Title :
Recognition method of shape distorted objects using hierarchical feature descriptions
Author :
Yang, J.Y. ; Hu, O.
Author_Institution :
Dept. of Comput. Sci., East China Inst. of Technol., Nanjing, China
Abstract :
A method is developed for recognizing shape-distorted and partially overlapped flat objects. Several features which are invariant or insensitive to the shape distortions caused by position, scaling, and 3D rotation are proposed. A hierarchical description and matching technique of the features make the recognition method powerful
Keywords :
pattern recognition; picture processing; 3D rotation; flat object recognition; hierarchical feature descriptions; occlusion; partially overlapping objects; pattern recognition; picture processing; position; scaling; shape-distorted objects; Argon; Artificial intelligence; Character recognition; Shape;
Conference_Titel :
Pattern Recognition, 1988., 9th International Conference on
Conference_Location :
Rome
Print_ISBN :
0-8186-0878-1
DOI :
10.1109/ICPR.1988.28393
