Development of novel signature architecture for signature recognition

The aim of this research paper is to propose a novel signature recognition system that utilizes deep learning techniques to accurately identify the name of a person based on their handwritten signature. The proposed architecture involves the use of a convolutional neural network (CNN) for feature extraction and a neural network for classification. Experiments were conducted on the GPDS synthetic Signature dataset [1] to evaluate the performance of the model. The results of the experiments showed that the proposed system achieved an impressive training accuracy of 99.98% and a validation accuracy of 84.53%