Convolutional Neural Network for Offline Signature Verification via Multiple Classifiers

The signature process is one of the most significant processes used by organizations to preserve the security of information and protect it from unwanted penetration or access. As organizations and individuals move into the digital environment, there is an essential need for a computerized system able to distinguish between genuine and forged signatures in order to protect people's authorization and decide what permissions they have. In this paper, we used Pre-Trained CNN for extracts features from genuine and forged signatures, and three widely used classification algorithms, SVM (Support Vector Machine), NB (Naive Bayes) and KNN (k-nearest neighbors), these algorithms are compared to calculate the run time, classification error, classification loss and accuracy for test-set consist of signature images (genuine and forgery). Three classifiers have been applied using (UTSig) dataset; where run time, classification error, classification loss and accuracy were calculated for each classifier in the verification phase, the results showed that the SVM and KNN got the best accuracy (76.21), while the SVM got the best run time (0.13) result among other classifiers, therefore the SVM classifier got the best result among the other classifiers in terms of our measures.

Offline Signature Verification System Using SVM Classifier with Image Pre-processing Steps and SURF Algorithm

A signature is a mark or name that represents the identity of the people and the Signature Verification System (SVS) is used to validate the identity of people. The signature verification system is mostly used for bank cheques, vouchers, intelligence agencies and others. There are two types of SVS which are online and offline signature verification systems. The paper deals with an offline signature verification system. The proposed system consists of four main stages, (i) image acquisition, (ii) image pre-processing, (iii) feature extraction and (iv) classification. The image pre-processing steps involved binarization, noise removal using Gaussian filter and image resizing and thinning. In the feature extraction stage, Bag-of-Features with the Speeded Up Robust Features (SURF) extractor was utilized. In the third stage, the Support Vector Machine (SVM) classifier is used. Lastly, the confusion matrix and the verification rate were used to evaluate the performance of the classifier. In this paper, we implement and compare the performance of the signature verification system without entering the user ID and the signature verification system entering the user ID. For the ratio of 75% and 25% of the training and testing, respectively, the average accuracy for the signature verification system without entering the user ID is 71.36%, whereas the average accuracy for the signature verification system entering the user ID is 79.55%.

A Comparative Study of Transfer Learning Models for Offline Signature Verification and Forgery Detection

Recognising one’s identity to enter a system is called authentication. This process can take various forms where users input the system with a set of identifying credentials to access the system. Signatures belong to behavioural biometric, where the distinct features of every individual are considered in order to corroborate the person’s identity. The act of falsely imitating one’s signature biometric to impersonate and leverage access to their asset is called signature forgery. Our paper presents a comparative study of various deep learning models using Siamese architecture, over a wide catalogue of signature images. Openly available datasets like CEDAR, Handwritten Signatures dataset from Kaggle, ICDAR 2011 SigComp, and BH-Sig260 signature corpus are used to train the models. A set of classifiers – Support Vector Classifiers (SVC), Gaussian Naïve Bayes (GNB), Logistic Regression (LR) and K-Nearest Neighbours (KNN) are applied sequentially to classify the signature as genuine or forged.