Typographical Features for Scene Text Recognition

Scene text images feature an abundance of font style variety but a dearth of data in any given query. Recognition methods must be robust to this variety or adapt to the query data's characteristics. To achieve this, we augment a semi-Markov model---integrating character segmentation and recognition---with a bigram model of character widths. Softly promoting segmentations that exhibit font metrics consistent with those learned from examples, we use the limited information available while avoiding error-prone direct estimates and hard constraints. Incorporating character width bigrams in this fashion improves recognition on low-resolution images of signs containing text in many fonts.

[1]  William T. Freeman,et al.  Presented at: 2nd Annual IEEE International Conference on Image , 1995 .

[2]  Tin Kam Ho,et al.  Enhancing degraded document images via bitmap clustering and averaging , 1997, Proceedings of the Fourth International Conference on Document Analysis and Recognition.

[3]  William W. Cohen,et al.  Semi-Markov Conditional Random Fields for Information Extraction , 2004, NIPS.

[4]  Theodosios Pavlidis,et al.  Font recognition and contextual processing for more accurate text recognition , 1997, Proceedings of the Fourth International Conference on Document Analysis and Recognition.

[5]  Rolf Ingold,et al.  Optical Font Recognition Using Typographical Features , 1998, IEEE Trans. Pattern Anal. Mach. Intell..

[6]  Thomas M. Breuel.  Character recognition by adaptive statistical similarity , 2003, Seventh International Conference on Document Analysis and Recognition, 2003. Proceedings..

[7]  Wayne Niblack,et al.  An introduction to digital image processing , 1986 .

[8]  Andrew McCallum,et al.  Piecewise Training for Undirected Models , 2005, UAI.

[9]  Robert Cooperman.  Producing good font attribute determination using error-prone information , 1997, Electronic Imaging.

[10]  Allen R. Hanson,et al.  A discriminative semi-Markov model for robust scene text recognition , 2008, 2008 19th International Conference on Pattern Recognition.

[11]  Jonathan J. Hull,et al.  Improving ocr performance with word image equivalence , 1995 .

[12]  Alan L. Yuille,et al.  Detecting and reading text in natural scenes , 2004, Proceedings of the 2004 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2004. CVPR 2004..

[13]  Jonathan J. Hull,et al.  Font and Function Word Identification in Document Recognition , 1996, Comput. Vis. Image Underst..

[14]  Erik G. Learned-Miller,et al.  Improving Recognition of Novel Input with Similarity , 2006, 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'06).