Automatic offline identification of signature author based on deep learning and its evaluation in noisy conditions

Subject Areas : H.3.7. Learning

Davood Keykhosravi ¹ , Seyed Naser Razavi ² , Kambiz Majidzadeh ³ , Amin Babazadeh sangar ⁴

1 - Department of IT and Computer Engineering, Urmia Branch, Islamic Azad University, Urmia, Iran
2 - Department of IT and Computer Engineering, Urmia Branch, Islamic Azad University, Urmia, Iran
3 - Department of IT and Computer Engineering, Urmia Branch, Islamic Azad University, Urmia, Iran.
4 - Department of IT and Computer Engineering, Urmia Branch, Islamic Azad University, Urmia, Iran.

Received: 2022-08-22 Accepted : 2022-10-03 Published : 2022-08-01

Keywords: convolutional neural network (CNN), Automatic Identification of the Writer of the Signature, Pre-trained Network, Feature Learning,

Abstract :

Signature identification plays an important role in many areas such as banking, administrative and judicial systems. For this purpose, in this paper, an automatic intelligent framework is developed by combining a deep pre-trained network with a recurrent neural network. The results of the proposed model were evaluated on several valid datasets and collected datasets. Since there was no suitable Persian signature dataset, we collected a Persian signature dataset based on US ASTM guidelines and standards, which can be very effective and profound for deep approaches. Due to the very promising results of the proposed model in comparison with recent studies and conventional methods, to evaluate the resistance of the proposed model to different noises, we added Gaussian Noise, Salt and Pepper Noise, Speckle Noise, and Local var Noise in different SNRs to the raw data. The results show that the proposed model can still be resistant to a wide range of SNRs; So at 15 dB, the accuracy of the proposed method is still above 90%.