PATTERN RECOGNITION SYSTEM

• US 20150302268A1
• Filed: 04/16/2014
• Published: 10/22/2015
• Est. Priority Date: 04/16/2014
• Status: Active Grant

• Current Assignee: I.R.I.S. (Fidelity National Information Services Incorporated)
• Original Assignee: I.R.I.S. (Fidelity National Information Services Incorporated)
• Inventors: DAUW, Michel, DE MUELENAERE, Pierre, DUPONT, Olivier, COLLET, Frederic, HAUTOT, Jordi, HENSGES, Gunter
• Granted Patent: US 9,311,558 B2
• Time in Patent Office: Days
• US Class Current: 1/1
• CPC Class Codes: G06F 18/2136 based on sparsity criteria, e.g. with an overcomplete basis
• CPC Class Codes: G06F 18/24 Classification techniques
• CPC Class Codes: G06T 5/10 using non-spatial domain filtering
• CPC Class Codes: G06V 30/10 Character recognition
• CPC Class Codes: G06V 30/18038 Biologically-inspired filters, e.g. difference of Gaussians [DoG], Gabor filters
• CPC Class Codes: G06V 30/19127 Extracting features by transforming the feature space, e.g. multidimensional scaling; Mappings, e.g. subspace methods

Abstract

A method for identifying a pattern in an image. In a first step the image is normalized to a binary matrix. A binary vector is subsequently generated from the binary matrix. The binary vector is filtered with a sparse matrix to a feature vector using a matrix vector multiplication wherein the matrix vector multiplication determines the values of the feature vector by applying program steps which are the result of transforming the sparse matrix in program steps including conditions on the values of the binary vector. Lastly, from the feature vector, a density of probability for a predetermined list of models is generated to identify the pattern in the image,

Claims

1. A method for identifying a pattern in an image, comprising the steps of

normalizing the image to a binary matrix,

generating a binary vector from the binary matrix,

filtering the binary vector with a sparse matrix using a matrix vector multiplication to a feature vector,

creating with the feature vector a density of probability for a predetermined list of models,

selecting the model with the highest density of probability as the best model, and

classifying the best model as the pattern of the input image,

wherein the matrix vector multiplication determines the values of the feature vector by applying program steps which are the result of transforming the sparse matrix in program steps including conditions on the values of the binary vector.

2. The method according to claim 1, wherein the conditions on the values of the binary vector are verifying if the values of the elements of the binary vector are non-zero.

3. The method according to claim 1, wherein the transforming of the sparse matrix in program steps further includes conditions on the values of the elements of the sparse matrix.

4. The method according to claim 3, wherein the conditions on the values of the elements of the sparse matrix are verifying if the values of the elements of the sparse matrix are higher than a predetermined value.

5. The method according to claim 4, wherein the image is an image of an Asian character.

6. The method according to claim 5, wherein the binary matrix is a 64×

64 matrix.

7. The method according to claim 6, wherein the sparse matrix is the result of a filtering based on a Gabor function.

8. A computer program product directly loadable into a memory of a computer, comprising software code portions for performing the steps of the method of claim 1 when said product is run on a computer.

9. A computer program product according to claim 8, stored on a computer usable medium.

10. A method for identifying a pattern in an image, comprising the steps of

normalizing the image to a binary matrix,

generating a binary vector from the binary matrix,

filtering the binary vector with a sparse matrix using a matrix vector multiplication to become a feature vector,

creating with the feature vector a density of probability for a predetermined list of models,

selecting the model with the highest density of probability as the best model, and

classifying the best model as the pattern of the input image,

wherein the matrix vector multiplication is an approximate matrix vector multiplication including only the elements of the binary vector which are not zero and including only the elements of the sparse matrix which are higher than a predetermined value.

11. The method according to claim 10, wherein the image is an image of an Asian character.

12. The method according to claim 11, wherein the binary matrix is a 64×

64 matrix.

13. The method according to claim 12, wherein the sparse matrix is the result of a filtering based on a Gabor function.

14. A computer program product directly loadable into a memory of a computer, comprising software code portions for performing the steps of the method of claim 10 when said product is run on a computer.

15. A computer program product according to claim 14, stored on a computer usable medium.

16. An approximate matrix vector multiplication method comprising the steps of:

unrolling the matrix in program steps including at least one condition on the values of the elements of the vector, and

applying the program steps on the vector to create the result of the matrix vector multiplication.

17. The matrix vector multiplication according to claim 16, wherein the conditions on the values of the binary vector are verifying if the values of the elements of the binary vector are non-zero.

18. The matrix vector multiplication according to claim 16, wherein the program steps further include at least one condition on the values of the elements of the matrix.

19. The matrix vector multiplication according to claim 18, wherein the conditions on the values of the binary vector are verifying if the values of the elements of the binary vector are non-zero.

20. A computer program product directly loadable into a memory of a computer, comprising software code portions for performing the steps of the method of claims 16 when said product is run on a computer.

21. A computer program product according to claim 20, stored on a computer usable medium.