Abstract
We introduce an effective approach for offline verification of signatures where the forgeries are skillfully done, i.e., the true and forgery sample appearances are almost alike. Subtle details of temporal information used in online verification are not available offline and are also hard to recover robustly. Thus we take help of the spatial dynamic information like the pen-tip pressure characteristics and emphasize on the extraction of low pressure points. The points result from the ballistic rhythm of a genuine signature which a forgery, however skillful that may be, always lacks. Ten effective features along with low pressure points and pressure multiplication ratio are proposed to make the distinction between a true and a forgery sample. Three different threshold values are also derived for better verification judgements.
Indexing terms:
Additional information
Notes on contributors
Abhijit Mitra
Abhijit Mitra was born on 2nd February 1975 in Serampore, India. He completed his BE (Hons) degree from REC Durgapur in 1997, ME from Jadavpur University, Kolkata in 1999 and PhD from IIT Kharagpur in 2004 respectively. Since January 2004, he is working at the Institute of Engineering and Management (IEM), Kolkata as an Assistant Professor. His research interests include Adaptive Signal Processing, Finite Wordlength Signal Processing, Wireless Communications, Digital Image Processing and Pattern Recognition. He is a member of IEEE (USA)