Off-line signature verification and forgery detection using fuzzy modeling

摘要: Automatic signature verification is a well-established and an active area of research with numerous applications such as bank check verification, ATM access, etc. This paper proposes novel approach to the problem automatic off-line forgery detection. The proposed based on fuzzy modeling that employs Takagi-Sugeno (TS) model. Signature detection are carried out using angle features extracted from box approach. Each feature corresponds set. fuzzified by exponential membership function involved in TS model, which modified include structural parameters. parameters devised take account possible variations due handwriting styles reflect moods. functions constitute weights optimization output model respect yields solution for We have also derived two models considering rule each input first formulation (Multiple rules) single all second formulation. In this work, we found multiple rules better than detecting three types forgeries; random, skilled unskilled large database sample signatures addition verifying genuine signatures. approaches, viz., innovative intuitive approaches improved performance.