Title :
Representation, recognition and reconstruction of objects through a features network
Author :
Silva, Tito ; Rosa, Agostinho
Author_Institution :
Laseeb-Syst. & Robotics Inst.-IST, Tech. Univ. Lisbon, Portugal
fDate :
6/24/1905 12:00:00 AM
Abstract :
We present a new approach on visual structures recognition. It consists of a representation model which stores the internal relations of visual structures in a location and orientation-invariant way. The system also learns abstract higher-level visual concepts which may be properly recalled. An application example is provided for illustration
Keywords :
image recognition; image reconstruction; image representation; learning (artificial intelligence); neural nets; neurophysiology; physiological models; vision; abstract visual concepts; conceptual cortex; image reconstruction; neural network; receptive fields; representation model; visual cortex; visual structures recognition; Brain modeling; Coherence; Computer vision; Image analysis; Image sequences; Neural networks; Neurons; Object detection; Robots; Solids;
Conference_Titel :
Neural Networks, 2002. IJCNN '02. Proceedings of the 2002 International Joint Conference on
Conference_Location :
Honolulu, HI
Print_ISBN :
0-7803-7278-6
DOI :
10.1109/IJCNN.2002.1007757
