二值文本信息翻译过程中光学字符识别方法研究

Research on optical character recognition method in the translation of binary text information

日常信息化办公过程中,常用到OCE技术识别文本图像中有效信息,为此,能否短时间内准确识别文本图像里的光学字符信息对人们办公效率存在直接影响。提出一种基于OCR技术的二值文本光学字符信息翻译识别方法,使用基于直方图分析和OTSU算法的文本图像二值化方法,将文本图像实施二值化,分割文本图像中光学字符信息的前景与背景;在分割后的前景中,使用基于OCR技术的二值文本光学字符信息翻译分类器,实现二值文本光学字符信息翻译识别。经验证,所提方法可实现高精度、高效率的二值文本光学字符信息翻译识别,和其他识别方法相比,该方法识别性能显著。

In the daily information office,the OCE technology is often used to recognise adequate information in text images. Therefore,whether the optical character information in text images can be accurately recognised in a short time has a direct impact on people’s office efficiency. A binary text optical character information translation and recognition method based on OCR technology are proposed. The text image binarisation method based on histogram analysis and OTSU algorithm is used to implement binarisation of the text image to segment the foreground and background of optical character information in the text image. In the foreground,after segmentation,the binary text optical character information translation classifier based on OCR technology is used to realise the translation recognition of binary text optical character information. It has been proved that the proposed method can realise the translation and recognition of binary text optical character information with high accuracy and high efficiency.