Showing papers on "Signature recognition published in 2007"

Off-line Handwritten Signature GPDS-960 Corpus

Abstract: The current need for large databases to evaluate automatic biometric recognition systems has motivated the developing of the GPDS-960 corpus, an off-line handwritten signature database which contains 24 genuine signatures and 30 forgeries of 960 individuals. This paper describes the GPDS signature corpus, gives details about the acquisition protocols and presents preliminary verification results obtained using the GPDS data.

Blind estimation of timing and carrier frequency offsets in OFDM systems

Abstract: Information fusion refers to the reconciliation of evidence presented by multiple sources of information in order to generate a decision. In the context of biometrics, evidence reconciliation plays a pivotal role in enhancing the recognition accuracy of human authentication systems and is referred to as multibiometrics. Multibiometric systems combine the information presented by multiple biometric sensors, algorithms, samples, units, or traits. Besides enhancing matching performance, these systems are expected to improve population coverage, deter spoofing and impart fault-tolerance to biometric applications. This introductory paper enumerates the various sources of biometric information that can be consolidated as well as the different levels of fusion in a biometric system. The role of using ancillary information such as biometric data quality and soft biometric traits (e.g., height) to enhance the performance of these systems is also discussed. It is becoming increasingly apparent that multibiometric systems will play a pivotal role in establishing identity in the 21st century.

Face Recognition System using Artificial Neural Networks Approach

Abstract: Advances in face recognition have come from considering various aspects of this specialized perception problem. Earlier methods treated face recognition as a standard pattern recognition problem; later methods focused more on the representation aspect, after realizing its uniqueness using domain knowledge; more recent methods have been concerned with both representation and recognition, so a robust system with good generalization capability can be built by adopting state-of-the-art techniques from learning, computer vision, and pattern recognition. A face recognition system based on recent method which concerned with both representation and recognition using artificial neural networks is presented. This paper initially provides the overview of the proposed face recognition system, and explains the methodology used. It then evaluates the performance of the system by applying two (2) photometric normalization techniques: histogram equalization and homomorphic filtering, and comparing with euclidean distance, and normalized correlation classifiers. The system produces promising results for face verification and face recognition

On-Line Signature Verification by Dynamic Time Warping and Gaussian Mixture Models

Abstract: Handwriting signature is the most diffuse mean for personal identification. Lots of works have been carried out to get reasonable errors rates within automatic signature verification on-line. Most of the algorithms that have been used for matching work by features extraction. This paper deals with the analysis of discriminative powers of the features that can be extracted from an on-line signature, how it's possible to increase those discriminative powers by dynamic time warping as a step in the preprocessing of the signal coming from the tablet. Also it will be covered the influence of this new step in the performance of the Gaussian mixture models algorithm, which has been shown as a successfully algorithm for on-line automatic signature verification in recent studies. A complete experimental evaluation of the algorithm base on dynamic time warping and Gaussian Mixture Models has been conducted on 2500 genuine signatures samples and 2500 skilled forgery samples from 100 users. Those samples are included at the public access MCyT-Signature-Corpus Database.

Biometric Signature Authentication Using Radon Transform-Based Watermarking Techniques

Abstract: In this paper we propose a signature-based biometric authentication system, where watermarking techniques are used to embed some dynamic signature features in a static representation of the signature itself. User authentication can be performed either by means of the only signature static image, or by using it together with the dynamic features embedded in the enrollment stage, by using a fusion approach. A multilevel authentication system, which is capable to provide two different levels of security, is then obtained. The proposed watermarking techniques are based on the properties of the Radon transform which well fits to the signature images. A robust embedding is obtained while keeping unaltered the original structure of the host signal.

Speech emotion recognition based on a hybrid of HMM/ANN

Abstract: Speech emotion recognition, as a vital part of affective human computer interaction, has become a new challenge to speech processing. In this paper, a hybrid of hidden Markov models (HMMs) and artificial neural network (ANN) has been proposed to classify emotions, combining advantage on capability to dynamic time warping of HMM and pattern recognition of ANN. HMMs, which export likelihood probabilities and optimal state sequences, have been used to model speech feature sequences, while ANN has been employed to make a decision. The recognition result of the hybrid classification has been compared with the isolated HMMs by two speech corpora, Germany database and Mandarin database, and the average recognition rates have reached 83.8% and 81.6% respectively.

