DocumentCode
3441666
Title
Extraction of depth information by cellular neural networks
Author
Tanaka, Mamoru ; Awata, Mitsuhiko
Author_Institution
Dept. of Electr. Eng., Sophia Univ., Tokyo, Japan
Volume
6
fYear
1994
fDate
30 May-2 Jun 1994
Firstpage
281
Abstract
This paper describes dynamic depth extraction for binocular stereo visual information by CNN (cellular neural network). The quantization for the funneling information is done by parallel neurons. And, the correspondence problem can be solved by pattern recognition for analog images reconstructed from the transmitted funneling halftoning images. The competitive CNN is used. The computer simulation will show the verification for dynamic extraction process for analog stereo images
Keywords
cellular neural nets; data compression; image coding; quantisation (signal); stereo image processing; analog stereo images; binocular stereo visual information; cellular neural networks; competitive CNN; correspondence problem; depth information extraction; funneling information; halftoning images; parallel neurons; pattern recognition; quantization; Biological neural networks; Cellular neural networks; Data mining; Equations; Image reconstruction; Neurons; Pattern recognition; Retina; Shape; Signal processing;
fLanguage
English
Publisher
ieee
Conference_Titel
Circuits and Systems, 1994. ISCAS '94., 1994 IEEE International Symposium on
Conference_Location
London
Print_ISBN
0-7803-1915-X
Type
conf
DOI
10.1109/ISCAS.1994.409581
Filename
409581
Link To Document