International Journal of Biometrics (12 papers in press)
- Phoneme dependent inter-session variability reduction for speaker verification
by Haoze Lu, Wenbin Zhang, Yasuo Horiuchi, Shingo Kuroiwa
Abstract: GMM-UBM super-vectors will potentially lead to worse modeling for speaker verification due to the inter-session variability, especially when a small amount of training utterances were available. In this study, we propose a phoneme dependent method to suppress the inter-session variability. A speakers model can be represented by several various phoneme Gaussian mixture models. Each of them covers an individual phoneme whose inter-session variability can be constrained in an inter-session independent subspace constructed by Principal Component Analysis (PCA), and it uses corpus uttered by a single speaker that has been recorded over a long period. SVM-based experiments performed using a large corpus, constructed by the National Research Institute of Police Science (NRIPS) to evaluate Japanese speaker recognition, demonstrate the improvements gained from the proposed method.
Keywords: Inter-session variability;phoneme;speaker verification;principal component analysis
- Biometric Signature Verification
by Suraiya Jabin, Farhana Javed Zareen
Abstract: In recent years, biometric signature verification (BSV) has been considered with renewed interest with increasing need of security and individual verification and authentication whether in banks, offices, institutions or other commercial organizations. Biometric signature verification is a behavioural biometric technique as a signature signifies unique behaviour of an individual. Biometric individual authentication has become a new and growing trend. It has truly become a necessity in modern organizations and businesses, as password and token based security systems have failed mournfully against the increasing vehemence of cyber attacks. It has also overcome the need of the physical presence of the person at the counters. It can upgrade online banking using online digital systems for signing which cannot be altered or manipulated. Digital signature pads use algorithms to record the features of the signature, which is used to authenticate a signer during a transaction. A number of government and private firms have been shifting to this technology lately also individuals using an iphone. This paper aims to present a comprehensive literature survey of the most recent research papers on biometric signature verification. It highlights the most important methods and addresses variations in the methods and features that are being taken up in the most recent research in this field along with the possible extensions.
Keywords: Biometric individual authentication, Signature verification, Feature extraction, Pattern recognition, Machine Learning, Security, Online-Signature
- Fast Match-on-Card technique using In-Matcher Clustering with ISO Minutia Template
by Tai-Pang Chen, Wei-Yun Yau, Xudong Jiang
Abstract: Fingerprint match-on-card is receiving more attention from government and the IT industry as it provides higher level of security. In addition, it also has less privacy concern as the enrolled template does not leave the card. To address the interoperability needs for match-on-card implementation, the ISO standard ISO/IEC19794-2, defines the finger minutiae data format that contains only the basic information for matching. However, with such limited basic information, fingerprint matching is a challenge for match-on-card with limited processing power, especially when dealing with deformation and common correspondence for alignment. In this paper, a novel in-matcher clustering method is proposed to search for the matched clusters of minutiae with the least deformation error. The proposed clustering method solves the deformation and alignment problems. However, matched minutia clusters may contain false or missing minutiae which may cause mismatch in some regions between the genuine user and imposter. Such mismatch may result in false acceptance. To alleviate this problem, a further matching step using Mahalanobis distance to measure the inter-cluster similarity is proposed to remove the wrongly matched clusters. Finally, the overall match score is generated by combining the minutia matching (local matching) in group (cluster) and the matching of the geometrical structure between groups (global matching). The proposed algorithm achieved an average EER<=5.1979% using all FVC databases (except FVC2006 DB1a). In the NIST evaluation, the achieved False Match Rate (FMR) = 0.001 and False Non-Match Rate (FNMR) = 0.08 (average across minutiae detectors of different vendors) and the average on-card verification time is 1.01s using 8-bit native smartcard running at 25MHz with 5K RAM.
Keywords: Fingerprint; biometric comparison; minutiae matching; in-matcher clustering; inter-cluster similarity; smartcard.
- Local Texture Description Framework based Modified Local Directional Number Pattern: A new descriptor for Face Recognition
by R. Reena Rose, Suruliandi Aandavar, Meena Nandhini
Abstract: Texture descriptors effectively capture the surface property of images. However, almost all the available local texture descriptors encode a texture pattern using the closest neighbors. But the Local Texture Description Framework (LTDF) proposed earlier proved the importance of eight sampling points that lie elliptically at a certain distance apart from a pixel under consideration in distinguishing different face images. Recently, a local texture descriptor namely Local Directional Number Pattern (LDN) is introduced to encode the directional information of the structure of a faces texture. Incorporating the concepts of LTDF and LDN, this paper proposes a new texture descriptor namely LTDF based Modified Local Directional Number Pattern (LTDF_MLDN). LTDF_MLDN describes a texture pattern with the sampling points at dissimilar area. Effectiveness of the system is tested for the different issues in face recognition using five benchmark databases. Experimental results reveal the effectiveness of the proposed descriptor over the state-of-the-art approaches.
