OFFLINE SIGNATURE VERIFICATION AND IDENTIFICATION USING SVM AND ANN

    The signature of a person is an important biometric attribute of a human being which can be used to authenticate human identity. However human signatures can be handled as an image and recognized using computer vision and neural network techniques. With modern computers, there is need to develop fast algorithms for signature recognition. There are various approaches to signature recognition with a lot of scope of research. In this project, off-line signature recognition & verification using ANN and SVM is proposed, where the signature is captured and presented to the user in an image format. Signatures are verified based on parameters extracted from the signature using various image processing techniques. The Off-line Signature Recognition and Verification is implemented using Matlab.

Steps for offline signature verification and identification:
1) Data acquisition and pre-processing
2) To extract features,
i. Apply Hu’s moment on original signature (will get 7 features)
ii. 1D radon transformation is applied on the signature image. The 2D radon function has been performed in 0, 45,90,135 directions (will get 35 features)
iii. After getting 1D radon images again apply Hu’s moment on this direction
iv. Segment original signature in 4 zones vertically (Normalized the signature in 32*128 size so that after zoning size of one zone is 32*64)
v. On each zone apply Gabor wavelet in 0,30,60,90,120, -30 directions
vi. Compute Energy and Standard Deviation (STD) separately on each sub band (will get 48 features)
vii. On each zone after getting Gabor wavelet images again apply Hu’s moment
3) For identification use nearest neighbor classifier
4) For verification use Support Vector Machine (SVM) and Artificial Neural Network(ANN) as a classifier

Reference Paper-1: Offline Signature Recognition & Verification using Neural Network

Author’s Name: O.C Abikoye,M.A Mabayoje and R. Ajibade

Source: International Journal of Computer Applications

Year:2011

Reference Paper-2: Offline Handwritten Signature Identification and Verification Using Multi-Resolution Gabor Wavelet

Author’s Name: Muhammad Reza Pourshahabi,Mohamad-Hoseyn Sigari and Hamid Reza Pourreza

Source: CiiT International Journal of Biometrics and Bioinformatics

Year:2011

Reference Paper-3: Off-Line Handwritten Signature Identification Using Rotated Complex Wavelet Filters

Author’s Name: M.S. Shirdhonkar and Manesh Kokare

Source: IJCSI International Journal of Computer Science

Year:2011

Reference Paper-4: Off-line Signature Verification based on Hu’s Moment Invariants and Zone Features using Support Vector Machine

Author’s Name: Mandeep Kaur Randhawa,A.K. Sharma and R.K Sharma

Source: International Journal of Latest Trends in Engineering and Technology (IJLTET)

Year:2012

Request design files for academic purpose, contact +91 7904568456 by whatsapp or sales@verilogcourseteam.com.

SIMULATION VIDEO DEMO                                                                                                                                     


PREVIOUS PAGE|NEXT PAGE