基于计算机视觉的手写字符输入

Handwritten character input based on computer vision

提出了一种非接触式的手写字符输入方法。利用摄像机捕捉发光笔在一固定的单色背景平面上"书写"的运动轨迹,根据发光笔光斑坐标的位置恢复出"书写"字符的图像,最后识别输出。实验结果表明,该方法简单实用,对大写英文字母和数字的识别率均达到98%以上。

A method of non-contact handwritten character input was proposed. A camera was used to capture the moving track of light spot that were projected by a laser pointer on a fixed plane with simple background. The image with a character can be recovered by determine the coordinate of light spot on every frame. The results show that the method is simple and practical and the recognition rate on the capital letters and numbers is more than 98%.