Features generation and spotting methods and systems using same

Details Features generation and spotting methods and systems using same Features generation and spotting methods and systems using same

2007-08-30

2011-10-25

Desire, Gregory M (Department: 2624)

Image analysis

Image segmentation

C382S321000

Reexamination Certificate

active

08045798

ABSTRACT:
An image partitioner is configured to find a partition point that divides a received image into four sub-images each having a pre-selected activated pixel count. A recursion processor is configured to (i) apply the image partitioner to an input image to generate a first partition point and four sub-images and to (ii) recursively apply the image partitioner to at least one of the four sub-images for at least one recursion iteration to generate at least one additional partition point. A formatter is configured to generate a features representation of the input image in a selected format. The features representation is based at least in part on the partition points. The features representation can be used in various ways, such as by a classifier configured to classify the input image based on the features representation.

REFERENCES:
patent: 5438630 (1995-08-01), Chen et al.
patent: 5745600 (1998-04-01), Chen et al.
patent: 5825919 (1998-10-01), Bloomberg et al.
patent: 5841902 (1998-11-01), Tu
patent: 6038340 (2000-03-01), Ancin et al.
patent: 6108444 (2000-08-01), Syeda-Mahmood
patent: 6356655 (2002-03-01), Sumikawa et al.
patent: 6424728 (2002-07-01), Ammar
patent: 6917708 (2005-07-01), Goodman et al.
patent: 6985859 (2006-01-01), Morin
patent: 7020338 (2006-03-01), Cumbee
patent: 7099507 (2006-08-01), Ouchi
patent: 7139438 (2006-11-01), Shimazawa
patent: 2007/0183655 (2007-08-01), Konig et al.
Majhi et al, “Novel Features for Off-line Signature Verification”, International Journal of Computers, Communications & Control, vol. I (2006), No. 1, pp. 17-24.
Quadtree, from Wikipedia, pp. 2, at http://en.wikipedia.org/wiki/Quadtree, last visited Jul. 3, 2007.
Rath et al., “Word Image Matching Using Dynamic Time Warping,” Proc. of the Conf. on Computer Vision and Pattern Recognition (CVPR), Madison, WI, vol. 2 pp. 1-7, 2003.
Kane et al., “Indexing George Washington's Handwritten Manuscripts,” Technical Report, University of Massachusetts Amherst, pp. 1-20, 2001.
Shen et al., “Off-line Signature Verification Using Geometric Features Specific to Chinese Handwriting,” 24thInt. Conf. Information Technology Interfaces ITI, Cavtat, Croatia, pp. 229-235, 2002.
Srihari et al., “Spotting Words in Latin, Devanagari and Arabic Scripts,” Indian Journal of Artificial Intelligence, pp. 1-8, 2006.
Rath et al., “Features for Word spotting in Historical Manuscripts,” ISSN 0-7695-1960-1, pp. 1-5, 2003.
Vinciarelli et al., “Offline Recognition of Unconstrained Handwritten texts . . . ,” IEEE Transactions on Pattern Analysis and Machine Intelligence, 16(6), pp. 709-720, 2004.
Marti et al., “Using a Statistical Language Model to Improve . . . ,” ISSN 981-02-4564-5, pp. 1-27, 2002.
U.S. Appl. No. 11/847,757, filed Aug. 2007, Serrano.
Marti et al., “Text Line Segmentation and Word Recognition . . . ,” IEEE, pp. 159-163, 2001.
Ataer et al., “Retrieval of Ottoman Documents,” ACM, pp. 155-162, 2006.
Manmatha et al., “Word Spotting: Indexing Handwritten Archives,” AAAI/MIT Press, 1997.
Plamondon et al., “On-Line and Off-Line Handwriting Recognition: A Comprehensive Survey,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 22, No. 1, pp. 63-84, 2000.
Viola et al., “Robust Real-Time Face Detection,” Intl. Journal of Computer Vision 57(2), pp. 137-154, 2004.
Vinciarelli, “A Survey on Off-Line Cursive word Recognition,” IDIAP-RR 00-43, 2002.
Majhi et al., “Novel Features for Off-line Signature Verification,” CCC Publications, vol. I, pp. 17-24, 2006.
Trier et al., “Feature Extraction Methods for Character Recognition—A Survey,” Pattern Recognition 29, pp. 641-662, 1996.

Affiliated with

Also associated with

Rating

Features generation and spotting methods and systems using same does not yet have a rating. At this time, there are no reviews or comments for this patent.

If you have personal experience with Features generation and spotting methods and systems using same, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Features generation and spotting methods and systems using same will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFUS-PAI-O-4299761