@conference {13628, title = {Re-Targetable OCR with Intelligent Character Segmentation}, booktitle = {DAS {\textquoteright}08: Proceedings of the 2008 The Eighth IAPRInternational Workshop on Document Analysis Systems}, year = {2008}, month = {2008/09//}, pages = {183 - 190}, abstract = {We have developed a font-model based intelligent character segmentation and recognition system. Using characteristics of structurally similar TrueType fonts, our system automatically builds a model to be used for the segmentation and recognition of the new script, independent of glyph composition. The key is a reliance on known font attributes. In our system three feature extraction methods are used to demonstrate the importance of appropriate features for classification. The methods are tested on both Latin (English) and non-Latin (Khmer) scripts. Results show that the character-level recognition accuracy exceeds 92\% for Khmer and 96\% for English on degraded documents. This work is a step toward the recognition of scripts of low-density languages which typically do not warrant the development of commercial OCR, yet often have complete TrueType font descriptions.}, author = {Agrawal,Mudit and David Doermann} }