Pattern Recognition of Signature Verification Using Cellular Automata Methods

Abstract

A pattern recognition technique in the field of machine learning and can be defined as "the act of taking raw data and act upon data classification". Much research has been done on the topic of pattern recognition using a variety of methods one of which is by using the cellular automata. In this study used cellular automata method for finding and extracting characteristics of an image of the signature and realized in a pattern recognition software that can verify the authenticity of the signature image by using cellular automata method for the extraction process characteristics. In this study used data 57 respondents with 6 signatures used as a reference image. Three pieces of the original signature image and 10 pieces of counterfeit signature image is used as the test images (query). From the testing that has been done precision 88.30%, recall 65.37% and accuracy 71.31%.