Impact of Signature Legibility and Signature Type in Off-Line Signature Verification

Abstract: The performance of two popular approaches for off-line signature verification in terms of signature legibility and signature type is studied. We investigate experimentally if the knowledge of letters, syllables or name instances can help in the process of imitating a signature. Experimental results are given on a sub-corpus of the MCYT signature database for random and skilled forgeries. We use for our experiments two machine experts, one based on global image analysis and statistical distance measures, and the second based on local image analysis and Hidden Markov Models. Verification results are reported in terms of Equal Error Rate (EER), False Acceptance Rate (FAR) and False Rejection Rate (FRR).

Spectroscopic method and system for multi-factor biometric authentication

Abstract: A multi-factor biometrics authentication method including the steps of: acquiring a non-spectrometric biometric signature (e.g. fingerprint, iris pattern, etc.) of a biometric signature source (e.g. fingertip, iris, etc.) of a subject to be authenticated (e.g. person); acquiring spectral information (e.g. diffuse reflectance spectrum, reflectance spectrum, etc.) of the biometric signature source; using the non-spectrometric biometric signature to determine the unique identity of the biometric signature source; and using the spectral information to verify that the subject to be authenticated belongs to a predetermined class of objects (e.g. living persons). A biometrics system (e.g. fingerprint authentication device, iris pattern authentication device) is augmented with spectral biometrics capability in a practical manner without introducing much overhead to the base biometrics technology or inconvenience to users.

The Compact Three Stages Method of the Signature Recognition

Abstract: In this paper the off-line type signature analysis have been considered. Signature image by means of three different approaches is analysed, what allows to define features (weights) of the signature. Different influences of such features were tested and stated. In this paper, personal signature is pre-processed and in the three stages signature is processed. In proposed approach the Hough transform is introduced, centre of signature gravity is determined, and the horizontal and vertical signature histograms are performed. Proposed approach gives good signature recognition level, hence described method can be used in many areas, for example in biometric authentication, as biometric computer protection or as method of the analysis of person's behaviour changes.

Towards fast 3D ear recognition for real-life biometric applications

Abstract: Three-dimensional data are increasingly being used for biometric purposes as they offer resilience to problems common in two-dimensional data. They have been successfully applied to face recognition and more recently to ear recognition. However, real-life biometric applications require algorithms that are both robust and efficient so that they scale well with the size of the databases. A novel ear recognition method is presented that uses a generic annotated ear model to register and fit each ear dataset. Then a compact biometric signature is extracted that retains 3D information. The proposed method is evaluated using the largest publicly available 3D ear database appended with our own database, resulting in a database containing data from multiple 3D sensor types. Using this database it is shown that the proposed method is not only robust, accurate and sensor invariant but also extremely efficient, thus making it suitable for real-life biometric applications.

The application of signature recognition to transparent handwriting verification for mobile devices

Abstract: Purpose – The popularity of mobile devices and the evolving nature of the services and information they can delivery make them increasingly desirable targets for misuse. The ability to provide effective authentication of the user becomes imperative if protection against misuse of personally and financially sensitive information is to be provided. This paper discusses the application of biometrics to a mobile device in a transparent and continuous fashion and the subsequent advantages and disadvantages that are in contention with various biometric techniques.Design/methodology/approach – An investigation was conducted to evaluate the feasibility of utilising signature recognition, to verify users based upon written words and not signatures, thereby enabling transparent handwriting verification. Participants were required to write a number of common words, such as “hello” “sorry” and “thank you”. The ability to correctly verify against their own template and to reject impostors was then established.Findings...

Some Handwritten Signature Parameters in Biometric Recognition Process

Abstract: In this paper there is the off-line type signature analysis profoundly considered. The analysis consists of three stages which allow to define the features (weights) of the signature. Different influences of such features are tested and stated. In this paper personal signature is first pre-processed and then processed in the three-stage method. In proposed approach the Hough transform is introduced, the centre of signature gravity is determined, and the horizontal and vertical signature histograms are performed. Proposed approach gives good signature recognition level, hence described method can be used in many areas, for instance in biometric authentication, either as biometric computer protection or as a method of the analysis of person's behaviour changes.

