Line removal and handwritten word recognition of police accident report forms

ABSTRACT

In this paper, we present an approach for line removal and handwritten word recognition using the New York State MV- 104A Police Accident Report (PAR) form. Only limited space is available on the form for written inputs and hence many handwritten characters overlap or touch the form's preprinted lines and characters. The complex structure of the form and the touching characters make line removal and word recognition difficult. We addressed this problem using run-length coding scheme and baseline analysis. Preliminary word recognition tests show promising results for PAR form processing and filled-in data extraction and recognition.

REFERENCES

• 1: Gyeonghwan Kim , Venu Govindaraju, A Lexicon Driven Approach to Handwritten Word Recognition for Real-Time Applications, IEEE Transactions on Pattern Analysis and Machine Intelligence, v.19 n.4, p.366-379, April 1997 [doi>10.1109/34.588017]
• 2: Bin Yu , Anil K. Jain, A Generic System for Form Dropout, IEEE Transactions on Pattern Analysis and Machine Intelligence, v.18 n.11, p.1127-1134, November 1996 [doi>10.1109/34.544084]
• 3: C. Y. Suen, et al. Bank check processing system. Int'l J. of Imaging Systems and Technology, 7(4): 392--403, 1996.
• 4: K. R. Arvind , Jayant Kumar , A. G. Ramakrishnan, Line Removal and Restoration of Handwritten Strokes, Proceedings of the International Conference on Computational Intelligence and Multimedia Applications (ICCIMA 2007), p.208-214, December 13-15, 2007 [doi>10.1109/ICCIMA.2007.272]
• 5: N. Otsu. A threshold selection method from gray level histograms. IEEE Transactions on Systems, Man and Cybernetics, 9:62--66, Mar. 1979.

INDEX TERMS

Primary Classification:
  I. Computing Methodologies
  I.5 PATTERN RECOGNITION

Additional Classification:
  I. Computing Methodologies
  I.4 IMAGE PROCESSING AND COMPUTER VISION

General Terms:
Algorithms, Experimentation

Keywords:
OCR, degraded image, form processing, police accident report form