Signature recognition

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

Comparative Analysis of Offline Handwriting Recognition Using Invariant Moments with HMM and Combined SVM-HMM Classifier

Abstract: Offline Handwriting recognition is considered as important research field in the field of forensic and biometric applications. It finds significance in fields like graphology which exploits the physiological behavior of the person based on the handwriting. There are several algorithms for Handwriting recognition. However none of the techniques is yet proved to be satisfactory especially for large number of classes. This is due to the fact that handwriting is a pattern which differs from instance to instance of the same writer. Hence HMM is most preferred technique in this domain. It is due to the fact the HMM produces good result for large number of statistical patterns. However, the performance of the system depends entirely on the feature vectors. Unlike the cases of usual patter recognition like face recognition, a user's training and test sample may vary. Hence recognition of the same is tough. Therefore in this work we propose a novel technique for offline handwriting recognition based on Invariant Moments and curve let transform. Curvelet transform and Invariant moments are used predominantly for character recognition problem and hence are more suitable for the work. Further we compare the performance of HMM based technique with combined HMM-SVM based technique and found that for some combined HMM-SVM technique is better than HMM. Combined HMM-SVM classifier improve the problem of HMM classifier of multiple detection of Class too.

Off-Line Signature Authentication Based on Moment Invariants Using Support Vector Machine

Abstract: Problem statement: The research addressed the computational load reduction in off-line signature verification based on minimal features using bayes classifier, fast Fourier transform, linear discriminant analysis, principal component analysis and support vector machine approaches. Approach: The variation of signature in genuine cases is studied extensively, to predict the set of quad tree components in a genuine sample for one person with minimum variance criteria. Using training samples, with a high degree of certainty the Minimum Variance Quad tree Components (MVQC) of a signature for a person are listed to apply on imposter sample. First, Hu moment is applied on the selected subsections. The summation values of the subsections are provided as feature to classifiers. Results: Results showed that the SVM classifier yielded the most promising 8% False Rejection Rate (FRR) and 10% False Acceptance Rate (FAR). The signature is a biometric, where variations in a genuine case, is a natural expectation. In the genuine signature, certain parts of signature vary from one instance to another. Conclusion: The proposed system aimed to provide simple, faster robust system using less number of features when compared to state of art works.

On-line signature verification based on fusion of global and local information

Abstract: Automatic signature verification has been an intense research area because of the social and legal acceptance and widespread use of written signatures. It is still a challenging issue because of "small sample size " problem as well as large intra-class variations and, when considering forgeries, small inter-class variations. In order to solve these problems, we propose a two-stage fusion method to get high accuracy. At first, an EDTW (enhanced dynamic time warping) algorithm and a normalized feature measure are proposed to build a classifier based on local features. The former enhances the separability between genuine and forgery signatures, while the latter approaches the problem as a two-class pattern recognition problem, which make it possible to use training signatures as many as possible. However, local method is time and resource consuming, so we then design another classifier based on global features using majority voting rule. We fuse the global and local method by two-sage serial strategy to build an on-line signature verification system. Experimental results on SVC2004 TASK2 show good performance of our system.

One Dimensional Fractal Coder for Online Signature Recognition

Abstract: Fractal Theory has been used for computer graphics, image compression and different fields of pattern recognition. In this paper we simplified a general purpose two-dimensional fractal coder used for image compression. Since in the case of on-line signature recognition, we loose gray levels, contrast and luminosity information, we do NOT employ these parameters in the fractal coder. Instead, we focused on geometrical relationship between the range block and its best domain block. Then, some features were extracted directly by the proposed one dimensional fractal coder. We will show their usefulness in the application of Persian on-line signature recognition.

A study of multimodal biometric system

Abstract: Biometrics is a technique by which an individual's identity can be authenticated by applying the physical or behavioral trait. Physical traits, like fingerprints, face, iris etc. are based on physical characteristics which are generally inherent and stable. Behavioral traits, like voice, signature or keystroke dynamics etc. on the other hand, is a quantifiable characteristic. That is obtained over time and is subject to deliberate alteration. Unimodal biometric systems developed for each of these biometric features may not always meets the required performance. The methods are analyzed to integrate the various features together to acquire a multi-modal biometric system. The recent research reveals that multi-modal biometric system is more effective in authentication. The objective of this paper is to highlight the importance of the use of multimodal biometrics in the area of secure person authentication. This study provides a different perception to use biometrics as a highest level of network security with the fusion of multiple biometric modalities.