Showing papers on "Signature recognition published in 2008"

An introduction to biometrics

Abstract: Summary form only given. Biometrics refers to the automatic identification (or verification) of an individual (or a claimed identity) by using certain physical or behavioral traits associated with the person. By using biometrics it is possible to establish an identity based on `who you are?, rather than by `what you possess? (e.g., an ID card) or `what you remember? (e.g., a password). Therefore, biometric systems use fingerprints, hand geometry, iris, retina, face, vasculature patterns, signature, gait, palmprint, or voiceprint to determine a person?s identity. The purpose of this tutorial is two-fold: (a) to introduce the fundamentals of biometric technology from a pattern recognition and signal processing perspective by discussing some of the prominent techniques used in the field; and (b) to convey the recent advances made in this field especially in the context of security, privacy and forensics. To this end, the design of a biometric system will be discussed from the viewpoint of four commonly used biometric modalities - fingerprint, face, hand, and iris. Various algorithms that have been developed for processing these modalities will be presented. Methods to protect the biometric templates of enrolled users will also be outlined. In particular, the possibility of performing biometric matching in the cryptographic domain will be discussed. The tutorial will also introduce concepts in biometric fusion (i.e., multibiometrics) in which multiple sources of biometric information are consolidated. Finally, there will be a discussion on some of the challenges encountered by biometric systems when operating in a real-world environment and some of the methods used to address these challenges.

Biometric Person Recognition: Face, Speech and Fusion

Abstract: Over the last decade, interest in biometric based identification and verification systems has increased considerably. One application is the use of speech signals, face images or fingerprints in order to supplement security systems based on passwords. Biometric recognition can also be applied to other areas, such as passport control (immigration checkpoints), forensic work (to determine whether a biometric sample belongs to a suspect) and law enforcement applications (e.g. surveillance). While biometric systems based on face images and/or speech signals can be effective, their performance can degrade in the presence of challenging conditions. In face based systems this can be in the form of a change in the illumination direction and/or face pose variations. Multi-modal systems use more than one biometric at the same time. This is done for two main reasons -- to achieve better robustness and to increase discrimination power. This book can serve as a useful primer for face and speech processing, as well as information fusion. It reviews relevant backgrounds and reports research aimed at increasing the robustness of single- and multi-modal biometric identity verification systems.

Template protection for HMM-based on-line signature authentication

Abstract: The security of biometric data is a very important issue in the deployment of biometric-based recognition systems. In this paper, we propose a signature-based biometric authentication system, where signal processing techniques are applied to the acquired on-line signature in order to generate protected templates, from which retrieving the original data is computationally as hard as randomly guessing them. A hidden Markov model (HMM)-based matching strategy is employed to compare the transformed signatures. The proposed protected authentication system generates a score as the result of the matching process, thus allowing to implement protected multibiometric recognition systems, through the application of score-fusion techniques. The experimental results show that, at the cost of only a slight performance reduction, the desired protection for the employed biometric templates can be properly achieved.

Multimodal Biometric System Based on Fingerprint Identification and Iris Recognition

Abstract: Mono modal biometric systems encounter a variety of security problems and present sometimes unacceptable error rates. Some of these drawbacks can be overcome by setting up multimodal biometric systems. Multimodal biometrics consists in combining two or more biometric modalities in a single identification system to improve the recognition accuracy. However features of different biometrics have to be statistically independent. This paper proposes a multimodal biometric systems using fingerprint and iris recognition.

Effects of watermarking on iris recognition performance

Abstract: Protection of biometric data and templates is a crucial issue for the security of biometric systems, and biometric watermarking is introduced for this purpose. However, watermarking introduces extra information into the biometric data (biometric images or biometric feature templates) which leads to certain distortion. In addition, watermarked images are always subject to the risk of being attacked. Hence, whether and how biometric recognition performance will be affected by biometric watermarking deserves investigation. In this paper, we make a first attempt in such investigations by studying two application scenarios in the context of iris recognition, namely protection of iris templates by hiding them in cover images as watermarks (iris watermarks), and protection of iris images by watermarking them. Experimental results suggest that watermark embedding in iris images does not introduce detectable decreases on iris recognition performance whereas recognition performance drops significantly if iris watermarks suffer from severe attacks.

