An OCR Post-processing Approach Based on Multi-knowledge

This paper proposes an OCR post-processing approach based on multi-knowledge, which integrates language knowledge and candidate distance information given by the OCR engine. In this approach, statistical language model and semantic lexicon are combined, and candidate distance information is used to reduce the size of the search space. The experimental results show that this approach is very effective. After postprocessing, the recognition accuracy rate on the test set increases from 58.45% to 83.73%, which means 60.84% error reduction.

• Type: Conference
• Year: 2005
• Where: KES
• Authors: Li Zhuang, Xiaoyan Zhu
• Keywords: Candidate Distance Information, KES 2005, OCR Post-processing Approach, Statistical Language Model