Method of image enhancement using convolution kernels

Image analysis – Image enhancement or restoration – Artifact removal or suppression

Patent

Rate now

  [ 0.00 ] – not rated yet Voters 0   Comments 0

Details

382101, 382205, 382254, 382279, G06K 940, G06K 900, G06K 956

Patent

active

056470274

ABSTRACT:
Noisy images of graphical or pictorial records, such as hand-written postal addresses, are cleaned by a method of analyzing the shapes of pixel clusters. According to such method, a set of structuring kernels is used to extract primitive shapes. The outcome of this extraction process is used to determine whether each pixel, in turn, is to be treated as part of a image element such as an alphanumeric character.

REFERENCES:
patent: 4984286 (1991-01-01), Dolazza
patent: 5027419 (1991-06-01), Davis
patent: 5054102 (1991-10-01), Gaborski
patent: 5081692 (1992-01-01), Kwon et al.
patent: 5138695 (1992-08-01), Means et al.
patent: 5202933 (1993-04-01), Bloomberg
patent: 5212741 (1993-05-01), Barski et al.
patent: 5216725 (1993-06-01), McCubbrey
patent: 5220614 (1993-06-01), Crain
patent: 5224176 (1993-06-01), Crain
patent: 5392137 (1995-02-01), Okubo
patent: 5392365 (1995-02-01), Steinkirchner
patent: 5521985 (1996-05-01), Camp, Jr. et al.
A. Rosenfeld et al, "Digital Picture Processing", vol. 1 and 2, Academic Press, Orlando, 1982.
A. N. Netravalli, et al., "Digital Pictures",Plenum Press, New York, 1988.
Henk, J. A. M. Heijmans, "Morphological Image Operators," Acedemic Press, Boston, 1994.
I. Pitas, et al., "Nonlinear Digital Filters," Kluwer Academic Publishers, Boston, 1990.
W. K. Pratt, "Digital Image Processing," John Wiley & Sons, New York, 1991.
B. R. Meijer, "Rules and algorithms for the design of templates for template matching," Proc. 11th IAPR Int. Conf. on Pattern Recognition, vol. 1, Conf. A: Computer Vision and Applications, IEEE Computer Society Press, Los Alamitos, CA (1992) pp. 760-763.
H. P. Graf, et al., "Address Block Location with a Neural Net System," Neural Information Processing Systems 6, Morgan Kaufmann, San Francisco (1994), pp. 785-792.
H. P. Graf, et al., "Image Recognition with an Analog Neural Net Chip," Proc. 11th IAPR 4 (1992) pp. 11-14.
H. P. Graf, et al., "A Recognfigurable CMOS Neural Network," Digest IEEE Int. Solid State Circuits Conf., (1990), pp. 144-145.
H. P. Graf, et al., "Reconfigurable Neural Net Chip with 32K Connections," Neural Information Processing Systems 3, J. E. Moody and D. S. Touretzky, Eds., Morgan Kaufmann, San Mateo, CA (1991), pp. 1032-1038.
E. Cosatto, et al., "NET32K High Speed Image Understanding System," Proc. Fourth International Conference on Microelectronics for Neural Networks and Fuzzy Systems, Sep. 26-28, 1994, IEEE Computer Society Press, Los Alamitos, CA (1994), pp. 413-421.
R. Hummel, et al., "Computational Considerations in Convolution and Feature-extraction in Images," From Pixels to Features, J. C. Simon ed., Elsevier Science Publishers B. V., North Holland, (1989), pp. 91-102.
R. P. Loce, "The Use of First-Order Structuring-Element Libraries to Design Morphological Filters," Proceedings of 11th IAPR International Conference on Pattern Recognition, Aug. 30-Sep. 3, 1992, vol. III, Conference C: Image, Speech, and Signal Analysis, pp. 256-259.
V. P. Concepcion, et al., "Using morphology and associative memories to associate salt-and-pepper noise with OCR error rates in document images," Proceedings of SPIE - The International Society for Optical Engineering, vol. 1661.

LandOfFree

Say what you really think

Search LandOfFree.com for the USA inventors and patents. Rate them and share your experience with other people.

Rating

Method of image enhancement using convolution kernels 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 of image enhancement using convolution kernels, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Method of image enhancement using convolution kernels will most certainly appreciate the feedback.

Rate now

     

Profile ID: LFUS-PAI-O-2413445

  Search
All data on this website is collected from public sources. Our data reflects the most accurate information available at the time of publication.