Automatic Discrimination between Printed and Handwritten Text in Documents

• Published in: 2009 XXII Brazilian Symposium on Computer Graphics and Image Processing pp. 261 - 267
• Main Authors: da Silva, Lincoln Faria, Conci, Aura, Sanchez, Angel
• Format: Conference Proceeding
• Language: English
• Published: IEEE 01.10.2009
• Subjects: Character recognition; Classification tree analysis; Computer graphics; Data mining; document analysis; Feature extraction; Hidden Markov models; Image databases; Image processing; Image segmentation; Machine Vision; Optical character recognition software; optical characters recognition; text identification
• ISBN: 1424449782; 9781424449781
• ISSN: 1530-1834
• DOI: 10.1109/SIBGRAPI.2009.40

Recognition techniques for printed and handwritten text in scanned documents are significantly different. In this paper we address the problem of identifying each type. We can list at least four steps: digitalization, preprocessing, feature extraction and decision or classification. A new aspect of our approach is the use of data mining techniques on the decision step. A new set of features extracted of each word is proposed as well. Classification rules are mining and used to discern printed text from handwritten. The proposed system was tested in two public image databases. All possible measures of efficiency were computed achieving on every occasion quantities above 80%.