Efficient Handwritten Signatures Identification using Machine Learning

Any agreement or contract between two more parties requires at least one party to employ a signature as evidence of the other parties' identities and means establishing intent. As result, people are curious about Signature Recognition than biometric methods like fingerprint scanning. Utilizing both Fourier Descriptors histogram oriented gradients (HOG) features, this paper presents an efficient algorithms for recognition. The use Local binary patterns (LBP) features in verification technique has been proposed. Using morphological techniques, is encapsulated within curve that symmetrical good match. Measured by frequency with which incorrect confirmed given system, false acceptance rate (FAR) provides indication effectiveness precision proposed system. local dataset 60 test patterns, investigation found 10% were incorrectly accepted FAR 0.169. Experiments conducted on photos from dataset. Verification signatures previously made KNN classifier. classifier produced higher FARs recognition accuracies prior techniques.