Title :
Automatic generation of prototypes in 3D structural object recognition
Author :
JIA, Jin ; Abe, Keiichi
Author_Institution :
Graduate Sch. of Sci. & Eng., Shizuoka Univ., Japan
Abstract :
A scheme of generating a prototype automatically from multiple learning objects is presented. The learning objects are not just one and the same object but different objects belonging to a same object class. In this paper we show how to generate prototypes and test the generated prototypes in recognizing objects from images of real scenes. Satisfactory recognition results were obtained
Keywords :
computer vision; image matching; learning systems; object recognition; stereo image processing; 3D structural object recognition; automatic prototype generation; computer vision; graph matching; learning systems; multiple learning objects; Computer science; Computer vision; Design engineering; Image recognition; Image segmentation; Joining processes; Layout; Object recognition; Prototypes; Testing;
Conference_Titel :
Pattern Recognition, 1998. Proceedings. Fourteenth International Conference on
Conference_Location :
Brisbane, Qld.
Print_ISBN :
0-8186-8512-3
DOI :
10.1109/ICPR.1998.711239
