Title :
Improved segmentation through dynamic time warping for signature verification using a neural network classifier
Author :
Lee, Wan Suck ; Mohankrishnan, N. ; Paulik, M.J.
Author_Institution :
Dept. of Electr. & Comput. Eng., Detroit Mercy Univ., MI, USA
Abstract :
A segmentation technique based on dynamic time warping is investigated as a means of obtaining improved alignment between multiple signatures from a writer; the segments generated through this approach are represented by an autoregressive model. The signature verification performance is evaluated with a neural network based classifier, and shown to be a significant improvement over previous results obtained by the authors that were based on uniform segmentation
Keywords :
autoregressive processes; handwriting recognition; image classification; image representation; image segmentation; multilayer perceptrons; neural net architecture; autoregressive model; biometric personal identification; dynamic time warping; multilayer perceptron; multiple signatures; neural network architecture; neural network classifier; segmentation; segments representation; signature verification; signature verification performance; uniform segmentation; Authentication; Biometrics; Computer networks; Data mining; Feature extraction; Handwriting recognition; Humans; Neural networks; Sampling methods; Spatial resolution;
Conference_Titel :
Image Processing, 1998. ICIP 98. Proceedings. 1998 International Conference on
Conference_Location :
Chicago, IL
Print_ISBN :
0-8186-8821-1
DOI :
10.1109/ICIP.1998.723707
