A on-line signature verification method is proposed for producing a subband decomposed signal from signature data. The method uses signal which subband decomposed a time change of five types of pen-tablet data (i.e., x-coordinate, y-coordinate, pressure, direction, altitude) by Discrete Wavelet Transform (DWT). The high frequency subband decomposed signal is used here since individual features stand out, and the differences between the registered authentic signature and the forged signature become clear. Adaptive signal processing is used as a verification algorithm. It is repeated in order to reduce the error margin between the registered signature and the input signature.