We present an algorithm for a priori Arabic optical Font Recognition (AFR). First, words in the training set of documents for each font are segmented into symbols that are rescaled. Next, templates are constructed, where every new training symbol that is not similar to existing templates is a new template. Templates are sharable between fonts. To classify the font of a word, its symbols are matched to the templates and the fonts of the best matching templates are retained. The most frequent font is the word font.

[1] Abuhaiba I., “Skew Correction of Textual Documents,” accepted in King Saud University Journal, Computer and Information Sciences Division.

[2] Abuhaiba I., “Discrete Script or Cursive Language Identification from Document Images,” accepted in Journal of King Saud University, Engineering Sciences Division.

[3] Manna S. L., Colla A. M., and Sperduti A., “Optical Font Recognition for Multi-Font OCR and Document Processing,” 10th International Workshop on Database & Expert Systems Applications, Florence, Italy, pp. 549-553, 1999.

[4] Shi H. and Pavlidis T., “Font Recognition and Contextual Processing for More Accurate Text Recognition,” 4th International Conference on Document Analysis and Recognition: (ICDAR’97), Germany, pp. 39-44, 1997.

[5] Zhu Y., Tan T., and Wang Y., “Font Recognition Based on Global Texture Analysis,” Fifth International Conference on Document Analysis and Recognition: (ICDAR’99), Bangalore, India, pp. 349-352, 1999.

[6] Zramdini A. and Ingold R., “A Study of Document Image Degradation Effects on Font Recognition,” (ICDAR’95), Montreal, Canada, pp. 740-743, 1995.

[7] Zramdini A. and Ingold R., “Optical Font Recognition Using Typographical Features,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 20, no. 8, pp. 877-882, 1998. Ibrahim Abuhaiba is an assistant professor at the Department of Electrical and Computer Engineering, Islamic University of Gaza, Palestine. He obtained his Master of Philosophy and Doctorate of Philosophy from Britain in the field of document understanding and pattern recognition. His research interests include computer vision, image processing, document analysis and understanding, pattern recognition, artificial intelligence, and many other fields. Dr. Abuhaiba presented important theorems and more than twenty- five algorithms in text recognition. He published many original contributions in the field of document understanding in well-reputed international journals and conferences.