Extraction of filled-in data from colour forms
The paper describes an intelligent system for extraction filled-in data from colour conventional forms. Filled-in characters in these forms can touch or cross the form frames. The empty form description is acquired in this system by interactive learning followed by automatic processing and extraction filled-in data from input forms. Some steps of input form processing (form coding and form dropout) are carried out for any input form and other (form registration and broken characters reconstruction) are needed if the colour of the user filled-in data coincides with the colour of the empty form only. Experimental results showing the performance of the system are described.
KeywordsLine Segment Form Registration Input Form Form Frame Form Template
Unable to display preview. Download preview PDF.
- Leedham and D. Monger, “Evaluation of an Interactive Tool for Handwritten Form Description”, Proc. Third International Conf. Document Analysis and Recognition, pp. 1,185–1,188, Montreal, 1995.Google Scholar
- S.L. Taylor, R. Fritzson and J.A. Pastor, “Extraction of Data from Preprinted Forms”, Machine Vision and Applications, vol. 5, pp. 211–222, 1992.Google Scholar
- G. Maderlechner, “Symbolic Subtraction from Fixed Formatted Graphics and Text from Filled In Forms”, Machine Vision and Applications, vol. 3, pp.457–459, 1990.Google Scholar
- R. Casey and D.Ferguson, “Intelligent Forms Processing”, IBM Systems Journal 29(3), pp. 435–450, 1990.Google Scholar
- R. Casey, D. Ferguson, K. Mohiuddin and E. Walach, “Intelligent Forms Processing System”, Machine Vision and Applications, vol. 5, pp. 143–155, 1992.Google Scholar
- Bin Yu and Anil K. Jain, “A Generic System for Form Dropout”, IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 18,pp. 1127–1134Google Scholar
- K. Franke, “Unterschriftenverification mit SIC Natura”, Bildanswertung für Handel, Banken and Behörden, Berlin, 19./20.02.97, Fraunhofer IPK — Workshop.Google Scholar