Text line segmentation using a fully convolutional network in handwritten document images. Issue 3 (1st March 2018)

• Record Type: Journal Article
• Authors: Vo, Quang Nhat; Kim, Soo Hyung; Yang, Hyung Jeong; Lee, Guee Sang
• Is Part Of: IET image processing. Volume 12:Issue 3(2018)
• Page Start: 438
• Page End: 446
• Publication Date: 2018-03-01
• Subjects: document image processing -- text detection -- edge detection -- image segmentation -- neural nets -- graph theory -- handwritten character recognition; text line segmentation -- fully convolutional network -- handwritten document images -- line detection -- scanned document processing -- hand‐designed features -- heuristic rules -- text line location estimation -- FCN -- text line structure prediction -- line map -- text strings -- touching characters -- image segmentation -- line adjacency graph -- ICDAR2013 handwritten segmentation contest data set -- multiskewed text lines; Image processing -- Periodicals; 621.36705
• DOI: 10.1049/iet-ipr.2017.0083
• Languages: English
• ISSNs: 1751-9659

Abstract

Abstract : Line detection in handwritten documents is an important problem for processing of scanned documents. While existing approaches mainly use hand‐designed features or heuristic rules to estimate the location of text lines, the authors present a novel approach that trains a fully convolutional network (FCN) to predict text line structure in document images. A rough estimation of text line, or a line map, is obtained by using FCN, from which text strings that pass through characters in each text line are constructed. Finally, the touching characters should be separated and assigned to different text lines to complete the segmentation, for which line adjacency graph is used. Experimental results on ICDAR2013 Handwritten Segmentation Contest data set show high performance together with the robustness of the system with different types of languages and multi‐skewed text lines.