Using pyramids to detect good continuation
作者： Tsai-Hong Hong , Michael O. Shneier , Ralph L. Hartley , Azriel Rosenfeld
DOI: 10.1109/TSMC.1983.6313152
关键词: Image processing 、 Set (abstract data type) 、 Feature extraction 、 Artificial intelligence 、 Image segmentation 、 Line (geometry) 、 Line segment 、 Pyramid 、 Pattern recognition (psychology) 、 Computer vision 、 Clutter 、 Computer science
摘要: Pictures containing lines and curves are often perceived by humans as being composed of a smaller number more global figures. For example, broken set collinear line segments is single straight line, even in the presence other overlapping segments. A method extracting such figures from images automatically highly parallel manner presented this work. pyramid successively lower-resolution used to transform problem one search local good continuation. Using pyramid, that both sparse obscured can successfully be extracted background clutter suppressed.
sci-hub.se 参考文章(5)
George Armitage Miller, The magical number seven plus or minus two: some limits on our capacity for processing information ,(1956)
T. H. Hong, M. Shneier, Extracting Compact Objects Using Linked Pyramids IEEE Transactions on Pattern Analysis and Machine Intelligence. ,vol. PAMI-6, pp. 229- 237 ,(1984) , 10.1109/TPAMI.1984.4767506
Ann Scher, Michael Shneier, Azriel Rosenfeld, CLUSTERING OF COLLINEAR LINE SEGMENTS Pattern Recognition. ,vol. 15, pp. 85- 91 ,(1982) , 10.1016/0031-3203(82)90003-6
Michael Shneier, Extracting linear features from images using pyramids NASA STI/Recon Technical Report N. ,vol. 81, pp. 11366- ,(1980) , 10.21236/ADA090238
Michael Shneier, Two hierarchical linear feature representations: Edge pyramids and edge quadtrees Computer Graphics and Image Processing. ,vol. 17, pp. 211- 224 ,(1981) , 10.1016/0146-664X(81)90002-2