Take a look at the new version of this page: [ beta version ]. Tell us what you think.

ABSTRACT

POSTER PAPER. Automatic indexing and searching in handwritten medical forms is a very important task. It is very challenging due to the poor image quality and the consequent low OCR performance. We describe a handwritten document retrieval system that improves the existing techniques in two respects. First, we present a Markov Random Fields based preprocessing algorithm that improves the image quality and OCR performance. Second, we improve the existing retrieval techniques by utilizing the OCR probabilities and language model into the term-weight scheme.

REFERENCES

• 1: H. Cao and V. Govindaraju. Handwritten carbon form preprocessing based on markov random field. Proceedings of the 2007 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'07), 2007.
• 2: H. Cao , V. Govindaraju, Vector Model Based Indexing and Retrieval of Handwritten Medical Forms, Proceedings of the Ninth International Conference on Document Analysis and Recognition (ICDAR 2007) Vol 1, p.88-92, September 23-26, 2007
• 3: 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]
• 4: R. Milewski and V. Govindaraju. Extraction of handwritten text from carbon copy medical form images. In Document Analysis Systems, pages 106--116, 2006.
• 5: C. J. Van Rijsbergen, Information Retrieval, Butterworth-Heinemann, Newton, MA, 1979

INDEX TERMS

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

Additional Classification:
  H. Information Systems
  H.3 INFORMATION STORAGE AND RETRIEVAL

General Terms:
Algorithms, Experimentation

Keywords:
Markov random fields, OCR, information retrieval