Research on Segmentation and Recognition of Printed Chinese Characters
Xi Wang, Hong Du, Xiping Wen · Journal of Physics Conference Series · 2019
Abstract The printed character recognition (PCR) is an efficient and automatic information entry method, which will become the important function interface of the computer in the future. A good character segmentation method can greatly improve the speed and accuracy of character recognition. This paper proposes a Chinese character segmentation algorithm based on OpenCV open source library and parallel processing, which can segment Chinese characters efficiently and accurately. And then, using the Tesseract-OCR character recognition engine to identify Chinese characters, the experimental results show that the average recognition time of a single Chinese character is 0.07s, and the recognition rate of Chinese characters is 96.2%, which proves the feasibility of the method.