ocr技术应用（OCR technology applications）.docVIP

ocr技术应用（OCR technology applications） Application of OCR technology in the process of Archives Digitalization 07 Soochow University Xu Chengchen class file Tutor Zhang Zhaoyu [Abstract] Based on the process of Digital Archives in OCR technology are introduced, and then analyzes the advantages of OCR technology and unique applications in the digitization of archives in, finally discusses the various methods to improve the recognition rate of OCR, which has reference to digital archives staff. [Keywords] Digital Archives OCR In the era of information, archives digitization has become the most important part of archives work in the future, and the scanning of paper archives is in full swing. However, the electronic file scanning generated is actually exist in the form of image files, rather than the true sense of the text file, that is to say, the computer only know file appearance, did not know the words, users see the original files through the computer only, but not for reference and retrieval operations on them this is undoubtedly the work content, use of electronic archives in the future caused great inconvenience. Taking into account the needs of file users, if we want to get the real text form of electronic files, so that the work of digital archives more effective and more thorough, it will be applied to OCR technology. I. General Situation of OCR The so-called OCR (Optical Character Recognition), optical character recognition, generally speaking, is to let the computer read . Its principle is through the special OCR software, the image will contain text into an independent recognition unit by the word cut, and then use a variety of algorithm analysis on morphological characteristics of text of each image unit, by comparing the standard feature library data, determine the text encoding standard in the computer, and to save the output format in a text file. The working process of OCR is as follows: image input, image pre-processing, character extraction, comparis