基于Office OCR组件的文档图象检索研究

文档图像的检索主要用于对文档图像进行管理。文章对文档检索技术进行了研究，提出了使用微软office内嵌的光学字符识别（OCR）组件对文档图像进行识别，获得了一种快速对文档图像检索的方法；另外，对类似发票图样的文档图像提出了定位识别的方法。实验证明，这些方法对文档图像的检索是有效的。

Document Image Retrieval Based on Office OCR

Document image retrieval is mainly used to manage the document image. This paper tells of the document retrieval technology first, and then presents the method for recognizing the document image by using microsoft office Optical Character Recognize（OCR）, and thus a way for rapid document retrieval is obtained. Furthermore, for the image similar to invoice pattern, this paper also proposes a method for locating and recognizing the image. Experiment indicates that these are effective ways for document image retrieval.