Neural Network Applications in Character Recognition and Document Analysis

Character Recognition has served as one of the principal proving grounds for neural-net methods and has emerged as one of the most successful applications of this technology. This chapter outlines optical character recognition document analysis systems developed at AT&T Bell Labs that combine the strengths of machine-learning algorithms with high-speed, fine-grained parallel hardware. From our point of view, the most significant aspect of this work has been the efficient integration of diverse methods into end-to-end systems. In this paper we use the task of locating and reading ZIP codes on US mail pieces as an illustration of the character recognition / document analysis process. We will also describe other applications of the technology, including interpretation of faxed forms and bit-mapped text to ASCII conversion.

[1]  Lawrence D. Jackel,et al.  Handwritten Digit Recognition with a Back-Propagation Network , 1989, NIPS.

[2]  Henry S. Baird,et al.  Global-to-Local Layout Analysis , 1990 .

[3]  Gale Martin,et al.  Recognizing Overlapping Hand-Printed Characters by Centered-Object Integrated Segmentation and Recognition , 1991, NIPS.

[4]  Yann LeCun,et al.  Multi-Digit Recognition Using a Space Displacement Neural Network , 1991, NIPS.

[5]  Lawrence D. Jackel,et al.  A Neurocomputer Board Based on the ANNA Neural Network Chip , 1991, NIPS.

[6]  James D. Keeler,et al.  A Self-Organizing Integrated Segmentation and Recognition Neural Net , 1991, NIPS.

[7]  Jan Ben,et al.  Image recognition with an analog neural net chip , 1992, Proceedings., 11th IAPR International Conference on Pattern Recognition. Vol. IV. Conference D: Architectures for Vision and Pattern Recognition,.

[8]  Y. Le Cun,et al.  Shortest path segmentation: a method for training a neural network to recognize character strings , 1992, [Proceedings 1992] IJCNN International Joint Conference on Neural Networks.

[9]  David Chapman,et al.  Learning to See Where and What: Training a Net to Make Saccades and Recognize Handwritten Characters , 1992, NIPS.

[10]  David E. Rumelhart,et al.  Self-organizing integrated segmentation and recognition neural network , 1992, Defense, Security, and Sensing.

[11]  Yann LeCun,et al.  Efficient Pattern Recognition Using a New Transformation Distance , 1992, NIPS.

[12]  Henry S. Baird,et al.  Language-free layout analysis , 1993, Proceedings of 2nd International Conference on Document Analysis and Recognition (ICDAR '93).

[13]  Howard P. Katseff,et al.  The Ferret Document Browser , 1993, USENIX Summer.

[14]  Henry S. Baird,et al.  Document image defect models , 1995 .