Title :
Figure recognition with intentional observation
Author :
Sakaguchi, Yutaka ; Nakano, Kaoru
Author_Institution :
Dept. of Math. Eng. & Inf. Phys., Tokyo Univ., Japan
Abstract :
When perceiving an object humans do not receive stimuli passively, but observe the object actively to obtain useful information for recognizing it. A neural network model which realizes such active perception by utilizing neural dynamics is proposed. The model consists of a sensory unit, a representation field, and recognition units. The model sequentially collects local information of the presented figure, gradually constructs its internal image, and recognizes it based on the constructed internal image. An intentional observation mechanism was constructed by which the model can selectively observe informative parts of the figure for constructing the internal image. Several computer simulation results are described. The model is discussed from the viewpoint of Bayesian inference and information theory
Keywords :
Bayes methods; inference mechanisms; information theory; neural nets; visual perception; Bayesian inference; active perception; figure recognition; information theory; intentional observation; neural dynamics; neural network model; recognition units; representation field; sensory unit; Bayesian methods; Biological systems; Computer simulation; Computer vision; Humans; Neural networks; Pattern recognition; Physics; Psychology; Shape;
Conference_Titel :
Neural Networks, 1992. IJCNN., International Joint Conference on
Conference_Location :
Baltimore, MD
Print_ISBN :
0-7803-0559-0
DOI :
10.1109/IJCNN.1992.227055
