Mao.abs

Jianchang Mao
IBM Almaden Research Center

HMM Recognition of Personal Checks

In this talk(*), I will discuss the effectiveness of a boosting algorithm in improving the performance of OCR (optical character recognition). We introduce three character degradation models in a boosting algorithm for training an ensemble of character classifiers. These models include an affine transformation, a deformable model, and a noise model. We also compare the boosting ensemble with the standard ensemble of networks trained independently with character degradation models. An interesting discovery in our comparison is that although the boosting ensemble is slightly more accurate than the standard ensemble at zero reject rate, the advantage of the boosting training over independent training quickly disappears as more patterns are rejected. Eventually the standard ensemble outperforms the boosting ensemble at high reject rates. Explanation of such a phenomenon will be discussed.

* Joint work with Dr. K. M. Mohiuddin

Back to Bay Area OCR home page