作者: Saeed Jamali
DOI:
关键词:
摘要: The most important and difficult stage of each offline signature verification system is feature extraction stage. performance the mainly depends on effectiveness algorithm. Current methods in this domain make use different classifications approaches like Radon Transform, VQ, Gabor filter, SVM, KNN, MD, etc. However, accuracy still main issue field. final aim study to implement an verify originality test images distinguish skilled random forgery from genuine. This project combines XGabor gravity center point as a novel algorithm uses FRG (Feature Relation Graph) classifier for classification phase. proposed validated using GDPS database, where it achieved equal error rate 7.66% which outperformed latest works