Use of Auto associative Network for signature recognition

Abstract

A Neural Network model has been designed and proposed for signature recognition using Auto-Associative memory for training. The model reads the images of the signatures individually in the form of matrices and evaluates the weight matrices associated with each image. After training process is complete, whenever any of the signatures is provided to the system, the model recognizes it appropriately and displays it with the help of arduino. This model eliminates the long time consuming process of signature recognition.