics communities. A...
This paper presents a probabilistic algorithm for segmenting and recognizing text embedded in video sequences. The algorithm approximates the posterior distribution of segmentatio...
In a variety of applications (including automatic target recognition) image classification algorithms operate on compressed image data. This paper explores the design of optimal t...
Statistical methods, such as independent component analysis, have been successful in learning local low-level features from natural image data. Here we extend these methods for le...
We present in this paper a new multi-class Bayes classifier that permits using separate feature vectors, chosen specifically for each class. This technique extends previous work o...