Keywords: Texture Descriptors, Local Texture Description Framework, Modified Local Directional Number Pattern, Local Texture Description Framework based Modified Local Directional Number Pattern, Nearest Neighborhood Classifier, Chi_square distance metric
- Recognition Accuracy of the New Fingerprint Construct based on a Compact Minutiae Pattern
by Vedrana Krivokuca, Waleed Abdulla
Abstract: Instead of using the entire minutiae template to generate a protected fingerprint template, recently a non-invertible cancellable fingerprint construct based on a 3-5 minutiae Pattern was proposed as a safer alternative. This paper investigates the recognition accuracy attainable by this new fingerprint construct. It is found that using five samples of a persons reference fingerprint and allowing for a maximum of three authentication attempts provides a genuine user with the best chance of being successfully authenticated. An evaluation of the FAR and FRR in this scenario demonstrates that the new fingerprint construct can be tuned to suit the performance and security requirements of different applications by adjusting the Pattern size and matching thresholds. The fingerprint construct is then modified to improve its ability to discriminate between genuine users and impostors. Compared to other non-invertible fingerprint template protection schemes, the performance of the modified fingerprint construct is found to be favourable.
Keywords: biometrics; fingerprints; fingerprint template protection; fingerprint construct; minutiae; minutiae template; minutiae pattern; compact minutiae pattern; recognition accuracy; cancellable biometrics; non-invertible fingerprint template; non-invertibility; cancellability; diversity.
- Face recognition using a novel image representation scheme and multi-scale local features
by Qingchuan Tao, Zhiming Liu, George Bebis, Muhammad Hussain
Abstract: This paper presents a new method for improving face recognition performance under difficult conditions. The proposed method represents faces using multi-scale local features extracted from a novel representation of face images which employs color information. Specifically, past research on face recognition has shown that color information can improve recognition accuracy and robustness. Instead of using the primary colors, R, G, andrnB, a new image representation scheme is proposed which is derived from the YCrQ color space using Principal Component Analysis (PCA) followed by Fisher Linear Discriminant Analysis (FLDA). Multi-scale local features are used for face representation which are computed by extracting different resolution Local Binary Patterns (LBP) features from the new image representation and transforming the LBP features into the wavelet domain using Discrete Wavelet Transform (DWT) and Haar wavelets; we refer to this new type of features as LBP-DWT. To optimizeface representation, a variant of Nonparametric Discriminant Analysis (NDA), called Regularized Nonparametric Discriminant Analysis (RNDA) is introduced to extract the most discriminating features from LBP-DWT. The proposed methodology has been evaluated using two challenging face databases (i.e. FERET and Multi-PIE).We report promising experimental results showing that the proposed method outperforms two state-of-the-art methods, one based on Gabor features and the other based on Sparse Representation Classification (SRC). Further improvements are reported using score-level fusion.
Keywords: Face Recognition; Local Feature; Color Information; Nonparametric Discriminant Analysis
- Efficient Palmprint identification using novel symmetry filter and alignment refinement
by Hoang Thien Van
Abstract: This paper presents a robust algorithm for line orientation code based palmprint identification in which we propose a novel symmetry filter and an efficient alignment refinement technique. The main idea of the symmetry filter is to compute the approximate magnitude of the Gabor filter based on the modified finite Radon transform (MFRAT), the so-called GMFRAT filter. The advantages of GMFRAT filters are that (1) they are capable of quickly computing orientation codes, and (2) they remarkably reduce remarkably the sizes of these features. The alignment refinement technique, which uses local orientation patterns, is also proposed to solve the problem of rotations and translations caused by an imperfect preprocessing phase. Based on our alignment refinement, the matching algorithm is designed. Experimental results obtained using the public databases of the Hong Kong Polytechnic University and the Indian Institute of Technology Delhi demonstrate the effectiveness of the proposed method.
