Image analysis – Pattern recognition – Feature extraction
Patent
1994-08-01
1996-02-06
Mancuso, Joseph
Image analysis
Pattern recognition
Feature extraction
382260, G06K 956
Patent
active
054902240
ABSTRACT:
This invention provides a feature extracting circuit including a shift register section arranged to store an image for a predetermined number of lines, the image consisting of a predetermined number of bits, and then to shift the image; a look-up table section for transforming a set of partial image data for a predetermined number of pixels supplied from the shift register section into a direction index and then for outputting the direction index; and a counter section for counting the direction index output from the look-up table section. The feature extracting circuit receives a binary digital image and extracts, as a feature of the image, a direction index which indicates the direction in which the boundary between adjacent black and white pixels extends.
REFERENCES:
patent: 3899771 (1975-08-01), Saraga et al.
patent: 3968475 (1976-07-01), McMahon
patent: 3979722 (1976-09-01), Sakoe
patent: 4003024 (1977-01-01), Riganati
patent: 4040009 (1977-08-01), Kadota et al.
patent: 4075698 (1978-02-01), Code
patent: 4151512 (1979-04-01), Riganati et al.
patent: 4506382 (1985-03-01), Hada et al.
patent: 4630306 (1986-12-01), West et al.
patent: 4805226 (1986-02-01), Guebey
patent: 4962542 (1990-10-01), Klees
Lee, "Digital Circuits and Logic Design", 1977, p. 576, Prentice Hall Inc.
"Implementation of Cellular-Logic Operator Using 3*3 Convolution and Table Lookup Hardware", Computer, Vision, Graphics & Image Processing, vol. 27, No. 1, pp. 115-123.
Canon Kabushiki Kaisha
Mancuso Joseph
LandOfFree
Feature extracting apparatus does not yet have a rating. At this time, there are no reviews or comments for this patent.
If you have personal experience with Feature extracting apparatus, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Feature extracting apparatus will most certainly appreciate the feedback.
Profile ID: LFUS-PAI-O-2181030