A survey of methods and strategies in character segmentation Export

@article{citeulike:1398883, abstract = {Character segmentation has long been a critical area of the OCR process. The higher recognition rates for isolated characters vs. those obtained for words and connected character strings well illustrate this fact. A good part of recent progress in reading unconstrained printed and written text may be ascribed to more insightful handling of segmentation. This paper provides a review of these advances. The aim is to provide an appreciation for the range of techniques that have been developed, rather than to simply list sources. Segmentation methods are listed under four main headings. What may be termed the \“classical\” approach consists of methods that partition the input image into subimages, which are then classified. The operation of attempting to decompose the image into classifiable units is called \“dissection.\” The second class of methods avoids dissection, and segments the image either explicitly, by classification of prespecified windows, or implicitly by classification of subsets of spatial features collected from the image as a whole. The third strategy is a hybrid of the first two, employing dissection together with recombination rules to define potential segments, but using classification to select from the range of admissible segmentation possibilities offered by these subimages. Finally, holistic approaches that avoid segmentation by recognizing entire character strings as units are described}, author = {Casey, R. G. and Lecolinet, E.}, booktitle = {Pattern Analysis and Machine Intelligence, IEEE Transactions on}, citeulike-article-id = {1398883}, citeulike-linkout-0 = {http://dx.doi.org/10.1109/34.506792}, citeulike-linkout-1 = {http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=506792}, doi = {10.1109/34.506792}, journal = {Pattern Analysis and Machine Intelligence, IEEE Transactions on}, keywords = {machine\_learning, ocr, survery}, number = {7}, pages = {690--706}, posted-at = {2007-06-19 17:15:22}, priority = {2}, title = {A survey of methods and strategies in character segmentation}, url = {http://dx.doi.org/10.1109/34.506792}, volume = {18}, year = {1996} }

TY - JOUR ID - citeulike:1398883 L3 - citeulike-article-id:1398883 N2 - Character segmentation has long been a critical area of the OCR process. The higher recognition rates for isolated characters vs. those obtained for words and connected character strings well illustrate this fact. A good part of recent progress in reading unconstrained printed and written text may be ascribed to more insightful handling of segmentation. This paper provides a review of these advances. The aim is to provide an appreciation for the range of techniques that have been developed, rather than to simply list sources. Segmentation methods are listed under four main headings. What may be termed the “classical” approach consists of methods that partition the input image into subimages, which are then classified. The operation of attempting to decompose the image into classifiable units is called “dissection.” The second class of methods avoids dissection, and segments the image either explicitly, by classification of prespecified windows, or implicitly by classification of subsets of spatial features collected from the image as a whole. The third strategy is a hybrid of the first two, employing dissection together with recombination rules to define potential segments, but using classification to select from the range of admissible segmentation possibilities offered by these subimages. Finally, holistic approaches that avoid segmentation by recognizing entire character strings as units are described IS - 7 JF - Pattern Analysis and Machine Intelligence, IEEE Transactions on EP - 706 TI - A survey of methods and strategies in character segmentation VL - 18 T2 - Pattern Analysis and Machine Intelligence, IEEE Transactions on SP - 690 KW - machine_learning KW - ocr KW - survery AU - Casey, RG AU - Lecolinet, E PY - 1996/// UR - http://dx.doi.org/10.1109/34.506792 ER -