Cancelable Biometrics for HMM-based Signature Recognition

Abstract: Along with the wide diffusion of biometric-based authentication systems, the need to provide security and privacy to the employed biometric templates has become an issue of paramount importance in the design of user-friendly applications. Unlike password or tokens, if a biometrics is compromised, usually it cannot be revoked or reissued. In this paper we propose an on-line signature-based biometric authentication system, where non invertible transformations are applied to the acquired signature functions, making impossible to derive the original biometrics from the stored templates, while maintaining the same recognition performances of an unprotected system. Specifically, the possibility of generating cancelable templates from the same original data, thus providing a proper solution to privacy concerns and security issues, is deeply investigated.

Multimodal biometric person authentication system using speech and signature features

Abstract: In this work, we present a multimodal biometric system using speech and signature features. Speaker recognition system is built using Mel frequency cepstral coefficients (MFCC) for feature extraction and vector quantization (VQ) for modeling. An offline signature recognition system is also built using vertical and horizontal projection profiles (VPP and HPP) and discrete cosine transform (DCT) for feature extraction. A multimodal biometric database with speech and signature biometric features collected from 30 users is used for the study. A multimodal biometric system is demonstrated using score level fusion of speaker and signature recognition systems. Sum rule is used for the fusion of the biometric scores. Experimental results show the efficacy of multimodal biometric system using speech and signature features when the biometric data is affected by noise.

On Signature Invariants for Effective Motion Trajectory Recognition

Abstract: Motion trajectory can be an informative and descriptive clue that is suitable for the characterization of motion. Studying motion trajectory for effective motion description and recognition is important in many applications. For instance, motion trajectory can play an important role in the representation, recognition and learning of most long-term human or robot actions, behaviors and activities. However, effective trajectory descriptors are lacking and most reported work just uses motion trajectory in its raw data form. In this paper, we propose a novel motion trajectory signature descriptor and study its rich descriptive invariants which benefit effective motion trajectory recognition. These invariants are key measures of the flexibility and effectiveness of a descriptor. Substantial descriptive invariants can be deduced from the proposed trajectory signature, which is attributed to the computational locality of the signature components. We first present the signature definition and its robust implementation. Then the signature's invariants are elaborated. A non-linear inter-signature matching algorithm is developed to measure the signature's similarity for trajectory recognition. Experiments are conducted to recognize human sign language, in which both synthetic and real data are used to verify the signature's invariants, and to illustrate the effectiveness in the signature recognition.

Offline handwritten Devanagari word recognition: A segmentation based approach

Abstract: A novel segmentation based approach is proposed for recognition of offline handwritten Devanagari words. Stroke based features are used as feature vectors. A hidden Markov model is used for recognition at pseudocharacter level. The word level recognition is done on the basis of a string edit distance.

Biometric template protection using watermarking with hidden password encryption

Abstract: For quite a few years the biometric recognition techniques have been developed. Here, we briefly review some of the known attacks that can be encountered by a biometric system and some corresponding protection techniques. We explicitly focus on threats designed to extract information about the original biometric data of an individual from the stored data as well as the entire authentication system. In order to address security and privacy concerns, we present a biometric authentication scheme that uses two separate biometric features combined by watermark embedding with hidden password encryption to obtain a non-unique identifier of the personage. Furthermore, to present the performance of the authentication system we provide experimental results. The transformed features and templates trek through insecure communication line like the Internet or intranet in the client-server environment. Our projected technique causes security against attacks and eavesdropping because the original biometric will not be exposed anywhere in the authentication system.

Dynamic signature recognition based on velocity changes of some features

Abstract: Dynamic signature analysis allows us to register individuals and their hidden human behaviour. This paper presents a stroke-based approach to dynamic analysis of signature. Individual features can be identified by finding the discrete signature points like x,y-coordinates, pressure, time and pen velocity. Between signatures, the correlation measure is determined. The dynamic features are extracted from authentic and forged signatures. Experimental results show that measurement of dynamic features (velocity changes) contains important information and offers a high level of accuracy for signature verification in comparison with the results without such measurements, which will be explained in the following parts of the paper.

A Method for Off-line Persian Signature Identification and Verification Using DWT and Image Fusion

Abstract: Signature verification and Identification has great importance in authentication systems. Persian signatures are different from other signature types because people usually do not use text in it and they draw a shape as their signature. In this paper, a method for off-line Persian signature identification and verification is proposed that is based on DWT (Discrete Wavelet Transform) and Image Fusion. To extract features, at first DWT is used to access details of signature; then several signatures instances of each person are fused together to generate reference pattern of person's signature. In the classification phase, Euclidean distance between the test image and each pattern is used in each sub band. Experimental results confirmed the effectiveness of proposed method.

