Title :
Text line segmentation in Chinese handwritten text images
Author :
Zhang, Chengdong ; Lee, Gueesang
Author_Institution :
Dept. of Electron. & Comput. Eng., Chonnam Nat. Univ., Gwangju, South Korea
Abstract :
In this paper, text line segmentation based on 2-D Tensor Voting is proposed, 2-D tensor voting is used to remove outliers and located center points of connected components. The saliency values and direction of normal vectors are represented information of tensors for segmentation. The text images obtained from HIT-MW dataset.
Keywords :
handwriting recognition; image segmentation; natural language processing; tensors; text analysis; 2D tensor voting; Chinese handwritten text images; HIT-MW dataset; normal vectors; saliency values; text line segmentation; Equations; Flowcharts; Image segmentation; Mathematical model; Standards organizations; Symmetric matrices; Tensile stress; handwritten characters; morphological operation; tensor voting; text line segmentation;
Conference_Titel :
Frontiers of Computer Vision (FCV), 2011 17th Korea-Japan Joint Workshop on
Conference_Location :
Ulsan
Print_ISBN :
978-1-61284-677-4
Electronic_ISBN :
978-1-61284-676-7
DOI :
10.1109/FCV.2011.5739736
