Technique for generating bounding boxes for word spotting in bit

Details Technique for generating bounding boxes for word spotting in bit Technique for generating bounding boxes for word spotting in bit

1994-09-20

1998-10-20

Mansor, Joseph

Image analysis

Image segmentation

Segmenting individual characters or words

382171, G06K 934

Patent

active

058259198

ABSTRACT:
Font-independent spotting of user-defined keywords in a scanned image. Word identification is based on features of the entire word without the need for segmentation or OCR, and without the need to recognize non-keywords. Font-independent character models are created using hidden Markov models (HMMs) and arbitrary keyword models are built from the character HMM components. Word or text line bounding boxes are extracted from the image, a set of features based on the word shape, (and preferably also the word internal structure) within each bounding box is extracted, this set of features is applied to a network that includes one or more keyword HMMs, and a determination is made. The identification of word bounding boxes for potential keywords includes the steps of reducing the image (say by 2.times.) and subjecting the reduced image to vertical and horizontal morphological closing operations. The bounding boxes of connected components in the resulting image are then used to hypothesize word or text line bounding boxes, and the original bitmaps within the boxes are used to hypothesize words. In a particular embodiment, a range of structuring elements is used for the closing operations to accommodate the variation of inter- and intra-character spacing with font and font size.

REFERENCES:
patent: 4769849 (1988-09-01), Alsing
patent: 4847912 (1989-07-01), Tanaka et al.
patent: 5048109 (1991-09-01), Bloomberg et al.
patent: 5093868 (1992-03-01), Tanaka et al.
patent: 5121447 (1992-06-01), Tanioka et al.
patent: 5144682 (1992-09-01), Nakamura
patent: 5181255 (1993-01-01), Bloomberg
patent: 5216725 (1993-06-01), McCubbrey
Dan S. Bloomberg, "Multiresolution Morphological Approach to Document Image Analysis", Proceedings of the Int. Conf. on Document Analysis and Recognition, Saint-Malo, France, Sep. 1991, pp. 963-971.
Simon Kahan et al., "On the Recognition of Printed Characters of Any Font and Size", IEEE Transations on Pattern Analysis and Machine Intelligence, vol. PAMI-9, No. 2, Mar. 1987, pp. 274-288.
Chinmoy B. Bose et al., Connected and Degraded Text Recognition Using Hidden Markov Model, Proceedings of the Int. Conf. on Pattern Recognition, Netherlands, Sep. 1992, pp. 116-119.
Tin Kam Ho et al., "A Word Shape Analysis Approach to Recognition of Degraded Word Images", Proceedings of the USPS Advanced Technology Conference, Nov. 1990, pp. 217-231.
Yang He et al., "Handwritten Word Recognition Using HMM with Adaptive Length Viterbi Algorithm", Proceedings of the Int. Conf. on Acoustics, Speech and Signal Processing, San Francisco, California, Mar. 1992, vol. 3, pp. 153-156.
Douglas B. Paul et al., "Speaker Stress-Resistant Continuous Speech Recognition", Proceedings of the Int. Conf. on Acoustics, Speech and Signal Processing, 1988, pp. 283-286.
Lawrence R. Rabiner, A Tutorial on Hidden Markov Models and Selected Applications in Speech Recognition, Proceedings of the IEEE, vol. 77, No. 2, Feb. 1989, pp. 257-285.
Lawrence R. Rabiner et al., "An Introduction to Hidden Markov Models", IEEE ASSP Magazine, Jan. 1986, pp. 4-16.

Affiliated with

Also associated with

Rating

Technique for generating bounding boxes for word spotting in bit does not yet have a rating. At this time, there are no reviews or comments for this patent.

If you have personal experience with Technique for generating bounding boxes for word spotting in bit, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Technique for generating bounding boxes for word spotting in bit will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFUS-PAI-O-254329