DocumentCode
2875515
Title
Parallel answer-in-weights neural network implementation for image preprocessing
Author
Valova, Iren ; Kosugi, Yukio
Author_Institution
Interdisciplinary Graduate Sch. & Sci. & Eng., Tokyo Inst. of Technol., Japan
fYear
1996
fDate
4-6 Sep 1996
Firstpage
569
Lastpage
578
Abstract
A neural network for image preprocessing is utilized for a parallel neurocomputer. The algorithm is based on an inverse approach and provides lossless decomposition and high rate compression of grey scale pictures with dimensions 128×128 pixel. The basic properties of the method are discussed and demonstrated by examples. The network is easily expandable for the purposes of image segmentation or feature extraction
Keywords
image processing; neural nets; parallel architectures; feature extraction; grey scale pictures; high rate compression; image preprocessing; image segmentation; inverse approach; lossless decomposition; parallel answer-in-weights neural network; parallel neurocomputer; Feature extraction; Image coding; Image decomposition; Image quality; Image segmentation; Matrix decomposition; Neural network hardware; Neural networks; Pixel; Sun;
fLanguage
English
Publisher
ieee
Conference_Titel
Neural Networks for Signal Processing [1996] VI. Proceedings of the 1996 IEEE Signal Processing Society Workshop
Conference_Location
Kyoto
ISSN
1089-3555
Print_ISBN
0-7803-3550-3
Type
conf
DOI
10.1109/NNSP.1996.550064
Filename
550064
Link To Document