A segmentation method for touching italic characters
Yun Li,Satoshi Naoi,Mohamed Cheriet,Ching Y. Suen +3 more
- Vol. 2, pp 594-597
TLDR
By improving the recognition rate on italic fonts, this work uses slant projection and contour analysis and the shortest path approach for accurately locating the cut path of each candidate segmentation point.Abstract:
Segmentation is an essential part of a recognition system. It is difficult to handle touching characters, especially for italic fonts. We present a method to achieve the accurate segmentation of touching italic characters. It is free of slant correction, so extra noises will not be introduced. We use slant projection and contour analysis to find the segmentation points. Then the shortest path approach is adopted for accurately locating the cut path of each candidate segmentation point. Based on dynamic programming, we can find the best segmentation result from those cut paths. By this method, we can improve the recognition rate on italic fonts.read more
Citations
More filters
Journal ArticleDOI
Non-uniform slant estimation and correction for Farsi/Arabic handwritten words
Majid Ziaratban,Karim Faez +1 more
TL;DR: It is concluded that successful results can be achieved by considering the special specifications of Farsi and Arabic manuscripts and the proposed overall and non-uniform deslanting methods.
Proceedings ArticleDOI
Italic or Roman: Word Style Recognition without A Priori Knowledge for Old Printed Documents
Loris Eynard,Hubert Emptoz +1 more
TL;DR: An Italic/Roman word type recognition system without a priori knowledge on the characters' font is presented and the results show a ratio of 100 %recognition for Italic words and 97.2 % for Roman words.
Contribution à la numérisation des documents imprimés du XVIIIème siècle
TL;DR: The Gazette de Leyde as discussed by the authors is a journal politique parmi les plus influent du XVIIIeme siecle and represente un corpus de plus de 140, 000 pages reparti sur plus d'un Siecle de parution.
Proceedings ArticleDOI
Italic detection and rectification
TL;DR: The rationale of the proposed method is that the difference of certain features derived from italic style characters after shear transformation will be canceled, whereas the difference will be more obvious for non-italic style (normal style) characters.
References
More filters
Journal ArticleDOI
A survey of methods and strategies in character segmentation
R.G. Casey,Eric Lecolinet +1 more
TL;DR: H holistic approaches that avoid segmentation by recognizing entire character strings as units are described, including methods that partition the input image into subimages, which are then classified.
Book
Handbook of Character Recognition and Document Image Analysis
Horst Bunke,Patrick S. P. Wang +1 more
TL;DR: Arabic character recognition, A. Amin automatic reading of braille documents, and Antonacopoulos techniques for improving OCR results.
Journal ArticleDOI
Machine printed character segmentation —; An overview
TL;DR: An overview of the character segmentation techniques in machine-printed documents is presented, which will cover techniques for segmenting uniformed or proportional fonts, broken and touching characters; techniques based on text image features and techniquesbased on recognition results.
Journal ArticleDOI
Segmentation of touching characters in printed document recognition
TL;DR: A dynamic recursive segmentation algorithm is developed for effectively segmenting touching characters based on both pixel and profile projections using contextual information and spell checking to correct errors caused by incorrect recognition and segmentation.
Journal ArticleDOI
Segmentation of merged characters by neural networks and shortest path
Jin Wang,J.S.N. Jean +1 more
TL;DR: A hybrid method is proposed which combines a neural network-based deferred segmentation scheme with conventional immediate segmentation techniques, and significantly improves its ability to read omnifont document text.
Related Papers (5)
Segmentation of Touching Characters in Mathematical Expressions Using Contour Feature Technique
Xuedong Tian,Yan Zhang +1 more
Segmentation of touching symbols for OCR of printed mathematical expressions: an approach based on multifactorial analysis
Utpal Garain,Bidyut B. Chaudhuri +1 more