Off-line Handwritten Signature Verification Research Articles

Off-line handwritten signature verification based on machine learning

This paper describes the results of recognizing handwritten signatures. For the experiments, the database of handwritten signatures BHSig260-Bengali, BHSig260-Hindi, CEDAR and TUIT was used. For classification, four options were used to reduce the signatures to sizes: 200×120, 250×150, 300×150 and 400×200 pixels. These images served as input for the proposed network architecture. As a result of testing the proposed approach, the average accuracy of correct classification of signatures on images of size 250×150 was achieved: for the CEDAR database it was 94.38%, for the BHSig260-Hindi database it was 95.63%, for the BHSig260-Bengali database it was 97.50% and for TUIT base is 90.04%.

Distribution of local curvature values as a structural feature for off-line handwritten signature verification

In the paper, a new feature for describing a digital image of a handwritten signature based on the frequency distribution of the values of the local curvature of the signature contours, is proposed. The calculation of this feature on the binary image of a signature is described in detail. A normalized histogram of distributions of local curvature values for 40 bins is formed. The frequency values recorded as a 40-dimensional vector are called the local curvature code of the signature.During verification, the proximity of signature pairs is determined by correlation between curvature codes and LBP codes described by the authors in [23]. To perform the signature verification procedure, a two-dimensional feature space is constructed containing images of the proximity of signature pairs. When verifying a signature with N authentic signatures of the same person, N(N-1)/2 patterns of the proximity of pairs of genuine signatures and N images of pairs of proximity of the analyzed signature with genuine signatures are presented in the feature space. The Support Vector Machine (SVM) is used as a classifier.Experimental studies were carried out on digitized images of genuine and fake signatures from two databases. The accuracy of automatic verification of signatures on the publicly available CEDAR database was 99,77 % and on TUIT was 88,62 %.

Research advanced in offline handwritten signature verification

Biometrics technology has penetrated into various fields of our lives that require authentication and verification, such as criminal investigation, check processing and legal procedures, which is a focus of debate in the scientific research community. As a biometric feature that is easy to obtain, verification of handwritten signatures has attracted great interest in the past several decades. Although the online handwritten signature verification (OnHSV) system can obtain more information and has a higher accuracy rate, the offline handwritten signature verification (OfHSV) system remains the focus of research, since most signatures we can obtain are offline. In this paper, according to the difference of steps of OfHSV, we classify and introduce the advanced research work of OfHSV from four aspects: datasets, preprocessing techniques, feature extraction methods, and neural network structures. Additionally, we introduced the background of signature verification system and the experimental results of existing technologies. Finally, we presented some notable challenges, leading the reader to current trends and future directions in this field.

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

Offline handwritten signature verification is one of the most prevalent and prominent biometric methods in many application fields. Siamese neural network, which can extract and compare the writers’ style features, proves to be efficient in verifying the offline signature. However, the traditional Siamese neural network fails to represent the writers’ writing style fully and suffers from low performance when the distribution of positive and negative handwritten signature samples is unbalanced. To address this issue, this study proposes a two-stage Siamese neural network model for accurate offline handwritten signature verification with two main ideas: (a) adopting a two-stage Siamese neural network to verify original and enhanced handwritten signatures simultaneously, and (b) utilizing the Focal Loss to deal with the extreme imbalance between positive and negative offline signatures. Experimental results on four challenging handwritten signature datasets with different languages demonstrate that compared with state-of-the-art models, our proposed model achieves better performance. Furthermore, this study tries to extend the proposed model to the Chinese signature dataset in the real environment, which is a significant attempt in the field of Chinese signature identification.

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.

