Machine printed text and handwriting identification in noisy document images

TitleMachine printed text and handwriting identification in noisy document images
Publication TypeJournal Articles
Year of Publication2004
AuthorsZheng Y, Li H, Doermann D
JournalPattern Analysis and Machine Intelligence, IEEE Transactions on
Volume26
Issue3
Pagination337 - 353
Date Published2004/03//
ISBN Number0162-8828
KeywordsAutomated;Reading;Reproducibility of Results;Sensitivity and Specificity;Signal Processing, Computer-Assisted;Information Storage and Retrieval;Models, Computer-Assisted;Pattern Recognition, Computer-Assisted;Stochastic Processes;Subtraction Technique;User-Computer Interface;Writing;, Markov random field;fisher classifiers;handwriting identification;machine printed text;noisy document images;page segmentation;recognition techniques;text identification;Markov processes;document image processing;feature extraction;handwriting recognition, Statistical;Numerical Analysis
Abstract

In this paper, we address the problem of the identification of text in noisy document images. We are especially focused on segmenting and identifying between handwriting and machine printed text because: 1) Handwriting in a document often indicates corrections, additions, or other supplemental information that should be treated differently from the main content and 2) the segmentation and recognition techniques requested for machine printed and handwritten text are significantly different. A novel aspect of our approach is that we treat noise as a separate class and model noise based on selected features. Trained Fisher classifiers are used to identify machine printed text and handwriting from noise and we further exploit context to refine the classification. A Markov Random Field-based (MRF) approach is used to model the geometrical structure of the printed text, handwriting, and noise to rectify misclassifications. Experimental results show that our approach is robust and can significantly improve page segmentation in noisy document collections.

DOI10.1109/TPAMI.2004.1262324