An application of hierarchical knowledge integration in hand-written form processing
In this paper, we present a Hierarchical Interactive Reasoning approach for hand-written form processing, and describe an application of this approach to a prototype form processing system. A priori domain knowledge is closely bound to all levels of a hierarchical structure in which bi-directional inferencing is possible. This approach has significantly improved recognition performance in the prototype system. We also touch on possible future extensions to the approach.
Unable to display preview. Download preview PDF.
- 1.Otsu, N. (1995). RWC program, current situation and perspectives. In RWC News, 7–11. Real World Computing Partnership.Google Scholar
- 2.Srihari, S.N., Y.C. Shin, Ramanaprasad, V., and D.S. Lee (1995). Name and address block reader system for tax form processing. In Proc. of Intl. Conf. on Document Analysis and Recognition, Montreal, Canada, 5–10. IEEE Computer Society Press.Google Scholar
- 3.Tan, A.H. and L.N. Teow. (1995) Learning by supervised clustering and matching. In Proceedings, 1995 IEEE International Conference on Neural Networks, Perth, volume I, 242–246.Google Scholar
- 4.Teow L.N. and A.H. Tan. (1995) Adaptive integration of multiple experts. In Proceedings, 1995 IEEE International Conference on Neural Networks, Perth, volume III, 1215–1220. IEEE Publisher.Google Scholar