Title :
Object extraction based on local features
Author :
Kosako, Akinori ; Ralescu, Anca L.
Author_Institution :
Lab. for Int. Fuzzy Eng. Res., Yokohama, Japan
Abstract :
The eigenspace method for object extraction is extended as follows: local object features and location constraints between these are modeled under different angles of rotation. The resulting method can accurately extract the modeled object region in the image under varying viewing angles and/or when occlusions are present
Keywords :
computational geometry; feature extraction; image segmentation; object detection; local object features; location constraints; object extraction; object region extraction; occlusions; varying viewing angles; Computer vision; Concrete; Data mining; Floors; Fuzzy reasoning; Image recognition; Laboratories; Parametric statistics; Stability; USA Councils;
Conference_Titel :
Fuzzy Systems, 1995. International Joint Conference of the Fourth IEEE International Conference on Fuzzy Systems and The Second International Fuzzy Engineering Symposium., Proceedings of 1995 IEEE Int
Conference_Location :
Yokohama
Print_ISBN :
0-7803-2461-7
DOI :
10.1109/FUZZY.1995.410024
