Signature recognition

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

Bimodal Biometric Verification Mechanism using fingerprint and face images(BBVMFF)

Abstract: An increased demand of biometric authentication coupled with automation of systems is observed in the recent times. Generally biometric recognition systems currently used consider only a single biometric characteristic for verification or authentication. Researchers have proved the inefficiencies in unimodal biometric systems and propagated the adoption of multimodal biometric systems for verification. This paper introduces Bi-modal Biometric Verification Mechanism using Fingerprint and Face (BBVMFF). The BBVMFF considers the frontal face and fingerprint biometric characteristics of users for verification. The BBVMFF Considers both the Gabor phase and magnitude features as biometric trait definitions and simple lightweight feature level fusion algorithm. The fusion algorithm proposed enables the applicability of the proposed BBVMFF in unimodal and Bi-modal modes proved by the experimental results presented.

Signature Recognition Using Backpropagation Neural Network

Abstract: Imitation or the fake signatures is the global fraud that cause the waste of financial sources, time and human effort. For this reason, signature recognition is the most widely used biometrics system for security and personal identification. Signatures are the most complex human patterns which are used to identify and approve the authorized persons. They can be varied according to the paper and pen influences, and human psychology and characteristics at the signature moment. Therefore, effective recognition of signatures is required in order to minimize the fraud. The usage of neural networks in biometrics, yet signature recognition, provides more steady and accurate identification thus authorization of person. This paper presents the preliminary results of developed offline signature recognition system using backpropagation neural network. Signature database is created by collecting the multiple signatures of 27 persons and the accuracy of the system is tested under artificially created conditions. System achieved 86% of highest recognition rate.

’Hidden signature’ —- a new solution for on-line verification using DTW

Abstract: The article presents the idea of hidden signature - an artificial signature which can effectively replace the template signature (the best representative of a training set) in signature verification algorithms employing DTW (dynamic time warping). In this paper a few methods for the hidden signature computation are presented with their quality parameters. The main approaches are based on recursive point-by-point averaging and evolutionary algorithms. The hidden signature was tested on the MCYT database, using both genuines and skilled forgeries. The results show that this approach leads to an improvement in verification system parameters.

Analysis of intra-person variability of features for off-line signature verification

Abstract: One of the major challenges in off-line signature verification is the fact that a person's own signature is influenced by a number of external and internal factors. This influence results in a high variability even between signatures written by the same signer. This paper proposes a method which is able to model the intra-person variability of a signature feature and also to identify and eliminate the effects of external factors. To demonstrate the efficiency of the algorithm, a sample signature verifier is constructed and evaluated on the Signature Verification Competition 2004 database. Experiments have shown that by using 3 features (endings, loops and skew vectors) an average error rate of 12% can be achieved by the system. These results may be further improved by increasing the number of features, used during the comparison of signatures.

Performance improvement of complex plane based feature vector for online signature recognition using soft biometric features

Abstract: This paper proposes well-worn approach for verification of Online Signature which is one of the biometric entity. The signature will capture on digitizer the missing points of the signature are calculated from MDDA algorithm. This paper uses a notion to extract the feature vector generation based on CAL-SAL function. To extract the feature vector intermediate transform of row & col will be evaluated and distributed over complex Walsh plane. The mean value for each blocks will be calculated which separates the first and last row & col of mean & density of CAL-SAL components for other transforms. Lastly soft biometric features are added to improve the performance. The results for the unimodal & Multi Algorithmic features vectors are compared. Performance Index & Security Performance Index will be evaluated which delivers the performance of the system.