Exemplar-based Parametric Hidden Markov Models for Recognition and Synthesis of Movements

Abstract: Disclosed is a method for controlling the flame front during the in situ combustion of a subterranean carbonaceous stratum which involves monitoring the extent and movement of said flame front to determine the location of one or more segments of the flame front which exhibit unfavorable combustion characteristics, and injecting one or more gases into the vicinity of one or more of said segments to control and optimize the combustion in said segment.

Methods for using a biometric parameter in the identification of persons

Abstract: Brain waves are used as a biometric parameter to provide for authentication and identification of personnel. The brain waves are sampled using EEG equipment and are processed using phase-space distribution functions to compare digital signature data from enrollment of authorized individuals to data taken from a test subject to determine if the data from the test subject matches the signature data to a degree to support positive identification.

Off-Line Signature Verification Based on Feature Matching

Abstract: This paper presents a novel approach for off-line signature verification. First the different aspects and problems of signature verification are discussed in conjunction with off-line analysis methods. It is shown, that on-line analysis methods perform usually better than off-line methods because they can make use of the temporal information (and thereby get a better perception of the semantics of the signature). An assumption is made, that off-line verification methods have difficulties improving their results because of the high level of abstraction they use, which is a direct consequence of the missing semantics. Afterwards a solution is presented with the ability to preserve some semantic information, and thereby deliver a better ability to analyze the results and optimize the system.

Evaluating the biometric sample quality of handwritten signatures

Abstract: This paper addresses the problem of evaluating the quality of handwritten signatures used for biometric authentication. It is shown that some signature samples yield significantly worse performance than other samples from the same person. Thus, the importance of good reference samples is emphasized. We also give some examples of features that are related to the signature stability and show that these have no influence on the actual utility of the sample in a comparison environment.

Automatic Template Update Strategies for Biometrics

Abstract: Some disadvantages of biometric systems are caused by intra-class variability that describes the fuzziness of biometric data given from a single person for one biometric characteristic. Reasons for example can be found in natural behavioral variability, poorly acquired biometric reference data, changing acquisition environments (e.g. alternating sensors) and/or in aging effects of the bearer of biometric information such wrinkles or injuries. The automatic exchange of biometric reference data sample in reference storage with another quality proofed biometric sample of particular person could greatly improve authentication performance of biometric systems. In this paper strategies are proposed to replace biometric reference samples adopting well known cache replacement strategies.

Pre-processing Biometric Parameters before Encoding and Decoding

Abstract: Biometric parameters acquired from human faces, voices, fingerprints, and irises are used for user authentication and access control. Because the biometric parameters are continuous and vary from one reading to the next, syndrome codes are applied to determine biometric syndrome vectors. The biometric syndrome vectors can be stored securely, while tolerating an inherent variability of biometric data. The stored biometric syndrome vector is decoded during user authentication using biometric parameters acquired at that time. The syndrome codes can also be used to encrypt and decrypt data. The biometric parameters can be pre-processed to form a binary representation, in which the binary representation has a set of predetermined statistical properties enforced imposed by a set of binary logical conditions.

Warping-Based Offline Signature Recognition

Abstract: Offline signature recognition is an important form of biometric identification that can be used for various purposes. Similar to other biometric measures, signatures have inherent variability and so pose a difficult recognition problem. In this paper, we explore a novel approach for reducing the variability associated with matching signatures based on curve warping. Existing techniques, such as the dynamic time warping approach, address this problem by minimizing a cost function through dynamic programming. This is by nature a 1-D optimization process that is possible when a 1-D parametrization of the curves is known. In this paper, we propose a novel approach for solving the curve correspondence problem that is not limited by the requirement of 1-D parametrization. The proposed approach utilizes particle dynamics and minimizes a cost function through an iterative solution of a system of first-order ordinary differential equations. The proposed approach is, therefore, capable of handling complex curves for which a simple parametrization is not available. The proposed approach is evaluated by measuring the precision and recall rates of documents based on signature similarity. To facilitate a realistic evaluation, the signature data we use were collected from real-world documents, spanning a period of several decades.

