Offline signature recognition: Artificial neural network approach

This paper discusses the offline signature recognition system in which features are extracted using Discrete Wavelet Transform (DWT) and Principal component analysis (PCA) and the artificial neural network (ANN) is used for the recognition of signature. ANN is used to recognize whether a signature is original or fraud. The user provide the scanned image of signature for computer database, modifies there quality by image preprocessing. Features are extracted from preprocessed image and extracted features are used as input of ANN training and recognition.