System for scaling images using neural networks

Details System for scaling images using neural networks System for scaling images using neural networks

2008-01-29

2010-06-08

Strege, John B (Department: 2624)

Image analysis

Image transformation or preprocessing

Changing the image coordinates

C382S156000, C382S300000

Reexamination Certificate

active

07734117

ABSTRACT:
An artificial neural network (ANN) based system that is adapted to process an input pattern to generate an output pattern related thereto having a different number of components than the input pattern. The system (26) is comprised of an ANN (27) and a memory (28), such as a DRAM memory, that are serially connected. The input pattern (23) is applied to a processor (22), where it can be processed or not (the most general case), before it is applied to the ANN and stored therein as a prototype (if learned). A category is associated with each stored prototype. The processor computes the coefficients that allow the determination of the estimated values of the output pattern, these coefficients are the components of a so-called intermediate pattern (24). Assuming the ANN has already learned a number of input patterns, when a new input pattern is presented to the ANN in the recognition phase, the category of the closest prototype is output therefrom and is used as a pointer to the memory. In turn, the memory outputs the corresponding intermediate pattern. The input pattern and the intermediate pattern are applied to the processor to construct the output pattern (25) using the coefficients. Typically, the input pattern is a block of pixels in the field of scaling images.

REFERENCES:
patent: 4631751 (1986-12-01), Anderson et al.
patent: 4712140 (1987-12-01), Mintzer et al.
patent: 4872064 (1989-10-01), Tutt et al.
patent: 5008752 (1991-04-01), Van Nostrand
patent: 5327257 (1994-07-01), Hrytzak et al.
patent: 5347597 (1994-09-01), Stephenson
patent: 5469216 (1995-11-01), Takahashi et al.
patent: 5710869 (1998-01-01), Godefroy et al.
patent: 6233365 (2001-05-01), Teruhiko
patent: 6323905 (2001-11-01), Kondo et al.
patent: 6915026 (2005-07-01), Sasai
patent: 6987884 (2006-01-01), Kondo et al.
patent: 11017934 (1999-01-01), None
patent: WO 9616380 (1996-05-01), None
Madani et al.; “ZISC-036 Neuro-processor Based Imaged Processing”, IWANN 2001, pp. 200-207, Jun. 13-15, 2001.
David et al.; “Description and practical uses of IBM ZISC036”, Procceedings of SPIE, vol. 3728, pp. 198-211, Mar. 1999.
Zero Instruction Set Computer Manual—Pattern Recognition Made Easy, Silicon Recognition Inc., Oct. 2000.
David R. et al., “Noise Reduction and Image Enhancement Using a Hardware Implementation of Artificial Neural Networks”, SPIE vol. 3728, pp. 212-221: ISSN 0277-786X, 1998.
Taguchi A. et al., “Enlargement of Digital Images by Using Multi-Neural Networks”, Part of the IS &T/SPIE Conference on Nonlinear Image Processing x, San Jose, CA; Jan. 1999, SPIE vol. 364, pp. 112-119.
Tamako O et al., “Enlargement of Digital Images by Neural Networks”, Bulletin of Faculty of Engineering, University of the Ryukyus University. Ryukyus Japan, No. 59; Mar. 2000, pp. 7-15 *T5 English Trasnslation-Abstract Only.
Sixth Office Action—European Patent Office 80298 Munich, Germany . Communication pursuant to article 94(3)EPC for European Counterpart 02368124.0-2218, Sep. 11, 2008.
Office Action Letter—European Patent Office- Oct. 15, 2008 for European Counterpart 02368124.0-2218.
Daugman J G: “Relaxation neural network for nonorthogonal image transforms”, IEEE International Conference on Neural Networks, Jul. 24-27, 1988, San Diego, CA, USA, pp. 547-560, vol. 1, XP010077930.

Affiliated with

Also associated with

Rating

System for scaling images using neural networks does not yet have a rating. At this time, there are no reviews or comments for this patent.

If you have personal experience with System for scaling images using neural networks, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and System for scaling images using neural networks will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFUS-PAI-O-4200746