Development of offline handwritten signature authentication using artificial neural network

Handwritten signatures are playing an important role in finance, banking and education and more because it is considered to be the “seal of approval” and remains the most preferred means of authentication. In this paper, an offline handwritten signature authentication algorithm is proposed using Artificial Neural Network (ANN). As part of the feature extraction, two image filters were used, i.e. Canny edge detector and averaging filter. A feedforward neural network with 1 hidden layer was trained using backpropagation algorithm. The number of nodes in the hidden layer was varied from 80 to 1000. The higher the number of nodes, the higher the recognition rate. Moreover, we found that Canny edge detector is the suitable feature extraction as it produced higher recognition rate compared to the averaging filter.