Image analysis – Learning systems – Neural networks
Patent
1995-11-07
2000-08-08
Au, Amelia
Image analysis
Learning systems
Neural networks
382216, G06T 140
Patent
active
06101270&
ABSTRACT:
A neural network architecture is provided for optical character recognition from an input image in which the target character may be rotated in the image plane. The architecture includes hidden units whose inputs receive image information from portions of the image which are rotationally distributed. That is, the local link between input units and the hidden units is adequate for rotation of the character in the image. Therefore, regardless of the orientation of the image, it is right side up, or approximately so, with respect to one of the hidden units. The hidden units have corresponding inputs with corresponding weight factors, i.e., symmetric weight sharing. Thus, regardless of the orientation of the image, one of the hidden units will produce a high output value indicative of an upright character. Alternatively, a single hidden unit has groups of inputs, each group having a corresponding set of weight factors. The groups are coupled to input units for rotationally distributed portions of the image. Therefore, for any orientation of the image corresponding with one of the groups of inputs of the hidden unit, the hidden unit produces the same output value. In an preferred embodiment, feature information such as local contour direction information is provided to the input units. The feature information is provided with respect to slices of the image taken in different directions.
REFERENCES:
patent: 3636513 (1972-01-01), Tisdale
patent: 3638188 (1972-01-01), Pincoffs et al.
patent: 4933872 (1990-06-01), Vandenberg et al.
patent: 4941122 (1990-07-01), Weideman
patent: 4947449 (1990-08-01), Peppers et al.
patent: 4958939 (1990-09-01), Samad
patent: 5048097 (1991-09-01), Gaborski et al.
patent: 5048100 (1991-09-01), Kuperstein
patent: 5052043 (1991-09-01), Gaborski
patent: 5054094 (1991-10-01), Barski
patent: 5058180 (1991-10-01), Khan
patent: 5060278 (1991-10-01), Fukumizu
patent: 5063605 (1991-11-01), Samad
patent: 5067164 (1991-11-01), Denker et al.
patent: 5075871 (1991-12-01), Weidman
patent: 5086479 (1992-02-01), Takenaga et al.
patent: 5093867 (1992-03-01), Hori et al.
patent: 5119438 (1992-06-01), Ueda et al.
Reed, K.A., "A Translation/Rotation Invariant Neural Network Trained via Conjugate Gradient Optimization," IEEE Conference on Systems Engineering, Aug. 1989.
H. Takahashi, A Simple Recognition Method for Hadwritten Kanji Characters by Using Primitive Connection Directions of Thinking, IBM Japan Ltd.
E. Persoon, K. S. Fu, Shape Discrimination Using Fourier Descriptors, IEEE Transaction Sys., Man, and Cybernetic, vol. SMC-7, No. 3, Mar. 1977, pp. 170-179.
S. W. Lee, H. S. Park and Y. Y. Tang, Translation-,Scale-,and Rotation-invariant Recogntion of Hangul Characters with Transformation Ring Projection, Dept. of Computer Sci. Chungbuk Nat. Univ., Republic of Korea, pp. 829-836.
Y. N. Hsu, H. H. Arsenault and G. April, Rotation-invariant Digital pattern Recognition Using Circular Harmonic Expansion, Applied Optics, vol. 21, No. 22, pp. 4012-4015, Nov. 15, 1982.
N. K. Hu, Visual Pattern Recognition by Moment Invariants, IRE Transactions on Information Theory, pp. 179-187, 1962.
A. Taza and C. Y. Suen, Discrimination of Planar Shapes Using Shape Matrices, IEEE Transaction on Sys., Man. & Cybernetics, vol. 19., No. 5, pp. 1281-1289, Sep./Oct. 1989.
Takahashi, Neural Network Architectures for Rotated Character Recognition, IBM RJ 8459 (76467), Nov. 1, 1991.
S. D. You, G. E. Ford, Connectionish Model for Object Recognition, APIE vol. 1709 Applications of Artificial Neural Networks III (1992), pp. 200-207.
R. Duran, B. Peikari, A New Neural Network Architecture for Rotationally Invariant Object Recognition, IEEE Proceddings of the 34th Midwest Symposium on Circuits and Systems Cat. No. 91CH3143-5, vol. 1, pp. 320-323, May 17, 1991.
Au Amelia
International Business Machines - Corporation
Prikockis Larry J.
LandOfFree
Neural network architecture for recognition of upright and rotat does not yet have a rating. At this time, there are no reviews or comments for this patent.
If you have personal experience with Neural network architecture for recognition of upright and rotat, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Neural network architecture for recognition of upright and rotat will most certainly appreciate the feedback.
Profile ID: LFUS-PAI-O-1157782