{"title":"Text data extraction from microfilm images of punched cards","authors":"Sudha U. Kumar, R. Kasturi","doi":"10.1109/ICPR.1992.201761","DOIUrl":null,"url":null,"abstract":"A system for reading text data from microfilm images of punched cards is described. The input is a high resolution gray level image obtained by scanning the card image from the microfilm. Noise due to the poor quality of microfilm data and similarity in gray levels of noise patches and punches are the major problems for text extraction. Thresholding, skew correction and morphological operations are performed on the input gray level image. Card parameters such as positions of punches, etc., are calculated and used along with the knowledge about the contents of the card to separate punched holes from other artifacts. Text data are recognized by locating the punched holes and errors are corrected by a context-based approach. The algorithm has been implemented in software and tested on several images.<<ETX>>","PeriodicalId":34917,"journal":{"name":"模式识别与人工智能","volume":"6 1","pages":"230-233"},"PeriodicalIF":0.0000,"publicationDate":"1992-08-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"5","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"模式识别与人工智能","FirstCategoryId":"1093","ListUrlMain":"https://doi.org/10.1109/ICPR.1992.201761","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q4","JCRName":"Computer Science","Score":null,"Total":0}
引用次数: 5
Abstract
A system for reading text data from microfilm images of punched cards is described. The input is a high resolution gray level image obtained by scanning the card image from the microfilm. Noise due to the poor quality of microfilm data and similarity in gray levels of noise patches and punches are the major problems for text extraction. Thresholding, skew correction and morphological operations are performed on the input gray level image. Card parameters such as positions of punches, etc., are calculated and used along with the knowledge about the contents of the card to separate punched holes from other artifacts. Text data are recognized by locating the punched holes and errors are corrected by a context-based approach. The algorithm has been implemented in software and tested on several images.<>
京公网安备 11010802042870号
京ICP备2023020795号-1
分享
求助内容：
应助结果提醒方式：
扫码关注我们
