Online signature verification using hybrid wavelet transform

Online signature verification is a prominent behavioral biometric trait. It offers many dynamic features along with static two dimensional signature image. In this paper, the Hybrid Wavelet Transform (HWT) was generated using Kronecker product of two orthogonal transform such as DCT, DHT, Haar, Hadamard and Kekre. HWT has the ability to analyze the signal at global as well as local level like wavelet transform. HWT-1 and -2 was applied on the first 128 samples of the pressure parameter and first 16 samples of the output were used as feature vector for signature verification. This feature vector is given to Left to Right HMM classifier to identify the genuine and forged signature. For HWT-1, DCT HAAR offers best FAR and FRR. For HWT-2, KEKRE 128 offers best FAR and FRR. HWT-1 offers better performance than HWT-2 in terms of FAR and FRR. As the number of states increase, the performance of the system improves. For HWT-1, KEKRE 128 offers best performance at 275 symbols whereas for HWT-2, best performance is at 475 symbols by KEKRE 128.