Detection of Signature Based Forgeries Using Artificial Neural Network

Abstract

Signature plays an important role in banking, financial, commercial etc. Signature may be unique for each person. In olden days, no techniques were used to find the forged signature and it becomes a tremendous strain for human brain. Sometimes the forged signature may also believe as an original one. But nowadays, there are so many methods to detect the forged signature. This paper explains about identifying the forged signature from original signature. The signatures are preprocessed then the features such area, centroid coordinate, eccentricity, kurtosis are extracted. Then it is classified using Artificial Neural Network effectively. The result is analyzed by changing the hidden nodes present in the Neural Network. The performance is evaluated using the parameters such as TPR, TNR, FPR and FNR.