基于OpenCV的数码管字符识别

Character Recognition of Digital Tube Based on OpenCV

为实现摄像机采集的电梯主板数码管字符图像的识别,研究一种针对数码管字符图像自动识别的方法。数码管图像经过预处理,包括图像灰度化、图像降噪、图像二值化等,并对图像进行字符定位和分割,最后采用穿线识别法对字符进行识别,可有效提高电梯故障识别率。实验结果表明,穿线识别法对数码管字符识别正确率高、效率高、实时性好。

In order to realize the recognition of digital tube character image of elevator mainboard collected by camera, a method for automatic recognition of digital tube character image was studied. The digital tube image was preprocessed, including image graying, image noise reduction, image binarization, etc., and the character positioning and segmentation of the image were carried out. Finally, the character recognition method was used to identify the characters, which could effectively improve the recognition rate of elevator fault. The experimental results show that the threading recognition method has high accuracy, high efficiency and good real-time performance.