Text line segmentation using a fully convolutional network in handwritten document images

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.

[1]  Jan P. Allebach,et al.  Text line detection based on cost optimized local text line direction estimation , 2015, Electronic Imaging.

[2]  Andrew Zisserman,et al.  Very Deep Convolutional Networks for Large-Scale Image Recognition , 2014, ICLR.

[3]  Gueesang Lee,et al.  Text Line Segmentation in Handwritten Document Images Using Tensor Voting , 2011, IEICE Trans. Fundam. Electron. Commun. Comput. Sci..

[4]  Gueesang Lee,et al.  Dense prediction for text line segmentation in handwritten document images , 2016, 2016 IEEE International Conference on Image Processing (ICIP).

[5]  Georgios Louloudis,et al.  Text Line Detection in Unconstrained Handwritten Documents Using a Block-Based Hough Transform Approach , 2007 .

[6]  Thomas Brox,et al.  Descriptor Matching with Convolutional Neural Networks: a Comparison to SIFT , 2014, ArXiv.

[7]  Haiyan Li,et al.  Text line segmentation using Viterbi algorithm for the palm leaf manuscripts of Dai , 2016, 2016 International Conference on Audio, Language and Image Processing (ICALIP).

[8]  Xiaogang Wang,et al.  Visual Tracking with Fully Convolutional Networks , 2015, 2015 IEEE International Conference on Computer Vision (ICCV).

[9]  Made Windu Antara Kesiman,et al.  A New Scheme for Text Line and Character Segmentation from Gray Scale Images of Palm Leaf Manuscript , 2016, 2016 15th International Conference on Frontiers in Handwriting Recognition (ICFHR).

[10]  Geoffrey E. Hinton,et al.  ImageNet classification with deep convolutional neural networks , 2012, Commun. ACM.

[11]  Georgios Louloudis,et al.  ICDAR 2009 Handwriting Segmentation Contest , 2009, ICDAR.

[12]  Xi Zhang,et al.  Text Line Segmentation for Handwritten Documents Using Constrained Seam Carving , 2014, 2014 14th International Conference on Frontiers in Handwriting Recognition.

[13]  Trevor Darrell,et al.  Caffe: Convolutional Architecture for Fast Feature Embedding , 2014, ACM Multimedia.

[14]  Venu Govindaraju,et al.  Segmentation and recognition of connected handwritten numeral strings , 1997, Pattern Recognit..

[15]  Ronan Collobert,et al.  Recurrent Convolutional Neural Networks for Scene Labeling , 2014, ICML.

[16]  Venu Govindaraju,et al.  2009 10th International Conference on Document Analysis and Recognition A Steerable Directional Local Profile Technique for Extraction of Handwritten Arabic Text Lines , 2022 .

[17]  Trevor Darrell,et al.  Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation , 2013, 2014 IEEE Conference on Computer Vision and Pattern Recognition.

[18]  Thomas Brox,et al.  Learning to Generate Chairs, Tables and Cars with Convolutional Networks , 2014, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[19]  Lawrence D. Jackel,et al.  Backpropagation Applied to Handwritten Zip Code Recognition , 1989, Neural Computation.

[20]  Karim Faez,et al.  Adaptive Script-Independent Text Line Extraction , 2011, IEICE Trans. Inf. Syst..

[21]  Ching Y. Suen,et al.  Thinning Methodologies - A Comprehensive Survey , 1992, IEEE Trans. Pattern Anal. Mach. Intell..

[22]  Trevor Darrell,et al.  Do Convnets Learn Correspondence? , 2014, NIPS.