摘要
为了实现水下视频图像文字提取与识别,文中提出了一种简捷有效的方法。主要解决了复杂背景下文字识别效果差,识别率低的问题。其实现过程是:首先根据形态学图像处理原理对视频图像进行预处理,增强对比度,滤除噪声;根据预处理结果对视频文字区域进行分割,并将分割出的字符进行归一化;最后进行模板匹配,进行文字识别并保存。实际应用表明,该系统具有操作简便、识别准确的特点,达到了设计要求。
In order to realize the text extraction and recognition of underwater image, a simple and effective method is proposed in this paper. This method mainly solves thepoor effectiveness of character recognition and low recognition ratio under complex background. The realization process is： First, pre-processing with the morphological image processing techniques is adopted to enhance the contrast and filter the noise. Then take character segmentation according to the result of pre-processing, Finally, normalize the segmented character to match the character template and save the results. The experiment and application show that this test system has good performance, and achieve the design requirement.
出处
《电子设计工程》
2015年第14期170-172,175,共4页
Electronic Design Engineering
关键词
水下视频
文本区域定位
字符分割
字符识别
underwater video
text region localization
character segmentation
character recognition
