Image analysis – Image compression or coding – Adaptive coding
Patent
1997-05-14
1998-09-22
Boudreau, Leo H.
Image analysis
Image compression or coding
Adaptive coding
382232, 382244, 382156, G06K 936, G06K 946
Patent
active
058127003
ABSTRACT:
The invention is embodied in an image data system including a lossy image compressor having an image compression ratio in excess of 10 for producing first compressed image data from an original image, the first compressed image data specifying a corresponding one of a set of predetermined images, apparatus for computing an difference between the original image and the predetermined image specified by the first compressed image data and a lossless image compressor for compressing at least the difference to produce second compressed image data.
REFERENCES:
patent: 4602333 (1986-07-01), Komori
patent: 5005206 (1991-04-01), Naillon et al.
patent: 5267334 (1993-11-01), Normille et al.
patent: 5333212 (1994-07-01), Ligtenberg
patent: 5339164 (1994-08-01), Lim
patent: 5420639 (1995-05-01), Perkins
patent: 5450132 (1995-09-01), Harris et al.
"A Neural Network Based VLSI Vector Quantizer for Real-Time Image Compression" Fang et al. IEEE Comp. Soc. Press 1991 pp. 342-351.
"Data Compression and VLSI Implementation" Fang, Wai-Chi ASIC Conference Sep. 1993 pp. 570-579.
Rice, Robert F. On the Optimality of Code Options for a Universal Noisless Coder, JPL Publication 91-92, Feb. 15, 1991.
Rice, Robert F. Some Practical Universe Noisless Coding Techniques, Part III, Module PS114, K+, JPL Publication 91-93, Nov. 15, 1991.
Fang Wai-Chi
Sheu Bing J.
Boudreau Leo H.
California Institute of Technology
Mehta Bhavesh
LandOfFree
Data compression neural network with winner-take-all function does not yet have a rating. At this time, there are no reviews or comments for this patent.
If you have personal experience with Data compression neural network with winner-take-all function, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Data compression neural network with winner-take-all function will most certainly appreciate the feedback.
Profile ID: LFUS-PAI-O-1631573