Optical Chinese character recognition for low-quality document images

In this article, we propose a new matching method for machine recognition of Chinese characters that are extracted from low-quality document images. This method employs a deformation representation, called character deformation model, to guide the detailed matching between templates and unknown characters. Experimental results show that the proposed method is very effective to recognize deformed characters extracted from low-resolution images or Xerox-copy documents. A recognition rate of 95.7% is achieved for 200 dpi document images, and the accumulated recognition rate of the first 3 candidates is higher than 99.8%. Moreover, even for the 100 dpi document images, the third accumulated recognition rate is still above 91%.