International Journal of Biometrics (10 papers in press)
- Novel Ear-Assisted 3D Face Recognition Under Expression Variations
by Paweł Krotewicz
Abstract: This paper concerns the novel region-based ear-assisted 3D face recognition based on Iterative Closest Point (ICP) algorithm in face expression changing scenario. The proposed algorithm for 3D face biometric recognition was prepared and tested. As a first contribution current state of the art in the field of 3D face recognition is presented and the main approaches to the problem are briefly described. Furthermore, all the data processing steps: preprocessing, segmentation, feature extraction and feature comparison are described in detail. As a second contribution, the algorithm behaviour is scrutinized on the DMCSv1 database and the results in the form of DET curves are highlighted in this paper. Also the comparison with results obtained my means of the algorithm neglecting ear regions is provided. It occurs that ear geometry information added to face as an auxiliary input to Iterative Closest Point can greatly improve recognition results especially in case of very strong facial expressions. Equal error rate does not exceed 6.25% on arbitrary data subset. In the last section conclusions are formulated and plans for future work are presented.
Keywords: Biometrics; Expression-Invariant Face Recognition; Biometric Identification; Contactless Identification; 3D Ear Geometry; 3D Face Geometry; Iterative Closest Point; Feature-Based System; Region-Based Method; Expression Variations
- CHALLENGING USB FINGERPRINT SCANNER SECURITY PROTOCOL: A METHODOLOGY USING CASTING AGENTS TO CAPTURE DIGIT AND LATENT RIDGE DETAIL TO ENABLE ACCESS
by Samuel McKenna, Mark Butler
Abstract: Fingerprint scanners are used as a form of control with access limited to the beholder of the ridge detail. However, to what extent these devices are capable of providing that control has not been fully explored. This study tested the reliability of a fingerprint scanner in accessing enrolled fingerprint data, when faced with the challenge of fake fingerprints. Ridge detail casts were crafted from moulds, with Gelatine and Silicone being applied as casting agents. The second stage required participants to place fingerprints on a bottle or tile; these latent impressions were subsequently powdered using Magneta Flake. Provil, a forensic casting material was applied directly onto the powder, creating simulated fingerprints from a latent print. Each of the produced fingerprints then went through a scanning process. All materials tested were able to gain access through the participants enrolled data. This suggests potential unreliability of the fingerprint scanner in storing pertinent data.
Keywords: Biometrics, fingerprints, scanner, cyber, crime, fingerprint data, identification, digital, verification, theft, cryptography, security, hacking
- Secure And Efficient Multibiometric Fusion Based Cryptosystem Using Blind Separation Encryption Algorithm
by Divya Rajalingam
Abstract: Multibiometrics is the usage of more than one physiological or behavioral characteristic to identify an individual. Multibiometrics is resilience to spoofing and has low False Acceptance Rate (FAR). However Multibiometrics requires storage of multiple biometric templates for each user which increase the risk to user privacy and system security. The existing Fuzzy logic has several limitations like non-revocability, cross matching and brute force attack. To overcome the above limitations of Fuzzy logic, Hard Fuzzy logic is proposed and implemented for the three biometric features and was simulated. Further authentication is extended to cryptosystem by making use of a novel cryptographic algorithm namely Blind Separation Encryption in which the client and server are authenticated and then the encryption is performed. Discrete Wavelet Transform (DWT) and Sparse Representation are implemented to reduce the redundant data and memory space.
Keywords: Multibiometric cryptosystem, feature level fusion, fuzzy commitment, Hard Fuzzy Logic, template security, Blind Separation Encryption, Sparse Representation.
- Multi-Level Fingerprint Continuous Classification for Large Scale Fingerprint Database Using Fractal Analysis
by Yunfei Zhong, Xiaoqi Peng
Abstract: A three-level classification method for fingerprints using fractal analysis was proposed to improve the speed, accuracy, and robustness of an automated recognition system for a large-scale fingerprint database. Low-quality fingerprints were first eliminated via an assessment algorithm with a multi-level progressive discriminant factor, thereby increasing the accuracy of fingerprint recognition. Next, three-level classification was done for fingerprints with acceptable quality. First, the fingerprints were sorted into six categories according to fingerprint types. Second, classification was made based on the number of ridge lines between the singular points of each fingerprint. Third, categorization was done in terms of the fractal dimensions of the stable-quality region of each fingerprint image. With the second and third levels of classification, continuous classification and redundancy retrieval could be achieved, thus effectively improving the accuracy and robustness of the method. The experimental results using the NIST-4 fingerprints database established that the proposed method has various advantages, including fast retrieval speeds, strong adaptability, and great robustness, making it particularly suitable for automated classification and recognition matching for large-scale fingerprint databases.
