TY - GEN
T1 - Detecting text lines in handwritten documents
AU - Yi, Li
AU - Yefeng, Zheng
AU - Doermann, David
PY - 2006
Y1 - 2006
N2 - Although detecting text lines in machine printed documents is typically considered a solved problem, it is still a challenge to segment handwritten text lines in the general sense given no prior knowledge of script. This paper models text line detection as an image segmentation problem by enhancing text line structures using a Gaussian window and adopting the level set method to evolve text line boundaries. Experiments show that the method, which is script independent, achieves high accuracy for detecting text lines in heterogeneous handwritten documents.
AB - Although detecting text lines in machine printed documents is typically considered a solved problem, it is still a challenge to segment handwritten text lines in the general sense given no prior knowledge of script. This paper models text line detection as an image segmentation problem by enhancing text line structures using a Gaussian window and adopting the level set method to evolve text line boundaries. Experiments show that the method, which is script independent, achieves high accuracy for detecting text lines in heterogeneous handwritten documents.
UR - https://www.scopus.com/pages/publications/34047211512
U2 - 10.1109/ICPR.2006.435
DO - 10.1109/ICPR.2006.435
M3 - Conference contribution
AN - SCOPUS:34047211512
SN - 0769525210
SN - 9780769525211
T3 - Proceedings - International Conference on Pattern Recognition
SP - 1030
EP - 1033
BT - Proceedings - 18th International Conference on Pattern Recognition, ICPR 2006
T2 - 18th International Conference on Pattern Recognition, ICPR 2006
Y2 - 20 August 2006 through 24 August 2006
ER -