Title :
Finding Point Correspondence Using Local Similarity and Global Constraint
Author :
Chuang, Jen-Hui ; Kao, Jau-Hong ; Lin, Chien-Chou
Author_Institution :
Dept. of Comput. & Inf. Sci., Nat. Chiao Tung Univ., Hsinchu
fDate :
Aug. 30 2006-Sept. 1 2006
Abstract :
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
Keywords :
computer vision; edge detection; feature extraction; image coding; image colour analysis; image sequences; stereo image processing; color codes; computer vision; corner detector; feature point correspondences; global constraint; image gradients; local similarity; long image sequence; spatial relationships; stereo images; Computer science; Computer vision; Data mining; Detectors; Feature extraction; Image analysis; Information science; Jacobian matrices; Layout; Stereo vision;
Conference_Titel :
Innovative Computing, Information and Control, 2006. ICICIC '06. First International Conference on
Conference_Location :
Beijing
Print_ISBN :
0-7695-2616-0
DOI :
10.1109/ICICIC.2006.278