Offline Handwritten Signature Verification Based on Local Ridges Features and Haar Wavelet Transform

Multiple applications use offline handwritten signatures for human verification. This fact increases the need for building a computerized system for signature recognition and verification schemes to ensure the highest possible level of security from counterfeit signatures. This research is devoted to developing a system for offline signature verification based on a combination of local ridge features and other features obtained from applying two-level Haar wavelet transform. The proposed system involves many preprocessing steps that include a group of image processing techniques (including: many enhancement techniques, region of interest allocation, converting to a binary image, and Thinning). In feature extraction and analysis stages, a combination of local ridge features and other features obtained from the details of Haar wavelet subbands are extracted. Each wavelet sub-band image is fragmented into blocks with overlap and then the local features and wavelet energies are extracted from each block. Experiments were performed using a database of 600 signature prints collected from 100 persons, (i.e., 6 samples per person). The recognition accuracy of the system was the optimum (100%) using two decomposition levels. For verification purposes, the False Reject Rate for the system was (0.025%) while False Acceptable Rate was (0.03%) respectively.

Reference Selection for Offline Hybrid Siamese Signature Verification Systems

This paper presents an off-line handwritten signature verification system based on the Siamese network, where a hybrid architecture is used. The Residual neural Network (ResNet) is used to realize a powerful feature extraction model such that Writer Independent (WI) features can be effectively learned. A single-layer Siamese Neural Network (NN) is used to realize a Writer Dependent (WD) classifier such that the storage space can be minimized. For the purpose of reducing the impact of the high intraclass variability of the signature and ensuring that the Siamese network can learn more effectively, we propose a method of selecting a reference signature as one of the inputs for the Siamese network. To take full advantage of the reference signature, we modify the conventional contrastive loss function to enhance the accuracy. By using the proposed techniques, the accuracy of the system can be increased by 5.9%. Based on the GPDS signature dataset, the proposed system is able to achieve an accuracy of 94.61% which is better than the accuracy achieved by the current state-of-the-art work.

Offline Handwritten Signature Verification Based on the One Class Symbolic Data Analysis Classifier for Reduced Reference Signatures

Offline Handwritten Signature Verification Based on the One Class Symbolic Data Analysis Classifier for Reduced Reference Signatures

Offline handwritten signature verification using various Machine Learning Algorithms

In today’s world it is necessary to protect one’s authenticity in order to ensure the protection of personal information that only the authenticate credentials of a person can have access to. Nowadays there is an increase in number of malpractices like signature forgery to access the important information of a person. To encounter signature verification problem, there have been a number of advances in verifying the authenticity of signature using various techniques including Machine Learning and Deep Learning. This paper introduces a novel approach to verify the signatures using difference of gaussian filtering technique, gray level co-occurrence matrix feature extraction technique, principle component analysis and kernel principal component analysis associated with various machine learning algorithms. The publicly available Kaggle offline handwritten signature dataset is used for training. This article compares the accuracy of the dataset on various machine learning algorithms. After training datasets the lowest accuracy achieved is 56.66% for Naive Bayes algorithm. The highest accuracy achieved is 82% for K-Nearest Neighbour (KNN) and 81.66% for Random Forest using principle components and kernel principle components of the dataset.

An Ensemble Based Offline Handwritten Signature Verification System

In the field of security and forgery prevention, handwritten signatures are the most widely recognized biometric since long and also most practical. Although handwritten signature verification systems are studied using both On-line and Off-line approaches, Off-line signature verification systems are more difficult to compare to On-line verification systems. This is due to the lack of dynamic information, viz. a database which constantly stores the latest signature of the person. In the paper an approach using ensemble methods are adopted to classify a signature as forgery or not. In proposed system, three classifiers, viz, one unsupervised, viz. Fuzzy C-Means (FCM) and two supervised classifiers, viz. Naive Bayes (NB) and Support Vector Machine (SVM) are used as base classifiers. An attempt is made to compare the different approaches. We attempt both the categories of classification not only because both of them are applicable in this particular case but also with an objective of finding out which performs better. In most cases it is observed that Naive Bayes and Ensemble are comparable as they exhibit better performance than the other two. But among them, in most of the cases Ensemble classifier performs better than the Naive Bayes and consequently we have taken the Ensemble as a final classifier.

