Off-line Signature Verification Research Articles

Similarity Distance Learning on SPD Manifold for Writer Independent Offline Signature Verification

Similarity Distance Learning on SPD Manifold for Writer Independent Offline Signature Verification

Offline signature verification using deep learning method

Offline signature verification using deep learning method

Signature Verification using ResNet-50 Model

Signed documents are widely accepted as a means of confirming identification, which offers signature verification systems a major advantage over other kinds of technologies. There are two types of approaches to solving this issue using a signature verification system: online and offline. Offline signature verification uses less electronic administration and uses recorded signature images from a camera or scanner. An offline signature verification method uses extracted features from the scanned signature image. This study's primary contribution is the understanding of how deep learning network ResNet-50 can be applied to offline signature verification systems. This paper proposes the use of ResNet-50 for offline signature verification. One kind of pretrained model that enables us to extract higher representations for the image content is called ResNet-50. CNN trained the model using the raw pixel data from the image, then automatically extracted the features for improved categorization. ResNet-50's primary advantage over its predecessors is that it has the highest accuracy of all image prediction algorithms and can automatically identify essential characteristics without human supervision. The accuracy of the ResNet-50 model was 75.8%, indicating good performance.

Writer Dependent Offline Signature Verification Based on Cluster-Specific Classifier

In this paper, we propose a writer dependent approach for offline signature verification based on writer-specific features and cluster-specific classifiers. In this work, writer-dependency is exploited at three levels: features, classifiers, and clusters. Initially, a template signature is selected for each writer from the training samples of that writer. This template signature serves as a representative signature of the respective writer. The relevant features for each writer are chosen using a filter-based feature selection method. The writers are then clustered based on their similar characteristics using the k-means algorithm. After clustering, a cluster-specific classifier is identified. This classifier is then set as the default classifier for all the writers in that cluster. During verification, writer-specific features and cluster-specific classifiers of the claimed writer are used to verify the authenticity of the given test signature. The approach is verified on three benchmarking offline signature datasets: CEDAR, MCYT, and GPDS-960.

Developing a Model for Offline Signature Verification Using CNN Architectures and Genetic Algorithm

The signature verification process has many applications, such as its use in financial operations, providing the electronic signature of documents, and providing an additional confidentiality standard to verify the identity of users in computer systems. This process has the advantage of being accepted by the community and is less intrusive compared to other biological methods. Deep learning (DL) and CNN (Convolutional Neural Network) are widely used by bioinformaticians. Due to the difficulty in extracting features in other systems or models, DL and CNN-based signature verification systems have been significantly improved. Yet Hyperparameter optimization for CNN models remains a challenging problem in designing highly efficient models with the most accurate results. It is often convolutional neural network (CNN) models that are manually designed. The proposed method is focused on a genetic algorithm that develops a population of CNN models in order to find the best fit architecture for designing an offline signature verification model. Our model is tested on more than one dataset, BHSig260-Bengali, BHSig260-Hindiin, GPDS, and CEDAR. The result of the approach proposed in this paper has the highest discrimination rate of FRR of 2.5, FAR 3.2, EER 2.35, and 97.73 %-accuracy rate.

TransOSV: Offline Signature Verification with Transformers

Signature verification is a frequently-used forensics technology in numerous safety-critical situations. Although convolutional neural networks (CNNs) have made significant advancements in the field of signature verification, their reliance on local neighborhood operations poses limitations in capturing the global contextual relationships among signature strokes. To overcome this weakness, in this paper, we propose a novel holistic-part unified model named TransOSV based on the vision transformer framework to solve offline signature verification problem. The signature images are first encoded into patch sequences by the proposed transformer-based holistic encoder to learn the global signature representation. Second, considering the subtle local difference between the genuine signature and forged signature, we design a contrast based part decoder along with a sparsity loss, which are utilized to learn the discriminative part features. With the learned holistic features and part features, the proposed model is optimized by the contrast loss function. To reduce the influence of sample imbalance, we also formulate a new focal contrast loss function. Furthermore, we conduct the proposed model to learn signature representations for writer-dependent signature verification task. The experimental results demonstrate the potential of the proposed TransOSV model for both writer-independent and writer-dependent signature verification tasks, achieving remarkable performance improvements and competitive results on four widely-used offline signature datasets.

