Title :
Offline signature verification using geometric center features
Author :
Afsardoost, Sepideh ; Yousefi, Siamak ; Khorshidi, M.A.
Author_Institution :
Dept. of Signals & Syst., Chalmers Univ. of Tech., Gothenburg
Abstract :
A modified offline signal verification method based on geometric centre has been presented in this paper. The aim is to distinguish if a signature is forgery or original. The method is based on geometric center features. After vertical and horizontal splitting of figure around its geometric center, Euclidean distance model was used for classification and then algorithm based on diagonal splitting is presented too. The overall system performance is considered in term of well defined measure quantities.
Keywords :
feature extraction; geometry; handwriting recognition; image recognition; Euclidean distance model; diagonal splitting algorithm; geometric center features; offline signature verification; static image; Classification algorithms; Error analysis; Euclidean distance; Feature extraction; Forgery; Handwriting recognition; Hidden Markov models; Solid modeling; System performance; Writing; Offline signature verification; forgery; geometric center; splitting;
Conference_Titel :
Signal Processing, 2008. ICSP 2008. 9th International Conference on
Conference_Location :
Beijing
Print_ISBN :
978-1-4244-2178-7
Electronic_ISBN :
978-1-4244-2179-4
DOI :
10.1109/ICOSP.2008.4697415