Keywords: Fractal Analysis;Box Dimension;Multi-Level Continuous Classification;Redundancy Retrieval;Large-scale Fingerprint Database
- Forensic Sketch Recognition using User Specific Facial Region
by Saurabh Singh, Madhavi Sinha
Abstract: Forensic sketches play an important role in criminal identification process. These sketches are drawn by forensic artists on the basis of the description provided by an eyewitness or victim. These sketches are publicized to get some clues to reveal the identity of the criminals. A faster way to identify the criminals is to match the forensic sketch with some government agency mug shot database. In the process of drawing a sketch, the description provided by the eyewitness often includes some unique facial details comprising the deviations from an average face. For example some spot on face, mole, scar, cuts etc. Study says that, the information which is more uncommon is more likely to be last in the memory. In this paper, we suggest a sketch to mug shot matching approach called difference vector based matching (DVBM), which utilizes deviations present in facial regions to measure the similarity between a sketch and a mug-shot image. The method is tested over a dataset containing 112 sketches and a large mug-shot gallery of 7112 images. The results generated using DVBM are compared with standard face matchers and show considerable improvement in matching accuracy.
Keywords: Biometrics; Sketch Recognition; Face Recognition; Specific Features; Image Analysis; Pattern Recognition; Dimensionality Reduction.
- A Survey of Attacks on Iris Biometric Systems
by Richa Gupta, Priti Sehgal
Abstract: Biometric recognition has several applications that provide reliable solutions to the user authentication problem. Its widespread use and popularity is itself making it prone to several vulnerabilities.
Iris is emerging as one of the most popular and accurate biometrics. Due to its inherent advantages and uniqueness, it is gaining popularity as a powerful authentication tool. However, the iris recognition systems may suffer from various attacks at different points during the authentication process. This article intends to review the popular attacks on the iris biometric, which affects its security, and present a survey on the approaches taken by various researchers to mitigate these attacks. The attacks have been divided into three categories, namely - User level, User-System interface level and Stored database attacks. We present an overview of these attacks and analyze the algorithms proposed in the literature that are usually used to secure iris biometric systems from these attacks.
Keywords: Biometrics, iris recognition, performance evaluation, liveness detection, multimodal system, template attack
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
- Multimodal Biometric Cryptosystem based on Fusion of Wavelet and Curvelet features in Robust Security Application.
by Sajeeda Mir, Yogesh Dandawate
Abstract: The authentication system used at the Automated Teller Machines (ATM) is a unique Personal Identification Number (PIN). This PIN can be easily tapped, to have a more secure transaction we propose a method wherein the PIN is replaced by the Biometrics of the individual.
Hardware is designed to capture the biometric traits such as face, fingerprint and palm vein. The captured images are enhanced and then features are extracted which are fused at feature level. Cryptography is applied to the fused feature vector. Matching is done using Euclidean distance. Palm vein is chosen as a biometric trait because it is unique and its impossible to forge the vein pattern of an individual. Curvelet Transform and Wavelet Transform are used for feature extraction. Experimental results indicate a good level of security and recognition rate of 91% and 89% is achieved when Wavelet Transform and Curvelet Transform is used as feature extraction methods respectively.
Keywords: Multimodal Biometrics, Curvelet Transform, Gabor Filter, Discrete Cosine Transform, RSA.
- Two-level Dimensionality Reduced Local Directional Pattern for Face Recognition
by Srinivasa Perumal Ramalingam, Chandra Mouli P.V.S.S.R.
Abstract: Face recognition can be done efficiently using local approaches. Local Directional Pattern (LDP) is one such approach that serves as a descriptor for face recognition. It assigns a code for each pixel and the image is encoded. Histogram binning is done on the LDP encoded image to represent the face. A two level dimensionality reduced local directional pattern (TL-DR-LDP) is proposed in this paper. The proposed TL-DR-LDP is robust in recognizing the faces with maximum recognition rate. The proposed descriptor codes the image by dividing the image into regions and for each region, a code is defined. The same process is repeated for one more level and hence named as TL-DR-LDP. At each level, the dimensions of the feature vector are drastically reduced and performance of the descriptor maintains the higher recognition rate. The proposed descriptor is tested on standard benchmark databases like FERET, Extended YALE B and ORL. The results obtained prove that the TL-DR-LDP is exemplary.
Keywords: Local Directional Pattern; Dimensionality Reduction; Face Recognition; Feature descriptor; Face descriptor; Face detection; Local patterns.