When confronted with degraded images of text, however, the performance of many commercial OCR systems deteriorates severely. This occurs because all these systems rely on a segmentation step that is prone to error in the presence of image noise and printing artifacts. The authors present a novel OCR approach that overcomes this problem by eliminating the segmentation step altogether. This approach is based on the concept and techniques of occluded object recognition. To achieve high efficiency as well as robustness, they incorporate the notions of indexing and voting, and tailor them to the problem of OCR. Preliminary experimental results are given.<>
{"title":"A segmentation-free approach to OCR","authors":"Chien-Huei Chen, J. DeCurtins","doi":"10.1109/ACV.1992.240312","DOIUrl":"https://doi.org/10.1109/ACV.1992.240312","url":null,"abstract":"When confronted with degraded images of text, however, the performance of many commercial OCR systems deteriorates severely. This occurs because all these systems rely on a segmentation step that is prone to error in the presence of image noise and printing artifacts. The authors present a novel OCR approach that overcomes this problem by eliminating the segmentation step altogether. This approach is based on the concept and techniques of occluded object recognition. To achieve high efficiency as well as robustness, they incorporate the notions of indexing and voting, and tailor them to the problem of OCR. Preliminary experimental results are given.<<ETX>>","PeriodicalId":153393,"journal":{"name":"[1992] Proceedings IEEE Workshop on Applications of Computer Vision","volume":"39 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1992-11-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134327656","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Z. Bien, Dongil Han, Jongcheol Park, Jong-Woon Lee, Changsuk Oh
In manufacturing CPT (Color Picture Tubes) used in TV sets and monitors, an ITC (Integrated Tube Components) adjustment process is involved. Automating the ITC adjustment process needs fast and robust visual sensing/measurement. Real time color purity and convergence measurement algorithms are described. Existing color purity measurement algorithms for ITC adjustment system often take too much time to detect color purity. Moreover, for convergence measurement, measurable data is not sufficient for accurate detection. To overcome these difficulties, real time vision system with 9 area cameras and many linear array cameras is developed. Area cameras are used for color purity measurements and linear array cameras are used for convergence measurements. To devise the purity measurement algorithm, the characteristics of CPT microscopic images are analyzed. To measure the exact color purity, several methods are selectively applied for calculating color purity depending on the conditions of CPT screen. For convergence measurement, special test CPT with no shadow mask and no black matrix is manufactured and a new measurement algorithm is developed using fuzzy inference and a priori knowledge taken from the specially manufactured CPT. The proposed algorithms are successfully applied as described in the experimental results.<>
{"title":"Real time color purity and convergence measurement algorithms for automatic ITC adjustment system","authors":"Z. Bien, Dongil Han, Jongcheol Park, Jong-Woon Lee, Changsuk Oh","doi":"10.1109/ACV.1992.240302","DOIUrl":"https://doi.org/10.1109/ACV.1992.240302","url":null,"abstract":"In manufacturing CPT (Color Picture Tubes) used in TV sets and monitors, an ITC (Integrated Tube Components) adjustment process is involved. Automating the ITC adjustment process needs fast and robust visual sensing/measurement. Real time color purity and convergence measurement algorithms are described. Existing color purity measurement algorithms for ITC adjustment system often take too much time to detect color purity. Moreover, for convergence measurement, measurable data is not sufficient for accurate detection. To overcome these difficulties, real time vision system with 9 area cameras and many linear array cameras is developed. Area cameras are used for color purity measurements and linear array cameras are used for convergence measurements. To devise the purity measurement algorithm, the characteristics of CPT microscopic images are analyzed. To measure the exact color purity, several methods are selectively applied for calculating color purity depending on the conditions of CPT screen. For convergence measurement, special test CPT with no shadow mask and no black matrix is manufactured and a new measurement algorithm is developed using fuzzy inference and a priori knowledge taken from the specially manufactured CPT. The proposed algorithms are successfully applied as described in the experimental results.<<ETX>>","PeriodicalId":153393,"journal":{"name":"[1992] Proceedings IEEE Workshop on Applications of Computer Vision","volume":"20 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1992-11-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121362491","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
L. B. Wolff, T. A. Mancini, P. Pouliquen, A. Andreou
Presents a fully automated system which unites CCD camera technology with liquid crystal technology to create a polarization camera capable of sensing the polarization of reflected light from objects at pixel resolution. As polarization affords a more general physical description of light than does intensity, it can therefore provide a richer set of descriptive physical constraints for the understanding of images. The authors present a scheme for mapping polarization states into hue, saturation and intensity which is a very convenient representation for a polarization image. The polarization camera outputs such a color image which can then be used in polarization-based vision methods. The unique vision understanding capabilities of the polarization camera system are demonstrated with experimental results showing polarization-based dielectric/metal material classification, specular reflection and occluding contour segmentations in a fairly complex scene, and surface orientation constraints for object recognition.<>
{"title":"Liquid crystal polarization camera","authors":"L. B. Wolff, T. A. Mancini, P. Pouliquen, A. Andreou","doi":"10.1117/12.132068","DOIUrl":"https://doi.org/10.1117/12.132068","url":null,"abstract":"Presents a fully automated system which unites CCD camera technology with liquid crystal technology to create a polarization camera capable of sensing the polarization of reflected light from objects at pixel resolution. As polarization affords a more general physical description of light than does intensity, it can therefore provide a richer set of descriptive physical constraints for the understanding of images. The authors present a scheme for mapping polarization states into hue, saturation and intensity which is a very convenient representation for a polarization image. The polarization camera outputs such a color image which can then be used in polarization-based vision methods. The unique vision understanding capabilities of the polarization camera system are demonstrated with experimental results showing polarization-based dielectric/metal material classification, specular reflection and occluding contour segmentations in a fairly complex scene, and surface orientation constraints for object recognition.<<ETX>>","PeriodicalId":153393,"journal":{"name":"[1992] Proceedings IEEE Workshop on Applications of Computer Vision","volume":"42 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1992-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122957948","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：