Method and apparatus for separating foreground from background i

Image analysis – Histogram processing – For setting a threshold

Patent

Rate now

  [ 0.00 ] – not rated yet Voters 0   Comments 0

Details

382171, 382270, G06K 900

Patent

active

058898859

ABSTRACT:
A method and apparatus for thresholding gray-scale images containing text as foreground and dirt, colors, noise and the like as background. The method is adaptive in nature and can successfully separate a wide variety of text fonts and sizes, whether printed, typewritten, or handwritten, from the image background. The method uses multiple sets of thresholding process parameters in a contrast-based histogram evaluation to produce multiple candidate thresholded binary images. The method automatically selects the highest quality binary image, that is, the binary image that best represents text in the foreground, from among the multiple candidate binary images. The apparatus for implementing the method is a pipeline processor for highest speed.

REFERENCES:
patent: 3715724 (1973-02-01), Demonte et al.
patent: 4003999 (1977-01-01), Kawahara
patent: 4119947 (1978-10-01), Leighton et al.
patent: 4504972 (1985-03-01), Scherl et al.
patent: 4547811 (1985-10-01), Ochi et al.
patent: 4736441 (1988-04-01), Hirose et al.
patent: 4742556 (1988-05-01), Davis, Jr. et al.
patent: 4794239 (1988-12-01), Allais
patent: 4809308 (1989-02-01), Adams et al.
patent: 4837450 (1989-06-01), Satomura et al.
patent: 4879753 (1989-11-01), El-Sherbini
patent: 4888646 (1989-12-01), Umeda et al.
patent: 4924078 (1990-05-01), Sant'Anselmo et al.
patent: 4929979 (1990-05-01), Kimoto et al.
patent: 4931881 (1990-06-01), Matsui et al.
patent: 4998122 (1991-03-01), Kanno et al.
patent: 5003616 (1991-03-01), Orita et al.
patent: 5046114 (1991-09-01), Zobel
patent: 5048096 (1991-09-01), Beato
patent: 5073953 (1991-12-01), Westdijk
patent: 5081690 (1992-01-01), Tan
patent: 5086485 (1992-02-01), Lin
patent: 5091965 (1992-02-01), Kobayashi et al.
patent: 5121224 (1992-06-01), Ng et al.
patent: 5166986 (1992-11-01), Mizuoka et al.
patent: 5179599 (1993-01-01), Formanek
patent: 5220615 (1993-06-01), Ishii et al.
patent: 5268967 (1993-12-01), Jang et al.
patent: 5384864 (1995-01-01), Spitz
patent: 5444797 (1995-08-01), Spitz et al.
patent: 5452367 (1995-09-01), Bick et al.
patent: 5502776 (1996-03-01), Wanabe
patent: 5572602 (1996-11-01), Naoi et al.
patent: 5581633 (1996-12-01), Hotta et al.
patent: 5583659 (1996-12-01), Lee et al.
patent: 5630037 (1997-05-01), Schindler
M.M. Menon, An Efficient MRF Image-Restoration Technique Using Deterministic Scale-Based Optimization, The Lincoln Laboratory Journal, vol. 6, No. 1, 1993.
Neural Networks for Computing, Snowbird, Divko R. et al., Stochastic Spin Models for Pattern Recognition, Apr. 13-16, 1986, No. 1986, pp. 129-134, XP 000040996, see p. 132, para. 3 -p. 134, para. 2.
Pattern Recognition, Shiaw-Shian Yu et al, Relaxation by the Hopefield Neural Network, vol. 25, No. 2, 1 Feb. 1992, XP 000263525, pp. 197-209.
Chen, "Run Length Coding Based New Approach to Automatic Image Thresholding," Circuits and Systems, 1993 IEEE Int'l. Symposium, pp. 555-558.
Liu et al., "An Object Attribute Thresholding Algorithm for Document Image Binarization," Document Analysis, 1993 Int'l Conference, pp. 278-281.
L. O'Gorman, Experimental Comparisons of Binarization and Multi-Thresholding Methods on Document Images, IEEE/IAPR Conference on Pattern Recognition, Oct. 9-13, 1994.

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 and apparatus for separating foreground from background i 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 and apparatus for separating foreground from background i, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Method and apparatus for separating foreground from background i will most certainly appreciate the feedback.

Rate now

     

Profile ID: LFUS-PAI-O-1222119

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