A discriminative linear regression approach to adaptation of multi-prototype based classifiers and its applications for Chinese OCR

This paper presents a new discriminative linear regression approach to adaptation of a discriminatively trained prototype-based classifier for Chinese OCR. A so-called sample separation margin based minimum classification error criterion is used in both classifier training and adaptation, while an Rprop algorithm is used for optimizing the objective function. Formulations for both model-space and feature-space adaptation are presented. The effectiveness of the proposed approach is confirmed by a series of experiments for adaptation of font styles and low-quality text, respectively.

► We have proposed a new SSM-MCE linear regression approach to adaptation of an SSM-MCE trained prototype-based classifier. ► Rprop optimization for both SSM-MCE training and adaptation. ► Formulations for both model-space and feature-space adaptation are presented. ► Experiments show our approach achieves significant improvements over state-of-the-art.