A Survey : Deep Learning Approaches for Signature Verification

Since a person's signature serves as the primary authentication and authorization method in legal transactions, there is a greater need than ever for effective auto-mated signature verification solutions. The fact that signatures are already recognized as a popular way of identity verification gives signature verification systems a significant edge over other types of technologies. The methods used to solve this problem and a signature verification system can be categorized into two categories: online and offline. An electronic tablet and pen that are connected to a computer are used in the online technique to extract information about a signature and collect dynamic data for verification purposes, such as pressure, velocity, and writing speed. Offline signature verification, on the other hand, employs signature images that have been recorded by a scanner or camera and involve less electronic management. Extracted features taken from the scanned signature image are used in an offline signature verification system. The main contribution of this study is how we can use deep learning approaches/networks for the task of offline signature verification systems.

FC-ResNet: A Multilingual Handwritten Signature Verification Model Using an Improved ResNet with CBAM

Offline signature verification is a widely used biometric method in finance, law, and administrative procedures. However, existing deep convolutional neural network models perform poorly on signature datasets that span different regions and ethnic people, while also suffering from problems such as large parameter counts and slow inference speeds. To address these issues, we propose an improved residual network model (FC-ResNet). This model introduces a convolutional block attention module into the classical residual network to adapt to the diversity and variability of signatures, while also compressing the model for lightweight deployment. Due to the lack of public, offline handwritten signature datasets for ethnic people, we collected a large-scale offline handwritten signature dataset, including genuine signatures and forged signatures in Chinese, Uyghur, Kazakh, and Kirgiz, totaling 38,400 images. Our FC-ResNet model achieved an accuracy of over 96% for each language in our self-built dataset, as well as accuracy rates of 96.21%, 98.42%, and 97.28% on the public datasets CEDAR, BHSig-B, and BHSig-H, respectively. Based on the above experimental results, our proposed model demonstrates great potential for both public and self-built signature datasets, while also exhibiting significant advantages in lightweight model deployment. We believe that this work can provide a feasible solution for ethnic people signature verification.

Human Signature Verification System Using CNN with Tensor flow

One of the most popular verification biometrics is the signature. On checks, forms, letters, applications, minutes, and other documents, handwritten signatures are required. A person's handwritten signature must be individually identified because each individual's signature is unique by nature. Signature verification is a popular technique for confirming anyone's identity while they are not present. Human verification can be inaccurate and occasionally unsure. The use of Convolutional Neural Networks (CNN) for Writer-Dependent models in signature verification is examined in this research. In order to create forged signatures, random distortions were created in real photos using an auto encoder and then fed to the classifier during training. In addition to demonstrating various test outcomes for varying the number of training sets of images, the study describes all image pre-processing procedures that were applied to the image. In the Persian dataset, the system's average test accuracy is 83% after 22 real photos were used to train it. When the model was trained on nine real photos, accuracy dropped by 9.4%. Key Word: Offline Signature Verification, WD (Writer Dependent), CNN (Convolutional Neural Network), FAR (False Acceptance Ratio), FRR (False Rejection Ratio), Auto encoder

A Siamese Network based Writer Independent Offline Signature Verification

Signatures are frequently used for both personal authorization and verification. The signatures on numerous papers, including legal agreements and bank checks, must be verified. Offline signature verification is a type of authentication that examines the physical action of signing while measuring the characteristics of an user's handwriting. In the present paper, an offline signature verification method was developed utilising Convolutional Siamese Network of Deep Learning [4]. Convolutional Siamese networks, which are dual networks that shares parameters, can be developed to acquire a feature map. Thus, Convolutional Siamese network is employed to verify the person's signature to a input signature that is saved in the database. Research has been conducted with a dataset of signatures that includes 750 signatures from 30 different individuals. An Accuracy of 91.6% was attained by the proposed solution.

