CNN state equations for binocular stereo vision

Author

Tanaka, Mamoru ; Awata, Mitsuhiko ; Kanaya, Mitsuhisa

Author_Institution

Dept. of Electr. Eng., Sophia Univ., Tokyo, Japan

Volume

3

fYear

1994

fDate

27 Jun-2 Jul 1994

Firstpage

1929

Abstract

This paper describes CNN (cellular neural network) state equations to perform direct dynamic halftoning and dynamic depth extraction for binocular stereo visual information. The quantization for the funneling information is done by parallel neurons without the use of multiple bit analog-to-digital converters, and, the correspondence problem can be solved by pattern recognition for analog images reconstructed from the transmitted halftoning images. Computer simulation shows the verification for dynamic halftoning and extraction process for analog stereo images

Keywords

cellular neural nets; image recognition; stereo image processing; analog stereo images; binocular stereo vision; cellular neural network state equations; correspondence problem; direct dynamic halftoning; dynamic depth extraction; extraction process; funneling information; parallel neurons; pattern recognition; quantization; Analog-digital conversion; Cellular neural networks; Computer simulation; Data mining; Equations; Image reconstruction; Neurons; Pattern recognition; Quantization; Stereo vision;

fLanguage

English

Publisher

ieee

Conference_Titel

Neural Networks, 1994. IEEE World Congress on Computational Intelligence., 1994 IEEE International Conference on

Conference_Location

Orlando, FL

Print_ISBN

0-7803-1901-X

Type

conf

DOI

10.1109/ICNN.1994.374455

Filename

374455