Title :
Recognition and visual learning of articulated shape by accumulative Hopfield matching
Author :
Li, Wen-Jing ; Lee, Tong
Author_Institution :
Dept. of Electron. Eng., Chinese Univ. of Hong Kong, Shatin, China
Abstract :
We describe a system that can recognize and learn a visual model of an articulated object automatically given different views of the object, provided that the local structure is unchanged. The system is based on the Hopfield style network and finds the feature correspondences between different views of an articulated object. With this proposed matching system, we can finally learn the relationship between articulated parts of the object and the poses detected. Experiments on real images show the effectiveness of the proposed system
Keywords :
Hopfield neural nets; feature extraction; learning (artificial intelligence); object recognition; Hopfield style network; accumulative Hopfield matching; articulated shape; feature correspondences; local structure; matching system; visual learning; Image generation; Image recognition; Layout; Neural networks; Object detection; Object recognition; Robustness; Shape; Target recognition; Very large scale integration;
Conference_Titel :
Neural Networks, 2001. Proceedings. IJCNN '01. International Joint Conference on
Conference_Location :
Washington, DC
Print_ISBN :
0-7803-7044-9
DOI :
10.1109/IJCNN.2001.938500
