• Anil Purandar Athane
• Dr. Prashant D. Gangawane

The main goal of signature verification system is to detect forgeries and simultaneously reduce rejection of genuine signature. This paper deals with off-line signature verification and presents simple and effective verification method depends on raw binary pixel intensities and avoids complex set of features. . This method looks at the off-line signature verification problem as graph matching problem, using Hungarian algorithm.Genuine and forgery signatures produced by different subject are used to test this method. This method is useful to detect random and simple forgery signatures except skilled forgery.Threshold selection is based on statistical parameters like cost factor (Cost) which is derived from standard cost matrix and co-relation factor (K). According to that FAR(false acceptance rate), FRR(false rejection rate) is calculated. Vital parameters such as FAR and FRR is considerably reduced. This method provides high accuracy with optimum speed. Final results are displayed using after after signature verification. Key Words- off-line signature verification, cost

off-line signature verification, cost matrix, cost factor, co-relation factor, FAR, FRR, GUI, Hungarian algorithm.

"Signature verification and reduction of FAR and FRR using Hungarian algorithm ", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.6, Issue 1, page no.731-741, January-2019, Available :http://www.jetir.org/papers/JETIR1901796.pdf

"Signature verification and reduction of FAR and FRR using Hungarian algorithm ", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.6, Issue 1, page no. pp731-741, January-2019, Available at : http://www.jetir.org/papers/JETIR1901796.pdf