Signature verification using geometrical features and artificial neural network classifier

Abstract

Signature verification has been one of the major researched areas in the field of computer vision. Many financial and legal organizations use signature verification as an access control and authentication. Signature images are not rich in texture; however, they have much vital geometrical information. Through this work, we have proposed a signature verification methodology that is simple yet effective. The technique presented in this paper harnesses the geometrical features of a signature image like center, isolated points, connected components, etc., and with the power of Artificial Neural Network (ANN) classifier, classifies the signature image based on their geometrical features. Publicly available dataset MCYT, BHSig260 (contains the image of two regional languages Bengali and Hindi) has been used in this paper to test the effectiveness of the proposed method. We have received a lower Equal Error Rate (EER) on MCYT 100 dataset and higher accuracy on the BHSig260 dataset. INTRODUCTIONBiometric plays a vital role in the authentication of an individual in many financial institutions, and signatures are the most widely used modality for this purpose.Biometrics is used to identify or verify an individual digitally. The security applications that have been used in many financial and educational institutions using biometrics technology for decades [17]. Biometrics are classified into two categories: physiological and behavioral [13]. Physiological biometrics includes Face, Iris, Fingerprint, etc. and behavioral biometrics has signature, gait, etc.. Authentication of the

A Two-Stage Siamese Network Model for Offline Handwritten Signature Verification

“…Up to now, many methods have been proposed for offline handwritten signature verification [19][20][21]. Many studies often use texture features extraction such as gray-level co-occurrence matrix [22] and Local Binary Patterns [23]; directional-based features such as directional-pdf [24] and histogram of oriented gradients [25]; feature extractors specifically designed for offline handwritten signatures, such as the estimation of strokes by fitting Bezier curves [26]. Moreover, an inverse discriminative network [27] is proposed for writerindependent handwritten signature verification.…”

Deep learning-powered multimodal biometric authentication: integrating dynamic signatures and facial data for enhanced online security

“…Focusing on potential vulnerabilities in signature biometrics, Gonzalez-Garcia et al [11] investigated various attack scenarios. Jain et al [12] took a different approach by integrating geometrical features and neural networks for signature verification. Utilizing signatures, there are also studies using machine learning methods [13][14][15].…”

Offline signature verification using deep learning method

“…While behavioral characteristics include handwritten signatures and gait, a signature is still the most reliable way for authentication in many financial transactions because its acquisition process is simple and it requires less effort. However, this study is considered one of the most difficult challenges because the signatures of the same person may be affected by the person's situation at different times and are not necessarily similar [1,2].…”

“…Feature extractors can be classified as handcrafted feature extractors or learning feature representations from row data. Handcrafted feature extractors are widely used for signature verification [2,7,8], but it need human experts, extensive domain understanding, and more time when dealing with huge datasets. With the breakthrough in artificial intelligence and the appearance of deep learning techniques, a revolution has occurred in the performance of automatic feature extraction systems because of their ability to learn more meaningful features from data by themselves effectively and handle a large and complex dataset in less time [9].…”

“…For the classification stage, classifiers like Euclidean distance [16], Neural Network (NN) [2,7,12,13 and 17], Support Vector Machine (SVM) [7,8,11,[18][19][20][21] and K-nearest neighbor (K-NN) [11 and 19] are widely used in signature verification problem, but NN and SVM are widely used as a result of their superb performance compared to the rest.…”