TY - GEN
T1 - Segmentation and pre-recognition of arabic handwriting
AU - Lorigo, Liana
AU - Govindaraju, Venu
PY - 2005
Y1 - 2005
N2 - We propose a novel algorithm for the segmentation and pre-recognition of off-line handwritten Arabic text. Our character segmentation method over-segments each word, then removes extra breakpoints using knowledge of letter shapes. On a test set of 200 images, 92.3% of the segmentation points were detected correctly, with 5.1% instances of over-segmentation, The pre-recognition component annotates each detected letter with shape information, to be used for recognition in future work.
AB - We propose a novel algorithm for the segmentation and pre-recognition of off-line handwritten Arabic text. Our character segmentation method over-segments each word, then removes extra breakpoints using knowledge of letter shapes. On a test set of 200 images, 92.3% of the segmentation points were detected correctly, with 5.1% instances of over-segmentation, The pre-recognition component annotates each detected letter with shape information, to be used for recognition in future work.
UR - https://www.scopus.com/pages/publications/33645150878
U2 - 10.1109/ICDAR.2005.207
DO - 10.1109/ICDAR.2005.207
M3 - Conference contribution
AN - SCOPUS:33645150878
SN - 0769524206
SN - 9780769524207
T3 - Proceedings of the International Conference on Document Analysis and Recognition, ICDAR
SP - 605
EP - 609
BT - Proceedings of the Eighth International Conference on Document Analysis and Recognition
T2 - 8th International Conference on Document Analysis and Recognition
Y2 - 31 August 2005 through 1 September 2005
ER -