Research on Chinese characters recognition in complex background images
Liu Shu-feng, Shen Shaohong, Sun Zhiyuan · 2017
In this paper, an automatic recognition method of Chinese characters in static complex background is proposed and studied. Firstly, an feature extraction model combing Gabor filter and Sobel operator to is designed to get Chinese characters area. Secondly, K-means clustering algorithm is used to distinguish between the character area and the background area. Then, according to structure characteristics of Chinese character, two effective parameters defined as stroke across and the energy density are designed to recognize Chinese characters. Specific method is comparative analysis of the characters to be identified and the standard font. Finally, a set of experimental data is selected to carry out experiment and the experimental results approve that the proposed Chinese characters recognition method targeted at Text region in complex background has a good adaptability and robustness.