This Article 
   
 Share 
   
 Bibliographic References 
   
 Add to: 
 
Digg
Furl
Spurl
Blink
Simpy
Google
Del.icio.us
Y!MyWeb
 
 Search 
   
Holistic Verification of Handwritten Phrases
December 1999 (vol. 21 no. 12)
pp. 1344-1356

Abstract—In this paper, we describe a system for rapid verification of unconstrained off-line handwritten phrases using perceptual holistic features of the handwritten phrase image. The system is used to verify handwritten street names automatically extracted from live U.S. mail against recognition results of analytical classifiers. Presented with a binary image of a street name and an ASCII street name, holistic features (reference lines, large gaps and local contour extrema) of the street name hypothesis are “predicted” from the expected features of the constituent characters using heuristic rules. A dynamic programming algorithm is used to match the predicted features with the extracted image features. Classes of holistic features are matched sequentially in increasing order of cost, allowing an ACCEPT/REJECT decision to be arrived at in a time-efficient manner. The system rejects errors with 98 percent accuracy at the 30 percent accept level, while consuming approximately 20/msec per image on the average on a 150 MHz SPARC 10.

[1] R.N. Haber, L.R. Haber, and K.R. Furlin, “Word Length and Word Shape as Sources of Information in Reading,” Reading Research Quarterly, vol. 18, pp. 165-189, 1983.
[2] S.J. Soltysiak, Visual Information in Word recognition: Word Shape or Letter Identities?, 1994.
[3] S. Madhvanath, E. Kleinberg, and V. Govindaraju, “Empirical Design of a Multi-Classifier Thresholding/Control Strategy for Recognition of Handwritten Street Names,” Int'l J. Pattern Recognition and Artificial Intelligence, vol. 11, no. 6, 1997.
[4] G. Kim and V. Govindaraju, “A Lexicon Driven Approach to Handwritten Word Recognition for Real Time Applications,“ IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 19, no. 4, pp. 366-379, Apr. 1997.
[5] J.T. Favata and S.N. Srihari, “Off-Line Recognition of Handwritten Cursive Words,” Proc. SPIE Symp. Electronic Imaging Science and Technology, San Jose, Calif., 1992.
[6] S. Madhvanath and V. Govindaraju, “Serial Classifier Combination for Handwritten Word Recognition,” Proc. Third Int'l Conf. Document Analysis and Recognition (ICDAR 95), Montreal, Canada, pp. 911-914, Aug. 1995.
[7] J. Moreau, “A New System for Automatic Reading of Postal Checks,” Proc. Int'l Workshop on Frontiers in Handwriting Recognition (IWFHR-2), Bonas, France, pp. 121-132, Sept. 1991.
[8] J.C. Salome, M. Leroux, and J. Badard, “Recognition of Cursive Script Words in a Small Lexicon,” Proc. First Int'l Conf. Document Analysis and Recognition (ICDAR 91), Saint-Malo, France, pp. 774-782, Sept./Oct. 1991.
[9] J. Camillerapp, G. Loreatte, G. Menier, H. Oulhadj, and J.C. Pettier, “Off-Line and On-Line Methods for Cursive Handwriting Recognition,” From Pixels to Features III: Frontiers in Handwriting Recognition, S. Impedovo and J.C. Simon, eds. pp. 273-288, North-Holland, 1992.
[10] J.-P. Dodel and R. Shinghal, “Symbolic/Neural Recognition of Cursive Amounts on Bank Cheques,” Proc. Third Int'l Conf. Document Analysis and Recognition (ICDAR), pp. 15-18, Aug. 1995.
[11] A.C. Downton, R.W.S. Tregidgo, C.G. Leedham, and Hendrawan, “Recognition of Handwritten British Postal Addresses,” From Pixels to Features III: Frontiers in Handwriting Recognition, S. Impedovo and J.C. Simon, eds., pp. 129-144, North-Holland, 1992.
[12] Hendrawan and A.C. Downton, “Verification of Handwritten British Postcodes Using Address Features,” Fundamentals of Handwriting Recognition, S. Impedovo, ed., pp. 313-317, Springer-Verlag, 1993.
[13] R. Plamondon and G. Lorette, “Automatic Signature Verification and Writer Identification—The State of the Art,” Pattern Recognition, vol. 22, pp. 107-131, 1989.
[14] S.S. Kuo and O. Agazzi, “Keyword Spotting in Poorly Printed Documents Using Pseudo 2-D Hidden Markov Models,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 16, no. 8, pp. 842-848, Aug. 1994.
[15] J. Bertille, M. Gilloux, and M. Leroux, “Recognition of Handwritten Words in a Limited Dynamic Vocabulary,” Proc. Third Int'l Workshop Frontiers in Handwriting Recognition (IWFHR III), Buffalo, N.Y., pp. 417-422, 1993.
[16] S. Madhvanath, “The Holistic Paradigm in Handwritten Word Recognition and its Application to Large and Dynamic Lexicon Scenarios,” PhD thesis, State Univ. of New York at Buffalo, 1997.
[17] S. Madhvanath, G. Kim, and V. Govindaraju, “Chaincode Processing for Handwritten Word Recognition,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 21, no. 9, Sept. 1999.
[18] S. Madhvanath and V. Govindaraju, “Holistic Lexicon Reduction,” Proc. Third Int'l Workshop Frontiers in Handwriting Recognition, Buffalo, N.Y., pp. 71-81, May 1993.
[19] S. Madhvanath and V. Govindaraju, “Contour-Based Image Processing for Holistic Handwritten Word Recognition,” Proc. Fourth Int'l Conf. Document Analysis and Recognition (ICDAR 97), Ulm, Germany, Aug. 1997.
[20] G. Kim and V. Govindaraju, “Handwritten Phrase Recognition as Applied to Street Name Images,” J. Pattern Recognition, vol. 31, no. 1, pp. 41-51, 1998.

Index Terms:
Word verification, holistic approaches, word shape matching, handwritten word recognition, address interpretation.
Citation:
Sriganesh Madhvanath, Evelyn Kleinberg, Venu Govindaraju, "Holistic Verification of Handwritten Phrases," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 21, no. 12, pp. 1344-1356, Dec. 1999, doi:10.1109/34.817412
Usage of this product signifies your acceptance of the Terms of Use.