Keywords: Palmprint Recognition; Modified Finite Radon Transform; Gabor filter; GMFRAT filter; Alignment refinement
- Approach to Cryptographic Key Generation from Fingerprint Biometrics
by Subhas Barman, Debasis Samanta, Samiran Chattopadhyay
Abstract: To ensure security during data transmission, cryptography technique
is known to be a powerful approach. In general, cryptographic keys are large
and difficult to remember. To maintain the secrecy of cryptographic key, another
level of protection such as authentication step is required. As an alternative
to this, biometric can be considered along with cryptography called cryptobiometric
system (CBS), where either access of cryptographic key is controlled
with biometric or the key is generated from biometric features. This work related
to the latter issue in CBS. In such a system, protecting the privacy and security
of the biometric data is an important concern. Further, cryptography requires key
diversification which is not possible in case of biometric as it is inherent for a user. A way out, cancelable transformation of biometric prior to cryptography is
known. In this paper, we propose an approach to generate cryptographic key from
cancelable fingerprint templates (CT ) of sender and receiver for the enhancement
of network security. Both sender and receiver exchange their CT s with each other
and generate the cryptographic key at their ends using the CT s. In this approach,
CT ensures the privacy of the fingerprints and at the same time, it produces
revocable key for the application of symmetric cryptography. The between-person
variability of CT s guarantees the randomness which ensures that imposter users
are not able to generate a genuine CT to break the cryptographic key.
Keywords: Symmetric cryptography, cryptographic key generation, fingerprint,
cancelable template, network security, crypto-biometric system
- An Embedded System for Extracting Keystroke Patterns Using Pressure Sensors
by Christopher Leberknight
Abstract: The most popular biometric security technologies are fingerprint and iris recognition systems. Technologies that use these characteristics are extremely accurate because the patterns associated with an individual
Keywords: Biometrics;classification;keystroke analysis;pattern recognition;physical security;typing dynamics
- Research of Dual-Modal Decision Level Fusion for Fingerprint and Finger Vein Image
by Hui Ma
Abstract: The use of personal identity authentication systems with multi-modal biometrics has been proposed in order to increase the performance and robustness against environmental variation and fraudulent attacks. This paper presents a novel fingerprint and finger vein identity authentication system based on multi-route detection. Firstly, two classifiers are designed for fingerprint image and finger vein image respectively. Then extracted feature vectors from the first stage are then concatenated to make the third classifier. The final result is achieved by the fusion of the three classifiersâ€™ recognition results at the decision level. Experimental results show that this algorithm not only overcomes the limitations of single-modal biometrics, but also effectively improves the recognition performance of the system.
Keywords: Biometrics; Concatenated classifier; Finger vein verification; Decision level Fusion
Special Issue on: "Emerging Biometric Modalities,"
- Overview and Challenges of Palm Vein Biometric System
by Zarina Mohd Noh, Abdul Rahman Ramli, M. Iqbal Saripan, Marsyita Hanafi
Abstract: Palm vein biometric system is one of the biometric technologies that has grabbed the attention of scholarly researchers and industrial alike, due to its distinctive properties and hidden nature. Constant effort had been done in improving the palm vein biometric system performance through the design of its vein acquisition system and vein image analysis. This paper provides an overview of the underlying elements of a palm vein biometric system that summarizes the works done, and predicts the upcoming research focus in this area.
Keywords: palm vein pattern; biometric recognition; acquisition system; vein image analysis
- Multi-resolution elongated CS-LDP with Gabor Feature for Face Recognition
by Xi Chen, Fangyuan Hu, Zengli Liu, Qingsong Huang, Jiashu Zhang
Abstract: Center-symmetric local derivative pattern (CS-LDP) algorithm is proposed to describe the local second-order derivative feature of texture, However, CS-LDP can only describe second-order derivative feature of texture on four directions and lost some discriminant information on other directions. Addressing such problems, this paper proposed multi-resolution elongated CS-LDP (ME-CS-LDP) to solve such problem. By increasing the number of directions, which can be implemented by increasing the sampling points on the ellipse radius with interpolation, multi-resolution elongated CS-LDP can provide more discriminant information on more directions. Furthermore, our proposed multi-resolution elongated CS-LDP is defined in ellipse field to depict some important ellipse part of faces, like eyes and mouth. Gabor filter plus ME-CS-LDP/weighed ME-CS-LDP is used for face recognition in this paper. Experiments are carried out on the illumination subset of Yale B database，the subset of PIE illumination database and VALID face database. Experimental results have validated the effectiveness of the proposed method.
Keywords: Face recognition; Gabor filter; Multi-resolution elongated CS-LDP