Signature recognition

About: Signature recognition is a research topic. Over the lifetime, 2138 publications have been published within this topic receiving 37605 citations.

Signature recognition application based on deep learning

Abstract: Nowadays, with the increase of biometric studies, the diversity of biometric data increases and new methods are used in evaluation methods. Traditional biometrics, such as face, fingerprints, handpieces, now leave their place to a variety of biometrics, which contain characteristic information about more people and include movement information. In this study, the performance of the deep learning method based on convolutional neural network (CNN) is demonstrated on a nonlinear signature recognition problem. In this non-real-time signature recognition application, it has been tried to reduce the process load and memory requirement by using deep learning method. Two data sets with different participant numbers were created in the study. The performance and reliability of the system are examined by various ratios of training and testing data on these data sets.

Signature Verification System Based on Wavelets

Abstract: Very large percentage of daily financial transactions is generally carried out on the basis of verification of signatures. Therefore signature plays an important role both for authentication and authorization of any legal documents. Signature verification is the process used to verify an individual's hand written signature is genuine or forged signature. Classification of recognition rate of genuine signature and rejection rate of forgery signature is 95% and 5% respectively.

A robust dissimilarity representation for writer-independent signature modelling

Abstract: In this study, the authors present a novel dissimilarity-based signature modelling framework for writer-independent off-line signature verification. The proposed framework utilises a discrete Radon transform and a dynamic time warping algorithm for writer-independent signature representation in dissimilarity space, and a writer-specific strategy for dissimilarity normalisation. A discriminative classifier, either a discriminant function or a support vector machine, is utilised for verification purposes. Both linear and non-linear decision boundaries are considered. The authors show that the novel techniques presented in this study provide an improved platform for writer-independent signature modelling. When evaluated on Dolfing's data set, a signature database that contains 1530 genuine signatures and 3000 amateur skilled forgeries, the systems presented in this study outperform all previous systems also evaluated on this data set.

Signature identification via efficient feature selection and GPU-based SVM classifier

Abstract: The problem of handwritten signature recognition is considered significant in biometrics, in particular for determining the validity of official documents. The rationale consists of creating an off-line classifier to discriminate between fake (forged) and genuine digitalized signatures. In such applications containing thousands of samples machine learning techniques such as Support Vector Machines (SVM) play a preponderant role in overcoming the challenges inherent to this problematic. However, to deal with the computational burden of calculating the large Gram matrix, approaches such as Graphics Processing Units (GPU) computing are required for efficiently processing big image biometric data. In this paper, first, we present an empirical study for efficient feature selection concerning the signature identification problem. Second, an GPU-based SVM classifier that integrates a component of the open source Machine Learning Library (GPUMLib) supporting several kernels is developed. Third, we ran several experiments with improved performance over baseline approaches. From our study, we gain insights in both performance and computational cost under a number of experimental conditions, and conclude that the most appropriate model is usually a trade-off between performance and computational cost for a given experimental setup and dataset.

Joint iris and facial recognition based on feature fusion and biomimetic pattern recognition

Abstract: Fusion biometric recognition modal contributes in two aspects. It can not only improve the biometric recognition accuracy, but also gives a comparatively safe strategy, since it is difficult for intruders to achieve multi-biometric information simultaneously, especially the iris information. In this paper, a novel biometric fusion recognition modal with iris and facial images based on biomimetic pattern recognition is proposed. The Contourlet transform (CT) and two directional two dimensional principal component analysis (2D)2PCA are used here to extract the iris feature and the facial feature respectively, and a new fusion feature vector was formed on the combination of the previous iris and facial features. Lastly, the fusion feature vector is used to construct the covering of high dimensional space using biomimetic pattern recognition method, in which the hyper-sausage neuron is adopted. Furthermore, a fixed random matrix is used here to reduce the computational complexity and improve the recognition efficiency. Experiments on the public union database show that the proposed modal can achieve the state-of-the-art recognition accuracy while keeping the enrollment process safe.