Off-line Signature Verification Research Articles

Metric meta-learning and intrinsic Riemannian embedding for writer independent offline signature verification

Offline signature verification necessitates the involvement of machine learning visual recognition techniques. Efficient signature e-verifiers in machine learning and data analysis methods often inherently assume that the visual representation of the signature data can be modeled by vectors of Euclidean nature. However, as scientists become increasingly aware, ignoring an intrinsically non-Euclidean, or geometric, structure of the data can lead to sub-optimal results. The objective of this research is to enhance offline signature verification by incorporating non-Euclidean representations, particularly symmetric positive definite matrices (SPD). Specifically, this work proposes a geometrically inspired solution to the challenging task of verifying a questioned signature sample given a reference set of template signatures. Thus, a pair of covariance matrices is intrinsically embedded into a vector, denoted as the Embedded Riemannian Pyramid (ERP) by exploring a set of pairwise SPD measures, between sub-SPD subsets originating from a pair of covariance matrices. In conclusion, the SigmML, a meta-optimization network in the space of the SPD matrices, is introduced as a novel metric learning framework with low-dimensional ERP embeddings as inputs. Evaluation is conducted under two blind scenarios, namely blind intra-dataset and cross-lingual testing, utilizing a multitude of signature datasets or different origins.

Enhancing Offline Signature Verification via Transfer Learning and Deep Neural Networks

Enhancing Offline Signature Verification via Transfer Learning and Deep Neural Networks

Handwritten Signature Verification Method Using Convolutional Neural Network

Automatic signature verification methods play a significant role in providing a secure and authenticated handwritten signature in many applications, to prevent forgery problems, specifically institutions of finance, and transections of legal papers, etc. There are two types of handwritten signature verification methods: online verification (dynamic) and offline verification (static) methods. Besides, signature verification approaches can be categorized into two styles: writer dependent (WD), and writer independent (WI) styles. Offline signature verification methods demands a high representation features for the signature image. However, lots of studies have been proposed for WI offline signature verification. Yet, there is necessity to improve the overall accuracy measurements. Therefore, a proved solution in this paper is depended on deep learning via convolutional neural network (CNN) for signature verification and optimize the overall accuracy measurements. The introduced model is trained on English signature dataset. For model evaluation, the deployed model is utilized to make predictions on new data of Arabic signature dataset to classify whether the signature is real or forged. The overall obtained accuracy is 95.36\% based on validation dataset.

Writer Independent Offline Signature Verification System using Global and Local Geometric Features

The objective of this paper is to propose an offline signature verification system (OSVS) designed for writer-independent applications. The system shall differentiate between original and forged signatures. The system encompasses key stages such as pre-processing, feature extraction, and model training and testing, employing the Support Vector Machine algorithm for classification. One challenge in creating a good OSVS is to find proper signature features to be used in the training/classification phases. In this research, global and local features are utilized. This includes signature area, mean, standard deviation, perimeter, number of connected components, number of vertical and horizontal edges, number of end points, number of branch points, and number of lines. The contributions of this paper are on several aspects of the offline signature verification process. Investigation in this study include data pre-processing techniques (normalization vs. standardization), kernel selection (Poly vs. RBF), dataset distribution for training and testing (80%-20% vs. 5-fold), and variations of the C and gamma parameters (C=1, 10, 100 and gamma=1, 10, 100). Improving the recognition rate involves removing of features with little or bad effect on the recognition rate. An algorithm for model-agnostic feature importance is executed, revealing that the most crucial features in the classification process are mean, standard deviation, perimeter, number of connected components, and number of end points. Signatures are classified as either original or forgery, and the model's performance is assessed on the CEDAR dataset. Experimental results shows a 95.65% accuracy of the proposed system when utilizing standardization with the RBF kernel.

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 Geometric Features using Filter Method

Offline Signature Verification based on Geometric Features using Filter Method

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

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

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