关键词: 复杂图像背景 文字分割 形态运算 区域生长

Abstract:

According to the morphic characteristics of the Chinese characters and background areas in a complex background image, we propose a fast text segmentation algorithm based on morph operation, and compare it with the LLT algorithm. The experimental results show that our algorithm can locate the text in a complex image in a very fast and precise way. In comparison with LLT, our algorithm has a higher processing speed and better segmentation result.

Key words: （complex background, text segmentation, morph operation, region growth）