Dynamic Programming Algorithms in Speech Recognition

Abstract: In a system of speech recognition containing words, the recognition requires the comparison between the entry signal of the word and the various words of the dictionary. The problem can be solved efficiently by a dynamic comparison algorithm whose goal is to put in optimal correspondence the temporal scales of the two words. An algorithm of this type is Dynamic Time Warping. This paper presents two alternatives for implementation of the algorithm designed for recognition of the isolated words.

A hierarchical motion trajectory signature descriptor

Abstract: Motion trajectory is a compact clue for motion characterization. However, it is normally used directly in its raw data form in most work and effective trajectory description is lacking. In this paper, we propose a novel hierarchical motion trajectory signature descriptor, which can not only fully capture motion features for detailed perception, but also can be used for probabilistic fast recognition. The hierarchy enables the signature to exhibit high functional adaptability meeting different application requirements. At the first-level, differential invariants are employed to describe trajectory features and a nonlinear signature warping method is developed to perceive and recognize trajectories. The second-level signature is the condensation of the first-level signature by applying PCA based dimension optimization. It behaves more efficiently in recognition based on the Gaussian Mixture modeling and Bayesian classifier. The conducted experiments verified the signature's effectiveness.

Isolated Malay Digit Recognition Using Pattern Recognition Fusion of Dynamic Time Warping and Hidden Markov Models

Abstract: This paper is presents a pattern recognition fusion method for isolated Malay digit recognition using Dynamic Time Warping (DTW) and Hidden Markov Model (HMM). The aim of the project is to increase the accuracy percentage of Malay speech recognition. This study proposes an algorithm for pattern recognition fusion of the recognition models. The endpoint detection, framing, normalization, Mel Frequency Cepstral Coefficient (MFCC) and vector quantization techniques are used to process speech samples to accomplish the recognition. Pattern recognition fusion method is then used to combine the results of DTW and HMM which uses weight mean vectors. The algorithm is tested on speech samples that are a part of a Malay corpus. This paper has shown that the fusion technique can be used to fuse the pattern recognition outputs of DTW and HMM. Furthermore it also introduced refinement normalization by using weight mean vector to get better performance with accuracy of 94% on pattern recognition fusion HMM and DTW. Unlikely accuracy for DTW and HMM, which is 80.5% and 90.7% respectively.

Spoken Digit Recognition using a Hierarchical Temporal Memory

Abstract: In this paper we explore the feasibility of the MemoryPrediction Theory, implemented in the form of a Hierarchical Temporal Memory (HTM), for automatic speech recognition. Up to nowHTMs have almost exclusively been applied to image processing. However, the underlying theory can also be used as an approach to active perception of audio signals. Using the software platform under development by NUMENTA we implemented a system for isolated digit recognition, the speech recognition task that can be most easily cast in a form similar to image recognition. Our results show that the HTM approach holds promises for speech recognition. At the same time it is clear that the present implementation is not ideally suited for processing signals that encode information mainly in dynamic changes.

SIGMA - A Malaysian signatures’ database

Abstract: This poster presents a database of Malaysian signatures named SIGMA describing the strategies adopted in compiling it and its technical details. The database consists of over 6,000 genuine signature samples and over 2,000 forged signature samples of Malaysian nationals. The signature samples are collected simultaneously in both online and offline mode thereby eliminating the variation which is inevitable if the two modes are done at different times. This is particularly appealing to studies which are aimed at exploring the co-relationships between static signature features and their dynamic counterparts (that are derived from offline and online signature samples respectively). Furthermore, all forgeries in the database are 'skilledforgeries'. The collection of only Malaysian signatures makes the database very useful for designing a signature verification system that is optimized to verify Malaysian signatures.

On Empirical Recognition Capacity of Biometric Systems Under Global PCA and ICA Encoding

Abstract: Performance of biometric-based recognition systems depends on various factors: database quality, image preprocessing, encoding techniques, etc. Given a biometric database and a selected encoding method, the recognition capability of a system is limited by the relationship between the number of classes that the recognition system can encode and the length of encoded data describing the template at a specific level of distortion. In this paper, we evaluate empirical recognition capacity of biometric systems under the constraint of two global encoding techniques: principal component analysis (PCA) and independent component analysis (ICA). The developed methodology is applied to predict the capacity of different recognition channels formed during the acquisition of different iris and face databases. The proposed approach relies on data modeling and involves classical detection and information theories. The major contribution is in providing a guideline on how to evaluate capabilities of large-scale biometric recognition systems that are based on PCA and ICA encoding. Recognition capacity can also be promoted as a global quality measure of biometric databases.

