Offline Signature Verification and Identification Using Angle Feature and Pixel Density Feature And Both Method Together
Rahul Verma1, D.S. Rao2
1Rahul Verma, Computer Science and Engineering Department, Indore Institute of Science and Technology, Indore, India.
2Dr. D.S. Rao, Computer Science and Engineering Department, Indore Institute of Science and Technology, Indore, India.
Manuscript received on March 24, 2013. | Revised Manuscript received on April 13, 2013. | Manuscript published on April 30, 2013. | PP: 740-746 | Volume-2, Issue-4, April 2013. | Retrieval Number: D1597042413/2013©BEIESP
Open Access | Ethics and Policies | Cite
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: Today the human signature of a person is used as an identification of person because we are all know that the each person has distinct signature and every signature has its own physiology or behavioral characteristics. So the human signature used as a identification of person in various work like bank checks etc. The fraud person can easily generated the signature instead of unique signer in fraud way so we need a signature identification system. The signature identification can be done either offline or online manner. Here we used the image processing technique for offline signature identification here no dynamic feature are available in offline identification. Neural network is used as a classifier for this system. Here we propose an intelligent neural network that work on the feature like pixel density method, angular method and mix both methods together. And compared these methods and see that which one method is provides the better result and accuracy.
Keywords: Angle method, FAR, FRR, Neural Network, Pixel Density.