On the invariance of the digital description of a handwritten signature

The article presents results of our experiments carried out to study the invariance of the digital description of the image of a handwritten signature presented on paper. The description is built on the basis of a normalized image of the signature, digitized in the visible range of the electromagnetic spectrum by a scanner, with subsequent calculation of the distribution of its local features. The variability of this representation of the signature under different conditions simulating a change in its color, orientation on paper, line thickness and dimensions has been experimentally studied. It is shown that the digital description of the handwritten signature image, previously proposed by the authors, is sufficiently invariant with respect to the listed conditions for its execution to perform the off-line signature verification procedure.

Offline Signature Verification based on Ensemble of Features using Support Vector Machine

Offline Signature Verification based on Ensemble of Features using Support Vector Machine

Offline Signature Verification based on Geometric Features using Filter Method

Offline Signature Verification based on Geometric Features using Filter Method

OffSig-SinGAN: A Deep Learning-Based Image Augmentation Model for Offline Signature Verification

Offline signature verification (OfSV) is essential in preventing the falsification of documents. Deep learning (DL) based OfSVs require a high number of signature images to attain acceptable performance. However, a limited number of signature samples are available to train these models in a real-world scenario. Several researchers have proposed models to augment new signature images by applying various transformations. Others, on the other hand, have used human neuromotor and cognitive-inspired augmentation models to address the demand for more signature samples. Hence, augmenting a sufficient number of signatures with variations is still a challenging task. This study proposed OffSig-SinGAN: a deep learning-based image augmentation model to address the limited number of signatures problem on offline signature verification. The proposed model is capable of augmenting better quality signatures with diversity from a single signature image only. It is empirically evaluated on widely used public datasets; GPDSsyntheticSignature. The quality of augmented signature images is assessed using four metrics like pixel-by-pixel difference, peak signal-to-noise ratio (PSNR), structural similarity index measure (SSIM), and frechet inception distance (FID). Furthermore, various experiments were organised to evaluate the proposed image augmentation model’s performance on selected DL-based OfSV systems and to prove whether it helped to improve the verification accuracy rate. Experiment results showed that the proposed augmentation model performed better on the GPDSsyntheticSignature dataset than other augmentation methods. The improved verification accuracy rate of the selected DL-based OfSV system proved the effectiveness of the proposed augmentation model.

Offline Signature Verification Using Image Processing

A person’s signature is merely a handwritten sign that closely resembles his/her name, frequently stylized and distinctive, and that expresses the person’s identity, intent, and consent. Two types of verifications are present. They are online signature verification and offline signature verification. Generally, Offline Signature verification is less efficient and slower process compare to online verification when come to the situation having larger number of documents and files to verify with in less time. Over the years, many researchers have developed so many methods for signature verifications to help the people or organizations to find whether the signature of a particular person is forged or genuine. To overcome this problems; In this paper we introduced a simple method to improve the verification of the signature in Image Processing using Convolution Neural Networks(CNN). Signature Verification it is used to authenticate various kinds of documents, including cheques, draughts, certificates, approvals, letters, and other legal ones, such verification is crucial for preventing document forgery and falsification. Previously, to verify a signature, it was manually checked against copies of real signatures. This straightforward approach might not be sufficient given that forgery and signature fraud techniques are becoming more sophisticated as a result of improving technology.