Multi Pattern Dynamic Time Warping for automatic speech recognition

Abstract: We are addressing the problem of jointly using multiple noisy speech patterns for automatic speech recognition (ASR), given that they come from the same class. If the user utters a word K times, the ASR system should try to use the information content in all the K patterns of the word simultaneously and improve its speech recognition accuracy compared to that of the single pattern based speech recognition. To address this problem, recently we proposed a multi pattern dynamic time warping (MPDTW) algorithm to align the K patterns by finding the least distortion path between them. A constrained multi pattern Viterbi algorithm was used on this aligned path for isolated word recognition (IWR). In this paper, we explore the possibility of using only the MPDTW algorithm for IWR. We also study the properties of the MPDTW algorithm. We show that using only 2 noisy test patterns (10 percent burst noise at -5 dB SNR) reduces the noisy speech recognition error rate by 37.66 percent when compared to the single pattern recognition using the dynamic time warping algorithm.

Automatic Signature Recognition and Verification Using Principal Components Analysis

Abstract: The fact that the signature is widely used as a means of personal verification emphasizes the need for an automatic recognition system. Recognition can be performed either offline or online based on the application. Online systems use dynamic information of a signature captured at the time the signature is made. Offline systems work on the scanned image of a signature. In this paper we present a method for Offline recognition and verification signatures using Principal components analysis. The proposed method consists of image prepossessing , feature extraction, evaluate the Principal components analysis for the extracted feature and the identification step. The identification step contain tow process recognition and verification. In the recognition process we use the K nearest-neighbours classifier and in the verification process we use the neural network classifier.

Online Signature Classification and its Verification System

Abstract: This work presents experimental results on online recognition of handwritten signature. The system makes use of dynamic data such as trajectory, pen velocity, pen pressure, pen azimuth, and pen altitude collected at the time of signing. In order to evaluate the effectiveness of the system several experiments are carried out. Online signature database from signature verification competition (SVC) 2004 is used during all of the tests. The first series of experiments show the classification process - the questioned signature is compared with reference samples and the destination class is determined from the most similar reference. The second part involves verification - the questioned signature is recognized as belonging to a particular individual when the distance between the questioned and individual's reference signature is below the threshold level.

Cross-validation for graph matching based Offline Signature Verification

Abstract: Biometric is an authentication system that identifies a person depending on his physiological or behavioral traits. Signature verification is a socially accepted biometric method and is widely used for banking transactions. In this paper, we propose Cross-validation for Graph Matching based Offline Signature Verification (CGMOSV) algorithm. Database signatures are preprocessed in which signature extraction method is used to obtain high resolution for smaller normalization box. The dissimilarity measure between two signatures in the database is determined by (i) constructing a bipartite graph G, (ii) obtaining complete matching in G and (iii) finding minimum Euclidean distance by Hungarian method. We use Cross-validation principle to select reference signatures from which an optimum decision threshold value is determined. The given test signature is pre-processed and a test feature is extracted from it, which is then compared with the threshold value to authenticate the test signature. It is observed that our algorithm gives better Equal Error Rate (EER) for skilled forgeries and random forgeries compared to the existing algorithm.

Biometric signature verification using pen position, time, velocity and pressure parameters

Abstract: Kertas kerja ini menerangkan tentang pembangunan satu sistem pengesahan tandatangan bertulis tangan yang melibatkan tekanan pen terhadap laluan tandatangan, masa ketika menandatangan, profil kelajuan dan kedudukan rupa bentuk tandatangan Isyarat bertulis tangan telah diperoleh dan diolah secara berdigit menggunakan tablet Ciri utama sistem pengesahan tandatangan yang dicadangkan ialah tandatangan bertulis tangan yang dikemaskini secara dinamik, keupayaan cuba semula semasa pengesahan, kegunaan jalur terima beserta nilai ambang, pembangunan mesra pengguna berdasarkan antara muka grafik pengguna, penggunaan kaedah paksi masa sepunya dan pengesahan tandatangan menggunakan satu kelas rangkaian neural laluan hadapan berlapis Satu algoritma khusus telah diguna pakai yang dapat memberikan keputusan pengesahan dengan ketepatan yang baik serta lebih cepat Sistem telah menghasilkan kadar penolakan palsu sebesar 13% dan kadar penerimaan palsu 0% dengan pengesahan dilakukan menggunakan tandatangan palsu yang telah diciplak Kata kunci: Biometrik, penentusahan tandatangan, perolehan data, jalur terima, rangkaian neural The paper describes the development of a handwritten signature verification system incorporating pen pressure of signature path, time duration of the signing procedure, velocity profile of signature and position of signature shape The handwritten signals have been captured and digitized using a tablet The main features of the proposed signature verification system are the dynamically update of handwritten signature, retries capability in verification, application of tolerance bands and threshold values, development of user friendly Graphic User Interface, application of Common Time Axes and verification of signatures using a class of a multilayer feed-forward neural network A novel algorithm has been applied that provides the ability to produce consistent and high accuracy verification result and maintain the speed of verification The system has yielded 133% of False Reject Rate and 0% False Acceptation Rate with the verification using random forgery signatures Key words: Biometrics, signature verification, data acquisition, tolerance bands, neural network

