Shortest path segmentation: a method for training a neural network to recognize character strings
- 2 January 2003
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 3, 165-172
- https://doi.org/10.1109/ijcnn.1992.227175
Abstract
The authors describe a method which combines dynamic programming and a neural network recognizer for segmenting and recognizing character strings. The method selects the optimal consistent combination of cuts from a set of candidate cuts generated using heuristics. The optimal segmentation is found by representing the image, the candidate segments, and their scores as a graph in which the shortest path corresponds to the optimal interpretation. The scores are given by neural net outputs for each segment. A significant advantage of the method is that the labor required to segment images manually is eliminated. The system was trained on approximately 7000 unsegmented handwritten zip codes provided by the United States Postal Service. The system has achieved a per-zip-code raw recognition rate of 81% on a 2368 handwritten zip-code test set.Keywords
This publication has 4 references indexed in Scilit:
- Handwritten zip code recognition with multilayer networksPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Reading handwritten digits: a ZIP code recognition systemComputer, 1992
- A tutorial on hidden Markov models and selected applications in speech recognitionProceedings of the IEEE, 1989
- The viterbi algorithmProceedings of the IEEE, 1973