PENGENALAN CITRA TANDA TANGAN MENGGUNAKAN GRAY LEVEL CO-OCCURRENCE MATRIX (GLCM) DAN PROBABILISTIC NEURAL NETWORK (PNN)

Abstract

The signature of a person is an important biometric attribute of a human being which can be used to authenticate human identity. There are various approaches to signature recognition with a lot of scope of research. In this paper, off-line signature recognition using probabilistic neural network is proposed, where the signature is captured and presented to the user in an image format. Signatures are recognized based on parameters extracted from the signature using gray level co-occurrence matrix. The features obtained are dissimilarity, entropy, and homogeneity. The recognition and verification was performed using probabilistic neural network. The proposed algorithm was tested on 100 signatures. The images of signature were divided in two sets: training set and test set. The leave-one-out cross-validation technique was applied for model validation. The research showed that the average accuracy from PNN was 71%