Deep learning-based data augmentation method and signature verification system for offline handwritten signature

Offline handwritten signature verification is a challenging pattern recognition task. One of the most significant limitations of the handwritten signature verification problem is inadequate data for training phases. Due to this limitation, deep learning methods that have obtained the state-of-the-art results in many areas achieve quite unsuccessful results when applied to signature verification. In this study, a new use of Cycle-GAN is proposed as a data augmentation method to address the inadequate data problem on signature verification. We also propose a novel signature verification system based on Caps-Net. The proposed data augmentation method is tested on four different convolutional neural network (CNN) methods, VGG16, VGG19, ResNet50, and DenseNet121, which are widely used in the literature. The method has provided a significant contribution to all mentioned CNN methods’ success. The proposed data augmentation method has the best effect on the DenseNet121. We also tested our data augmentation method with the proposed signature verification system on two widely used databases: GPDS and MCYT. Compared to other studies, our verification system achieved the state-of-the-art results on MCYT database, while it reached the second-best verification result on GPDS.

Use of the Shearlet Transform and Transfer Learning in Offline Handwritten Signature Verification and Recognition

Despite the growing growth of technology, handwritten signature has been selected as the first option between biometrics by users. In this paper, a new methodology for offline handwritten signature verification and recognition based on the Shearlet transform and transfer learning is proposed. Since, a large percentage of handwritten signatures are composed of curves and the performance of a signature verification/recognition system is directly related to the edge structures, subbands of shearlet transform of signature images are good candidates for input information to the system. Furthermore, by using transfer learning of some pre-trained models, appropriate features would be extracted. In this study, four pre-trained models have been used: SigNet and SigNet-F (trained on offline signature datasets), VGG16 and VGG19 (trained on ImageNet dataset). Experiments have been conducted using three datasets: UTSig, FUM-PHSD and MCYT-75. Obtained experimental results, in comparison with the literature, verify the effectiveness of the presented method in both signature verification and signature recognition.

An Offline Signature Verification and Forgery Detection Method Based on a Single Known Sample and an Explainable Deep Learning Approach

Signature verification is one of the biometric techniques frequently used for personal identification. In many commercial scenarios, such as bank check payment, the signature verification process is based on human examination of a single known sample. Although there is extensive research on automatic signature verification, yet few attempts have been made to perform the verification based on a single reference sample. In this paper, we propose an off-line handwritten signature verification method based on an explainable deep learning method (deep convolutional neural network, DCNN) and unique local feature extraction approach. We use the open-source dataset, Document Analysis and Recognition (ICDAR) 2011 SigComp, to train our system and verify a questioned signature as genuine or a forgery. All samples used in our testing process are collected from a new author whose signatures are not present in the training or other stages. From the experimental results, we get the accuracy between 94.37% and 99.96%, false rejection rate (FRR) between 5.88% and 0%, false acceptance rate (FAR) between 0.22% and 5.34% in our testing dataset.

Meta-Learning for Fast Classifier Adaptation to New Users of Signature Verification Systems

Offline Handwritten Signature verification presents a challenging Pattern Recognition problem, where only knowledge of the positive class is available for training. While classifiers have access to a few genuine signatures for training, during generalization they also need to discriminate forgeries. This is particularly challenging for skilled forgeries, where a forger practices imitating the user’s signature, and often is able to create forgeries visually close to the original signatures. Most work in the literature address this issue by training for a surrogate objective: discriminating genuine signatures of a user and random forgeries (signatures from other users). In this work, we propose a solution for this problem based on meta-learning, where there are two levels of learning: a task-level (where a task is to learn a classifier for a given user) and a meta-level (learning across tasks). In particular, the meta-learner guides the adaptation (learning) of a classifier for each user, which is a lightweight operation that only requires genuine signatures. The meta-learning procedure learns what is common for the classification across different users. In a scenario where skilled forgeries from a subset of users are available, the meta-learner can guide classifiers to be discriminative of skilled forgeries even if the classifiers themselves do not use skilled forgeries for learning. Experiments conducted on the GPDS-960 dataset show improved performance compared to Writer-Independent systems, and achieve results comparable to state-of-the-art Writer-Dependent systems in the regime of few samples per user (5 reference signatures).

