Method for recognizing object images and learning method for neu

Details Method for recognizing object images and learning method for neu Method for recognizing object images and learning method for neu

1994-08-29

1998-04-14

Mancuso, Joseph

Image analysis

Pattern recognition

Feature extraction

382156, 382165, 382203, 382282, G06K 946, G06K 966

Patent

active

057402744

ABSTRACT:
A method for recognizing an object image comprises the steps of extracting a candidate for mineda predetermined object image from an overall image, and making a judgment as to whether the extracted candidate for the predetermined object image is or is not the predetermined object image. The candidate for the predetermined object image is extracted by causing the center point of a view window, which has a predetermined size, to travel to the position of the candidate for the predetermined object image, and determining an extraction area in accordance with the size and/or the shape of the candidate for the predetermined object image, the center point of the view window being taken as a reference during the determination of the extraction area. A learning method for a neural network comprises the steps of extracting a target object image, for which learning operations are to be carried out, from an image, feeding a signal, which represents the extracted target object image, into a neural network, and carrying out the learning operations of the neural network in accordance with the input target object image.

REFERENCES:
patent: 4476494 (1984-10-01), Tugaye
patent: 4652803 (1987-03-01), Kamejima et al.
patent: 4754489 (1988-06-01), Bokser
patent: 5058184 (1991-10-01), Fukushima
patent: 5111516 (1992-05-01), Nakamo et al.
patent: 5220619 (1993-06-01), Keokoek
patent: 5239594 (1993-08-01), Yoda
patent: 5465308 (1995-11-01), Hutcheson et al.
patent: 5604820 (1997-02-01), Ono
Himes, et al., SPIE, vol. 1469, No. 2, VLSI implementable neural networks for target tracking, (1991), pp. 671-682.
Mehanian, et al., SPIE, vol. 1471, Bi-directional Log-polar Mapping for Invariant Object Recognition, (1991), pp. 200-209.
Gawronski, et al., SPIE, vol. 1293, No. 2, Experimental optimization of the Neuronlike Network applied for the processing of moving images, (1990), pp. 838-849.
Lee, et al., SPIE, vol. 937, Applications of Artificial Intelliegence VI (1988), pp. 328-335.
Zhou, et al., IEEE Int'l Conf. on Neural Networks, Computation of Optical Flow Using A Neural Network (1988), pp. 71-78.
Weller, et al., A Gradient Comparison Method For Tracking And Focusing Purposes, Time-Varying Image Processing . . . (1990), pp. 316-322.
Grattoni, et al., Computer Vision . . . , vol., 43, No. 1, A Contour Detection Algorithm Based on the Minimum Radial Inertia (MRI) Criterion, (1988), pp. 22-36.
Kageyu et al., "Augmented Multi-Layer Perception for Rotation and Scale-Invarient Hand-Written Numeral Recognition", 1991 Joint Conference on Neural Networks, IEEE Cat #91CH3065-0, pp. 54-59, vol. 1 Nov. 1991.
"Neocognitron" A Neural Network Model for a Mechanism of Pattern Recognition Unaffected by Shift in Position, Collected Papers of the Institute of Electronics and Communication Engineers of Japan, J62-A(10), pp. 658-665, Oct. 1979.
"Neural Net for Extracting Size Invariant Features", Computrol, No. 29, pp. 26-31.
"Visual and Auditory Information Processing in Living Body System", Information Processing, vol. 23, No. 5, pp. 451-459, 1982.
"Structure and Function of Visual System", Information Processing, vol. 26, No. 2, pp. 108-116, 1985.
"Pattern Recognition Learning System", Image Information (1), 1987 Jan., pp. 31-37.
"Simulation of Saccadic Movement by Pseudo-Retina Mask", Telivision Engineering report, ITEJ Tec. Rep., vol. 14, No. 36, pp. 25-30, ICS' 90-54, AIPS' 90-46, Jun. 1990.
"Neural Net for Specifying a Viewpoint", Television Engineering Report, ITEJ Tec. Rep. vol. 14, No. 33, pp. 25-30, VAI' 90-28, Jun. 1990.

Affiliated with

Also associated with

Rating

Method for recognizing object images and learning method for neu does not yet have a rating. At this time, there are no reviews or comments for this patent.

If you have personal experience with Method for recognizing object images and learning method for neu, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Method for recognizing object images and learning method for neu will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFUS-PAI-O-644423