Effects of Time Normalization on the Accuracy of Dynamic Time Warping

Abstract: This paper revisits dynamic time warping, a method for assessing the dissimilarity of time series. In particular, this paper provides theoretical and experimental evidence showing that uncritical normalizing the length of the time series to be compared has a detrimental effect on the recognition accuracy in application domains such as on-line signature recognition, where the length of compared time series matters for their classification as match or non-match.

On the Use of Context-Dependent Modeling Units for HMM-Based Offline Handwriting Recognition

Abstract: The use of context dependent modeling units in handwriting recognition has been considered by many authors as promising substantial performance improvements in systems based on Hidden-Markov models. Interestingly, in the literature only a few approaches limited to online recognition are documented to make use of this technology. Therefore, we investigated whether context dependent modeling also offers advantages for offline recognition systems. The moderate performance improvements we achieved on a challenging unconstrained handwriting recognition task suggest that context dependent modeling can not easily be exploited for offline recognition. In this paper we will present the principles behind context dependent modeling and discuss the reasons for its limited applicability in recognizing offline handwriting data.

Off-Line Signature Recognition and Verification Using Neural Network

Abstract: In this paper, we present an off-line signature recognition and verification system using global and grid features of the signatures An artificial neural network based on back propagation algorithm is used for recognition and verification Performance measures like the learning rate FAR and FRR are analyzed The system was tested with 400 test signature samples, which include genuine and forgery signatures of twenty individuals With this system, a false rejection ratio of less than 01 and a false acceptance ratio of less than 02 are achieved

Biometric based repeat visitor recognition system and method

Abstract: A biometric authorization method, system, and program product Biometric data associated with a subject can be detected and acquired. Thereafter, particular biometric features can be segmented and extracted from the biometric data. These particular biometric features are then compared to biometric data previously stored in a database in order to determine if the particular biometric features match the biometric data previously stored in the database and thereby rapidly and automatically determine if the subject comprises a repeat visitor.

A single sensor hand biometric multimodal system

Abstract: Nowadays the question of identifying a person assumes a major role in many applications. To circumvent the limitations of traditional identity recognition mechanisms (e.g., passwords or ID cards), modern security control procedures often exploit people biometrics. This paper proposes a multimodal biometric system for personal recognition, based on three different biometrics computed from the same hand image. Features extracted from each of the five finger surface areas are fused at score level into a single biometric mode. Hand geometry, palmprint and finger surface biometric features are finally fused at decision level to come to a recognition decision. The achieved recognition results of FAR=0.31%, FRR=0.80% and a maximum recognition rate of 98.28% indicate that this work should be continued and might be considered for high security applications.

HMM Based Eyebrow Recognition

Abstract: We study the problem of how to recognize a person only by his eyebrow based on hidden Markov models (HMM). By experiments on a small-scale eyebrow image database taken from 27 subjects, we show that our HMM-based eyebrow recognition method can achieve the highest accuracy of 92.6%, based on the relation of its accuracy to the number of observation symbols and that of states. Hence, we conclude that human eyebrow can work as a biometric with certain possibility and feasibility.

Ordinal representations for biometrics recognition

Abstract: Biometrics provides a reliable method for automatic personal identification and has wide and important applications. The success of a biometric recognition system depends critically on its feature representation model for biometric patterns. The most challenging issue in biometric feature representation is to achieve sensitivity to inter-class differences and at the same time robustness against intra-class variations. Many biometric representation schemes have been reported but the above issue remains to be resolved. In this paper, we introduce ordinal measures for iris, face and palmprint image representation in an attempt to resolve this issue. With this so-called ordinal representation model in place, many best-performing biometric recognition methods may be interpreted as special cases of this model. In this sense, the proposed ordinal representation model forms a general framework for biometric pattern representation. Extensive experimental results on public biometric databases demonstrate the effectiveness and generality of this representation.

Robust multi-modal biometric fusion via multiple SVMs

Abstract: Existing learning-based multi-modal biometric fusion techniques typically employ a single static support vector machine (SVM). This type of fusion improves the accuracy of biometric classification, but it also has serious limitations because it is based on the assumptions that the set of biometric classifiers to be fused is local, static, and complete. We present a novel multi-SVM approach to multi-modal biometric fusion that addresses the limitations of existing fusion techniques and show empirically that our approach retains good classification accuracy even when some of the biometric modalities are unavailable.