Writer-independent Offline Handwritten Signature Verification using Novel Feature Extraction Techniques

Writer-independent Offline Handwritten Signature Verification using Novel Feature Extraction Techniques

Feature Learning for Offline Handwritten Signature Verification Using Convolutional Neural Network

In biometrics, handwritten signature verification can be considered as an important topic. In this article, the authors' proposed method to verify handwritten signatures are based on deep convolution neural network (CNN), which is s bio-inspired network that works as if there exists human brain. Deep CNN extracts features from the studied images, which is followed by cubic support vector machine for classification. To evaluate their proposed work, the authors have tested on three different datasets: GPDS, BME2 and SVC20, and have received encouraging results.

Off-line handwritten signature verification using compositional synthetic generation of signatures and Siamese Neural Networks

In this work, we propose the use of Siamese Neural Networks to help solve the off-line handwritten signature verification problem with random forgeries in a writer-independent context. Our proposed solution can be used on new signers without the need for any additional training. Also, we have analyzed three types of synthetic data to increase the amount of samples and the variability needed for training deep neural networks: augmented data samples from GAVAB dataset, a proposal of compositional synthetic signature generation from shape primitives and the GPDSSynthetic dataset. The first two approaches are “on-demand” generators and they can be used during the training stage to produce a potentially infinite number of synthetic signatures. In our approach, we initially trained Siamese Neural Networks using signatures from GAVAB dataset and different combinations of synthetic data. The best verification results were obtained when combining original and synthetic signatures for training. Additionally, we tested our approach on the GPSSynthetic, MCYT, SigComp11 and CEDAR datasets demonstrating the generalization capabilities of our proposal.

Offline Handwritten Signature Verification using Distance based Classifier

Offline Handwritten Signature Verification using Distance based Classifier

Characterizing and Evaluating Adversarial Examples for Offline Handwritten Signature Verification

The phenomenon of Adversarial Examples is attracting increasing interest from the Machine Learning community, due to its significant impact to the security of Machine Learning systems. Adversarial examples are similar (from a perceptual notion of similarity) to samples from the data distribution, that "fool" a machine learning classifier. For computer vision applications, these are images with carefully crafted but almost imperceptible changes, that are misclassified. In this work, we characterize this phenomenon under an existing taxonomy of threats to biometric systems, in particular identifying new attacks for Offline Handwritten Signature Verification systems. We conducted an extensive set of experiments on four widely used datasets: MCYT-75, CEDAR, GPDS-160 and the Brazilian PUC-PR, considering both a CNN-based system and a system using a handcrafted feature extractor (CLBP). We found that attacks that aim to get a genuine signature rejected are easy to generate, even in a limited knowledge scenario, where the attacker does not have access to the trained classifier nor the signatures used for training. Attacks that get a forgery to be accepted are harder to produce, and often require a higher level of noise - in most cases, no longer "imperceptible" as previous findings in object recognition. We also evaluated the impact of two countermeasures on the success rate of the attacks and the amount of noise required for generating successful attacks.

Fixed-sized representation learning from offline handwritten signatures of different sizes

Methods for learning feature representations for Offline Handwritten Signature Verification have been successfully proposed in recent literature, using Deep Convolutional Neural Networks to learn representations from signature pixels. Such methods reported large performance improvements compared to handcrafted feature extractors. However, they also introduced an important constraint: the inputs to the neural networks must have a fixed size, while signatures vary significantly in size between different users. In this paper we propose addressing this issue by learning a fixed-sized representation from variable-sized signatures by modifying the network architecture, using Spatial Pyramid Pooling. We also investigate the impact of the resolution of the images used for training, and the impact of adapting (fine-tuning) the representations to new operating conditions (different acquisition protocols, such as writing instruments and scan resolution). On the GPDS dataset, we achieve results comparable with the state-of-the-art, while removing the constraint of having a maximum size for the signatures to be processed. We also show that using higher resolutions (300 or 600dpi) can improve performance when skilled forgeries from a subset of users are available for feature learning, but lower resolutions (around 100dpi) can be used if only genuine signatures are used. Lastly, we show that fine-tuning can improve performance when the operating conditions change.