Browsing by Author "Kao, Jau-Hong"

Now showing 1 - 2 of 2

Finding point correspondence using local similarity and global constraint
(2006)
Chuang, Jen-Hui
;
Kao, Jau-Hong
;
Lin, Chien-Chou
;
資訊工程學系
;
Department of Computer Science
Establishing feature point correspondences from a pair of stereo images or a long sequence of images is a very important research topic in computer vision. In this paper, an algorithm using local similarity and global constraint to obtain point correspondence is proposed. The point correspondences are obtained by comparing the color codes, computed by image gradients obtained as by-products from the corner detector, and spatial relationships among neighboring feature points.
Practical error analysis of cross-ratio-based planar localization
(2007)
Chuang, Jen-Hui
;
Kao, Jau-Hong
;
Lin, Horng-Horng
;
Chin, Yu-Ting
;
資訊工程學系
Recently, more and more computer vision researchers are paying attention to error analysis so as to fulfill various accuracy requirements arising from different applications. As a geometric invariant under projective transformations, cross-ratio is the basis of many recognition and reconstruction algorithms which are based on projective geometry. We propose an efficient way of analyzing localization error for computer vision systems which use cross-ratios in planar localization. By studying the inaccuracy associated with cross-ratio-based computations, we inspect the possibility of using linear transformation to approximate localization error due to 2-D noises of image extraction for reference points. Based on such a computationally efficient analysis, a practical way of choosing point features in an image so as to establish the probabilistically most accurate planar location system using cross-ratios is developed.