This Article 
   
 Share 
   
 Bibliographic References 
   
 Add to: 
 
Digg
Furl
Spurl
Blink
Simpy
Google
Del.icio.us
Y!MyWeb
 
 Search 
   
Optical Font Recognition Using Typographical Features
August 1998 (vol. 20 no. 8)
pp. 877-882

Abstract—A new statistical approach based on global typographical features is proposed to the widely neglected problem of font recognition. It aims at the identification of the typeface, weight, slope and size of the text from an image block without any knowledge of the content of that text. The recognition is based on a multivariate Bayesian classifier and operates on a given set of known fonts. The effectiveness of the adopted approach has been experimented on a set of 280 fonts. Font recognition accuracies of about 97 percent were reached on high-quality images. In addition, rates higher than 99.9 percent were obtained for weight and slope detection. Experiments have also shown the system robustness to document language and text content and its sensitivity to text length.

[1] S. Kahan, T. Pavlidis, and H. S. Baird, "On the Recognition of Printed Characters of Any Font and Size," Trans. Pattern Analysis and Machine Intelligence, vol. 9, no. 2, pp. 274-288, 1987.
[2] G. Nagy and S. Seth, "Modern Optical Character Recognition," The Froehlich/Kent Encyclopedia of Telecommunication, F. Froehlich and A. Kent, eds., vol. 11, pp. 473-531. Marcel Dekker, Inc., 1996.
[3] A. Zramdini, "Study of Optical Font Recognition Based on Global Typographical Features," Ph.D. dissertation, University of Fribourg, 1995.
[4] J.C. Anigbogu, Reconnaissance de Textes Imprimés Multifontesàl'aide de Modèles Stochastiques et Métriques, Ph.D. dissertation, Universitéde Nancy I, 1992.
[5] Y. Chenevoy, Reconnaissance Structurelle de Documents Imprimés:Études et Réalisations, Ph.D. dissertation, CRIN-University of Nancy, France, 1993.
[6] G.E. Kopec, “Least-Squares Font Metric Estimation from Images,” IEEE Trans. Image Processing, vol. 2, no. 4, pp. 510-519, 1993.
[7] B. Cooperman, "Producing Good Font Attribute Determination Using Error-Prone Information," SPIE, vol. 3,027, pp. 50-57, 1997.
[8] H. Shi and T. Pavlidis, “Font Recognition and Contextual Processing for More Accurate Text Recognition,” Proc. Fourth Int'l Conf. Document Analysis and Recognition, (ICDAR '97), pp. 39-44, Aug. 1997.
[9] R.A. Morris, "Classification of Digital Typefaces Using Spectral Signatures," Pattern Recognition, vol. 25, no. 8, pp. 869-876, 1992.
[10] S. Khoubyari and J. Hull, "Font and Function Word Identification in Document Recognition," Computer Vision and Image Understanding, vol. 63, no. 1, pp. 66-74, 1996.
[11] R. Rubinstein, Digital Typography: An Introduction to Type and Composition for Computer System Design. Addison-Wesley, 1988.
[12] B. Bauermeister, Manual of Comparative Typography: The PANOSE System.New York: VNR Company, 1991.
[13] P.G. De Luca and A. Gisotti, "Printed Character Preclassification Based on Word Structure," Pattern Recognition, vol. 24, no. 7, pp. 609-615, 1991.
[14] S. Chen, F.Y. Shih, and P.A. Ng, "Fussy Typographical Analysis for Character Preclassification," TSMC, vol. 25, no. 10, pp. 1,408-1,413, Oct. 1995.
[15] F. Bapst and R. Ingold, "Using Typography in Document Image Analysis," RIDT'98: Fourth Int'l Conf. Raster Imaging and Digital Typography,San Malo, France, Apr. 1998.

Index Terms:
Optical font recognition, typographical features, font models, multivariate Bayesian classifier, document analysis, OCR.
Citation:
Abdelwahab Zramdini, Rolf Ingold, "Optical Font Recognition Using Typographical Features," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 20, no. 8, pp. 877-882, Aug. 1998, doi:10.1109/34.709616
Usage of this product signifies your acceptance of the Terms of Use.