Image analysis – Learning systems – Neural networks
Patent
1992-04-28
1996-04-23
Boudreau, Leo
Image analysis
Learning systems
Neural networks
382203, 382205, G06K 962
Patent
active
055111343
ABSTRACT:
A two-dimensional bit image generated by the input device is processed by a four-layer neural network and recognized. The neurons in the second layer are connected only to the neurons of the first layer aligned in a specific direction, thereby enabling the second layer to extract line components in specific directions. The second layer is further divided into plural regions, and all neurons in each region are connected to one corresponding neuron in the third layer. The output of the third layer neurons thus express the position and degree of the extracted line component in the image. All of the neurons in the third layer are connected to all of the neurons in the fourth layer, and image recognition is possible by learning.
REFERENCES:
patent: 4805225 (1989-02-01), Clark
patent: 5040230 (1991-08-01), Takatori et al.
patent: 5046019 (1991-09-01), Basehore
patent: 5111516 (1992-05-01), Nakano et al.
patent: 5153923 (1992-10-01), Matsuba et al.
Wasserman, "What are they and why is everybody so interested . . . " Spring 88, pp. 10-15.
Berkan et al, "Concept of Learning Equilibrium Dynamics . . . " Jul. 9, 1990, pp. 920-924.
T. Morita and K. Fuji, "Recognition System for Handwritten Letters Simulating Visual Nervous System", Electronics and Communications in Japan, vol. 52-C, No. 7, pp. 100-108 (1969).
T. A. Jamison and R. J. Schalkoff, "Feature Extraction and Shape Classification of 2-D Polygons Using a Neural Network", Proceedings of the Southeastcon, vol. 3 of 3, pp. 953-958 (1989).
X. Zhu et al., "Handwritten Character Recognition by a Layered Neural Network", Systems and Computers in Japan, vol. 21, No. 13, pp. 88-97 (1990).
K. Fukushima et al., "Neocognitron: A New Algorithm for Pattern Recognition Tolerant of Deformations and Shifts in Position", Pattern Recognition, vol. 15, No. 6, pp. 455-469 (1982).
"Orig. Cont--Neocognition: A Hierarchial Neural Network Cap. Of Visual Pattern Recognition" by K. Fukushima Neural Networks, vol. 1, pp. 119-131 (1988).
"Optical Neurochip based on a 3 Layered feed forward model" by J. Ohta et al. Optical Letters, vol. 15, No. 23, pp. 1362-1364 (Dec. 1, 1990).
"Proposal of a quantized learning rule and its application to optical neural network for 26 char.-alpha recognition", by M. Takahashi et al. pp. 321-322.
"GaAs/AlGaAs Optical Neurochip (Second Report)" by Y. Nitta et al. copied from Conference Record of 1990 International Topical Meeting on Optical Computing pp. 319-320.
Masatoshi Ishikawa, et al., "Optical association: a simple model for optical associtive memory", Applied Optics, vol. 28, No. 2, pp. 291-301 (Jan. 15, 1989).
Kuratomi Yasunori
Ogawa Hisahito
Boudreau Leo
Kelley Chris
Matsushita Electric - Industrial Co., Ltd.
LandOfFree
Image recognition device and image recognition method 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 recognition device and image recognition method, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Image recognition device and image recognition method will most certainly appreciate the feedback.
Profile ID: LFUS-PAI-O-2315556