Offline Signature Verification with Attention

Offline Signature Verification with Attention

One-Class Arabic Signature Verification: A Progressive Fusion of Optimal Features

Signature verification is regarded as the most beneficial behavioral characteristic-based biometric feature in security and fraud protection. It is also a popular biometric authentication technology in forensic and commercial transactions due to its various advantages, including noninvasiveness, user-friendliness, and social and legal acceptability. According to the literature, extensive research has been conducted on signature verification systems in a variety of languages, including English, Hindi, Bangla, and Chinese. However, the Arabic Offline Signature Verification (OSV) system is still a challenging issue that has not been investigated as much by researchers due to the Arabic script being distinguished by changing letter shapes, diacritics, ligatures, and overlapping, making verification more difficult. Recently, signature verification systems have shown promising results for recognizing signatures that are genuine or forgeries; however, performance on skilled forgery detection is still unsatisfactory. Most existing methods require many learning samples to improve verification accuracy, which is a major drawback because the number of available signature samples is often limited in the practical application of signature verification systems. This study addresses these issues by presenting an OSV system based on multifeature fusion and discriminant feature selection using a genetic algorithm (GA). In contrast to existing methods, which use multiclass learning approaches, this study uses a one-class learning strategy to address imbalanced signature data in the practical application of a signature verification system. The proposed approach is tested on three signature databases (SID-Arabic handwriting signatures, CEDAR (Center of Excellence for Document Analysis and Recognition), and UTSIG (University of Tehran Persian Signature), and experimental results show that the proposed system outperforms existing systems in terms of reducing the False Acceptance Rate (FAR), False Rejection Rate (FRR), and Equal Error Rate (ERR). The proposed system achieved 5% improvement.

Siamese Convolutional Neural Network-Based Twin Structure Model for Independent Offline Signature Verification

One of the toughest biometrics and document forensics problems is confirming a signature’s authenticity and legal identity. A forgery may vary from a genuine signature by specific distortions. Therefore, it is necessary to continuously monitor crucial distinctions between real and forged signatures for secure work and economic growth, but this is particularly difficult in writer-independent tasks. We thus propose an innovative and sustainable writer-independent approach based on a Siamese neural network for offline signature verification. The Siamese network is a twin-like structure with shared weights and parameters. Similar and dissimilar images are exposed to this network, and the Euclidean distances between them are calculated. The distance is reduced for identical signatures, and the distance is increased for different signatures. Three datasets, namely GPDS, BHsig260 Hindi, and BHsig260 Bengali datasets, were tested in this work. The proposed model was analyzed by comparing the results of different parameters such as optimizers, batch size, and the number of epochs on all three datasets. The proposed Siamese neural network outperforms the GPDS synthetic dataset in the English language, with an accuracy of 92%. It also performs well for the Hindi and Bengali datasets while considering skilled forgeries.

Multi-scripted Writer Independent Off-line Signature Verification using Convolutional Neural Network

Multi-scripted Writer Independent Off-line Signature Verification using Convolutional Neural Network

Multilingual Offline Signature Verification Based on Improved Inverse Discriminator Network

To further improve the accuracy of multilingual off-line handwritten signature verification, this paper studies the off-line handwritten signature verification of monolingual and multilingual mixture and proposes an improved verification network (IDN), which adopts user-independent (WI) handwritten signature verification, to determine the true signature or false signature. The IDN model contains four neural network streams with shared weights, of which two receiving the original signature images are the discriminative streams, and the other two streams are the reverse stream of the gray inversion image. The enhanced spatial attention models connect the discriminative streams and reverse flow to realize message propagation. The IDN model uses the channel attention mechanism (SE) and the improved spatial attention module (ESA) to propose the effective feature information of signature verification. Since there is no suitable multilingual signature data set, this paper collects two language data sets (Chinese and Uyghur), including 100,000 signatures of 200 people. Our method is tested on the self-built data set and the public data sets of Bengali (BHsig-B) and Hindi (BHsig-H). The method proposed in this paper has the highest discrimination rate of FRR of 10.5%, FAR of 2.06%, and ACC of 96.33% for the mixture of two languages.