Image processing using genetic mutation of neural network parame

Details Image processing using genetic mutation of neural network parame Image processing using genetic mutation of neural network parame

1993-12-17

1996-10-22

Downs, Robert W.

395 22, G06T 500, G06F 1518

Patent

active

055685900

ABSTRACT:
A system and method of image processing using neural networks to control image processing elements. Neural network parameters are defined by genotypes consisting of network vectors. Genotypes may be selectively mutated and cross-bred to provide a mechanism for modifying the behavior of the neural networks, or phenotypes. Genetic modeling processes are used to perform such mutation and cross-over. User feedback concerning output images, is used to select particular genotypes for further mutation and exploration. Preconditioning is employed to extract structural information from source images prior to network processing. Genetic morphing and subnet fusion are also available, to provide additional variations on image processing operations.

REFERENCES:
David Salesin et al., "Adjustable Tools: An Object-Oriented Interaction Metaphor", ACM Transactions on Graphics, vol. 12, No. 1, Jan., 1993, pp. 103-107.
IBM Technical Disclosure Bulletin, vol. 33, No. 6B, Nov. 1990. US; pp. 61-62.
PCT International Application WO,A,90 11568 (Honeywell Inc.) 4 Oct. 1990; pp. 1-3.
Computer Graphics, vol. 25, No. 4, Jul. 1991, USA; Sims, K. "Artificial Evolution for Computer Graphics".
D. Montana and L. Davis, "Training Feedforward Neural Networks Using Genetic Algorithms," Proc. Int'l. Joint Conf. on Artificial Intelligence.
S. Baluja, et al., "Simulating a User's Preferences: Towards Automated Artificial Evolution for Computer Generated Images," Carnegie Mellon University, CMU-CS-93-198.
M. Schwartz et al., "A CMOS-Array-Computer with On-Chip Communication Hardware Developed for Massively Parallel Applications," 1991 IEEE Int'l. Joint Conf. on Neural Networks (Nov. 1991), pp. 89-94.
T. Masui, "Graphic Layout with Interactive Genetic Algorithms," Proc. 1992 IEEE Workshop on Visual Languages (Sep. 1992), pp. 74-80.

Affiliated with

Also associated with

Rating

Image processing using genetic mutation of neural network parame does not yet have a rating. At this time, there are no reviews or comments for this patent.

If you have personal experience with Image processing using genetic mutation of neural network parame, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Image processing using genetic mutation of neural network parame will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFUS-PAI-O-2366241