TY - GEN
T1 - Text-independent writer identification using texture feature
AU - Wang, Dongli
AU - Wen, Ying
AU - Lu, Yue
PY - 2012
Y1 - 2012
N2 - This paper proposes an efficient method based on texture feature for text-independent writer identification. In order to extract texture feature, we use the modified 2-D Gabor filter, which can decompose the image into sub-bands with different frequencies and orientations. Nearest neighbor classifier based on weighted chi-square distance is utilized in classification. The experiments on a database containing 203 writers of address images demonstrate that the performance of our modified 2-D Gabor filter is better than that of the traditional 2-D Gabor filter and our proposed method achieves promising results.
AB - This paper proposes an efficient method based on texture feature for text-independent writer identification. In order to extract texture feature, we use the modified 2-D Gabor filter, which can decompose the image into sub-bands with different frequencies and orientations. Nearest neighbor classifier based on weighted chi-square distance is utilized in classification. The experiments on a database containing 203 writers of address images demonstrate that the performance of our modified 2-D Gabor filter is better than that of the traditional 2-D Gabor filter and our proposed method achieves promising results.
KW - modified 2-D Gabor filter
KW - weighted chisquare distance
KW - writer identification
UR - https://www.scopus.com/pages/publications/84868157008
U2 - 10.1007/978-3-642-34595-1_23
DO - 10.1007/978-3-642-34595-1_23
M3 - 会议稿件
AN - SCOPUS:84868157008
SN - 9783642345944
T3 - Communications in Computer and Information Science
SP - 162
EP - 168
BT - Advances on Digital Television and Wireless Multimedia Communications - 9th International Forum on Digital TV and Wireless Multimedia Communication, IFTC 2012, Proceedings
T2 - 9th International Forum on Digital TV and Wireless Multimedia Communication, IFTC 2012
Y2 - 9 November 2012 through 10 November 2012
ER -