Title :
Wavelet Transform Based Global Features for Online Signature Recognition
Author :
Afsar, F.A. ; Arif, M. ; Farrukh, U.
Author_Institution :
Dept. of Comput. & Inf. Sci., Pakistan Inst. of Eng. & Appl. Sci., Islamabad
Abstract :
This paper presents an efficient algorithm for an online signature verification system that is based on the extraction of global features from the spatial coordinates obtained during the online acquisition of a signature using one dimensional wavelet transform. A k-NN classifier is used for classification purposes. Low error rates obtained for both random and skilled forgeries datasets illustrate the feasibility of the algorithm for an online signature verification system
Keywords :
feature extraction; handwriting recognition; neural nets; pattern classification; wavelet transforms; global feature; neural net classifier; online signature recognition; wavelet transform; Authentication; Biometrics; Data mining; Error analysis; Feature extraction; Forgery; Handwriting recognition; Hidden Markov models; Spatial databases; Wavelet transforms; Biometrics; Signature Verification; Wavelet Transform; k-NN Classifier;
Conference_Titel :
9th International Multitopic Conference, IEEE INMIC 2005
Conference_Location :
Karachi
Print_ISBN :
0-7803-9429-1
Electronic_ISBN :
0-7803-9430-5
DOI :
10.1109/INMIC.2005.334431