Using the Keystrokes Dynamic for Systems of Personal Security

Abstract: This paper presents a boarding on biometric authentication through the Keystrokes Dynamics that it intends to identify a person from its habitual rhythm to type in conventional keyboard. Seven done experiments: verifying amount of prototypes, threshold, features and the variation of the choice of the times of the features vector. The results show that the use of the Keystroke Dynamics is simple and efficient for personal authentication, getting optimum resulted using 90% of the features with 4.44% FRR and 0% FAR. Keywords—Biometrics techniques, Keystroke Dynamics, pattern recognition.

Template selection for on-line signature verification

Abstract: In this paper, we propose two effective methods to perform automatic template selection where the goal is to select prototype signature templates for a user from a given set of online signatures. The first method employs a clustering strategy to choose a template set that best represents the intra-class variations, while the second method selects templates that exhibit maximum similarity with the rest of the signatures. In the experiment, two typical online signature verification have been employed, respectively based on global and local features, and the verifying results on a database Task2 of SVC2004 (First Signature Verification Competition 2004), with 20 genuine signatures and 20 skilled forgeries for each set, indicate that two proposed selection procedures as presented here results in better performance than random template selection.

Shape-Based Human Activity Recognition Using Independent Component Analysis and Hidden Markov Model

Abstract: In this paper, a novel human activity recognition method is proposed which utilizes independent components of activity shape information from image sequences and Hidden Markov Model (HMM) for recognition. Activities are represented by feature vectors from Independent Component Analysis (ICA) on video images and based on these features, recognition is achieved by trained HMMs of activities. Our recognition performance has been compared to the conventional method where Principle Component Analysis (PCA) is typically used to derive activity shape features. Our results show that superior recognition is achieved with our proposed method especially for activities (e.g., skipping) that cannot be easily recognized by the conventional method.

Dynamic signature verification with template protection using helper data

Abstract: A biometric template protection system for dynamic signature verification is presented. The approach uses auxiliary (helper) data that allows the matching with secure templates but do not provide information to a potential attacker. The performance of the proposed system is evaluated using the MCYT signature database comprising 330 users, with 25 genuine signatures and 25 skilled forgeries per user. The results show similar performance compared to the baseline unprotected system. However, the security of the proposed system against attacks to the template database is significantly higher.

A Pattern Matching Classifier for Offline Signature Verification

Abstract: Offline signature verification can be linked as a biometric classifier that categorizes a signature into two classes: genuine and forged. In this paper a contour matching algorithm is proposed that tracks the basic characteristic patterns in a sample signature and verifies it. It capitalizes on the geometrical properties of the signature and takes into account the inevitable intrapersonal variations for the user set A. The system is trained with 8 original signatures and given a test sample; verification is done by a triangle matching algorithm that validates a signature on the basis of the relative position of the critical points(minimum set of points which when provided can retrace any given signature model). Results verify the effectiveness of the proposed mechanism.

Noise robust multimodal biometric person authentication system using face, speech and signature features

Abstract: In this work, we present a multimodal biometric system using face, speech and signature features which is robust to noise. Face recognition is done using subspace, principal component analysis (PCA) and linear discriminant analysis (LDA) techniques. Speaker recognition system is built using mel frequency cepstral coefficients (MFCC) for feature extraction and vector quantization (VQ) for pattern matching. An off-line signature recognition system is built using vertical and horizontal projection profiles (VPP, HPP) and discrete cosine transform (DCT) for feature extraction. A multimodal biometric database with face, speech and signature biometric features has been collected for 30 users. A multimodal biometric system is built using score level fusion. Sum rule was used for the fusion of the biometric scores. Experimental results show the efficacy of the multimodal biometric system when the biometric data is affected by noise.