Freeman chain code (FCC) representation in signature fraud detection based on nearest neighbour and artificial neural network (ANN) classifiers.

Abstract

This paper presents a signature verification system that used Freeman Chain Code (FCC) as directional feature and data representation. There are 47 features were extracted from the signature images from six global features. Before extracting the features, the raw images were undergoing pre-processing stages which were binarization, noise removal by using media filter, cropping and thinning to produce Thinned Binary Image (TBI). Euclidean distance is measured and matched between nearest neighbours to find the result. MCYT-SignatureOff-75 database was used. Based on our experiment, the lowest FRR achieved is 6.67% and lowest FAR is 12.44% with only 1.12 second computational time from nearest neighbour classifier. The results are compared with Artificial Neural Network (ANN) classifier.