Signature Verification using Convolutional Neural Network & Autoencoder


  • Prakash Ratna Prajapati Kantipur Engineering College
  • Samiksha Poudel
  • Madan Baduwal
  • Subritt Burlakoti
  • Sanjeeb Prasad Panday


Offline Signature, Writer Dependent, Convolutional Neural Network, Autoencoder


Signature has been one of the widely used verification biometrics out there. Handwritten signatures are used in cheques, forms, letters, applications, minutes, etc. The Signature of every individual is unique in nature, that's why it’s essential that a person’s handwritten signature be uniquely identified. Signature Verification is a widely used method for authenticating any individual during absence. Signature is a behavioural trait which cannot be copied easily, thus works as proof of identity. This paper presents an investigation of using Convolutional Neural Network (CNN) for Writer-Dependent models in signature verification. Random distortions were generated in genuine images using autoencoders to get forgery signatures, which were passed during training the classifier. The paper details all the pre-processing steps carried out on the image and shows various test results for changing the number of training sets of images.



How to Cite

P. R. Prajapati, S. Poudel, M. Baduwal, S. Burlakoti, and S. P. Panday, “Signature Verification using Convolutional Neural Network & Autoencoder ”, JIE, vol. 16, no. 1, pp. 33 - 40, Apr. 2021.