Abstract
In order to recognize objects one must be able to compute a stable, canonical representation that can be used to index into memory. The most widely accepted theory on how people recognize objects seems to be that they first segment the object into its component parts and then recognition occurs by using this part description to classify the object. The problem of segmenting objects into parts, however, has remained unsolved despite much research.
© 1989 Optical Society of America
PDF ArticleMore Like This
Ruzena Bajcsy and Alok Gupta
WA2 Image Understanding and Machine Vision (IUMV) 1989
Heinrich H. Bulthoff, Shimon Edelman, and Daphna Weinshall
MJJ5 OSA Annual Meeting (FIO) 1989
M.S. Monjur, S. Tseng, A.M. Khan, N.M. Rajpoot, and M.S. Shahriar
JTh2A.24 CLEO: QELS_Fundamental Science (CLEO:FS) 2013