OCR技术应用(国外英语资料).docVIP

OCR技术应用(国外英语资料) Application of OCR technology in archives digitization process The university of suzhou 2007 file class is made Instruct teacher zhang zhao yu 【 abstract 】 this paper for the OCR technique were simply introduced in the process of digital archives, and analyzes on the advantages of the OCR technology and unique application in archives digitization work, finally discusses the methods of OCR recognition rate for archives digitization reference staff. [keywords] the digitized OCR In the information age, the digitisation of archives has become a top priority for archival work in the future, and paper records are being scanned everywhere. , however, produced by scanning electronic files, in fact, there is only in the form of image files, rather than a real sense of text files, that is to say, the computer file appearance know, but dont know the inner text, the user through a computer can only see the files to their original state, but not for the contents for reference and retrieval operation, no doubt about the future of electronic archives utilization work caused great inconvenience. Considering the file the use of user demand, if you want to get real text form of electronic file, make the digital file to work more effectively and more completely, then to apply to the OCR. One, OCR profiles The so-called Optical Character Recognition, or Optical Character Recognition, is simply a way of making the computer read. Its principle is through special OCR software, image containing a text is cut up into independent recognition modules according to the word, and then use all kinds of algorithm analysis each image in the cell morphological characteristics of the word, by comparing data in a standard feature library, judge the standard encoding of the text in the computer, and in accordance with the general format output is saved in a text file. The process of OCR is: image input, pre-image processing, text feature extraction, comparison identification, artificia