Dynamic planar warping for optical character recognition
- 1 January 1992
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 3, 149-152 vol.3
- https://doi.org/10.1109/icassp.1992.226254
Abstract
The authors extend the dynamic time warping (DTW) algorithm, widely used in automatic speech recognition (ASR), to a dynamic plane warping (DPW) algorithm, for application in the field of optical character recognition (OCR) or similar applications. Although direct application of the optimality principle reduced the computational complexity somewhat, the DPW (or image alignment) problem is exponential in the dimensions of the image. It is shown that by applying constraints to the image alignment problem, e.g., limiting the class of possible distortions, one can reduce the computational complexity dramatically, and find the optimal solution to the constrained problem in linear time. A statistical model, the planar hidden Markov model (PHMM), describing statistical properties of images is proposed. The PHMM approach was evaluated using a set of isolated handwritten digits. An overall digit recognition accuracy of 95% was achieved. It is expected that the advantage of this approach will be even more significant for harder tasks, such cursive-writing recognition and spotting.Keywords
This publication has 5 references indexed in Scilit:
- A tutorial on hidden Markov models and selected applications in speech recognitionProceedings of the IEEE, 1989
- Modeling and Segmentation of Noisy and Textured Images Using Gibbs Random FieldsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1987
- Classification of textures using Gaussian Markov random fieldsIEEE Transactions on Acoustics, Speech, and Signal Processing, 1985
- Isolated and Connected Word Recognition--Theory and Selected ApplicationsIEEE Transactions on Communications, 1981
- Continuous speech recognition by statistical methodsProceedings of the IEEE, 1976