International Journal of Biometrics (11 papers in press)
On the performance Improvement of Non-Cooperative Iris Biometrics using Segmentation and Feature Selection Techniques
by Alice Nithya, Lakshmi C
Abstract: In this work, an improved segmentation methodology and a novel statistical dependency based backward feature selection algorithm are proposed. From the input eye image, iris boundary is identified using Circular Hough Transform. A bounding box is defined using the radius obtained followed by iterative thresholding techniques to eliminate specular reflections, eyelids, eyelashes and pupil region. First-order and second-order statistical features are extracted from the segmented iris. For the first time, the statistical measure, Chi-Square value is computed from GLCM as a new novel feature from iris images. Statistical dependency based backward feature selection (SDBFS) algorithm is used to reduce the feature vector size. By operating on local features in reduced search space, computation complexity of segmentation is reduced with less mislocalization count and eliminates pupil dilation effects. Results of SDBFS show the usefulness of minimal-useful features. Experimental results conducted on CASIA V1, V3-Interval and UBIRIS V1 datasets show that statistical features in non-ideal iris images outperform some of the state-of-the-art methods.
Keywords: Iris Recognition; Circular Hough Transform; GLCM; Backward Feature Selection; Chi-Square Value; Segmentation; Statistical Dependency.
Human Age Classification using Appearance and Facial Skin Ageing Features with Multi-class Support Vector Machine
by Jayant Jagtap, Manesh Kokare
Abstract: Human age classification via face images is not only difficult for human being but also challenging for a machine. But, because of potential applications in the field of computer vision this topic has attracted attention of many researchers. In this paper, a novel two stage age classification framework based on appearance and facial skin ageing features with Multi-class Support Vector Machine (M-SVM) is proposed to classify the face images into seven age groups. Appearance features consist of shape features such as, geometric ratios and face angle, and facial skin textural features extracted by using Local Gabor Binary Pattern Histogram (LGBPH). Facial skin ageing features consist of facial skin textural features and wrinkle analysis. The proposed age classification framework is trained and tested with face images collected from FG-NET ageing database and PAL face database, and achieved greatly improved age classification
accuracy of 94.45%.
Keywords: Appearance features; Facial skin ageing features;Multi-class Support Vector Machine (M-SVM); Local Gabor Binary Pattern Histogram (LGBPH); Wrinkle analysis; Age classification framework.
Bone- and Air-Conduction Speech Combination method for Speaker Recognition
by Satoru Tsuge, Shingo Kuroiwa
Abstract: In this paper, first, we report speaker recognition performance using
bone-conduction speech based on an i-vector-based speaker recognition system,
which is the current state-of-the-art method. In addition, we propose three speaker
recognition methods combining bone-conduction speech and air-conduction
speech: a feature combination method, a speaker model combination method,
and a similarity score combination method. To evaluate the proposed methods,
we conducted speaker recognition experiments using a part of a large speech
corpus constructed by the National Research Institute of Police Science, Japan.
Experimental results show the bone-conduction speech performs almost the
same as the air-conduction speech when the enrollment data and evaluation data
are collected in the same session. In addition, all proposed methods improved
the speaker recognition performance of air- and bone-conduction speech in the
experiments. From these results, we conclude that fusing air- and bone-conduction
speech improves the speaker recognition performance.
Keywords: Speaker recognition; Bone-conduction speech; Air-conduction speech; i-vector; Speech processing.
A novel discriminant multiscale representation for ear recognition
by Doghmane Hakim, Abdelhani Boukrouche, Larbi Boubchir
Abstract: This paper proposes a novel representation for ear recognition. It introduces a new alternative of binarized statistical image features based on multiscale framework. The proposed representation allows capturing the image content at multiple resolutions. The recognition accuracy can be enhanced by the following steps. First, for a given ear image, a set of multiscale response images are derived from the Bank of Binarized Statistical Image Features (B-BSIF) filter. Second, the obtained response images are summarized by concatenating their histograms, which are obtained at each scale. Finally, a discriminative ear image representation is build by projecting the above mentioned histograms into a linear discriminant analysis subspace.
The proposed representation is applied on three public databases: IIT Delhi-1, IIT Delhi-2 and USTB. The obtained recognition accuracy confirms its performance than the recent existing methods.
Keywords: Ear recognition; Binarized statistical image feature; multiresolution analysis; k-NN; LDA.
A Survey on Different Continuous Authentication Systems
by Ayeswarya S, Jasmine Norman
Abstract: There has been significant research in the provision of trustworthy initial login user authentication, however, there is still a need for continuous authentication during a user session. Most mobile devices and computer systems authenticate a user only at the initial login session and do not take steps to recognize whether the present user is still the initial authorized user, an alternate user or an intruder pretending to be a valid user. Therefore, a system to check the identity of the user continuously throughout the whole session is necessary. To ensure the authenticity of the user during their whole login session, a continuous user authentication mechanism is required. In this paper, an overview of different continuous authentication methods is presented along with a discussion on the merits and demerits of the available approaches. This paper also discusses the understanding of the emerging necessities and open problems in continuous user authentication system.
Keywords: Continuous Authentication; Continuous Verification; Biometrics; Data Privacy; Security.
Fingerprint Indexing via BRIEF Minutia Descriptors
by Robert Pollak, Roland Richter
Abstract: We use BRIEF binary local image descriptors as minutia descriptors for indexing of biometric fingerprint databases. Tests with varying descriptor size and parametrization are performed on a proprietary database. Compared with the speed of an implementation of conventional minutiae matching, we find that BRIEF descriptors are fast enough for database indexing. The tested descriptors outperform two other image descriptors (LBP, HoG) from recent literature with respect to matching rates and average penetration rates.
Keywords: biometrics; fingerprints; indexing; BRIEF; image descriptors.
Forensic dental biometry - a human identification system using panoramic dental radiographs based on shape of mandibular bone
by Mahroosh Banday, Ajaz Hussain Mir
Abstract: Dental biometrics is a new and growing area of forensic biometrics that uses the unique features of dental structures from dental radiographs to automatically establish a person's identity from their dental remains when the conventional biometric features are not available. In this paper, we present a new and efficient approach for identifying people, by using the structure of mandible from the panoramic dental radiographs as a biometric identifier. The system automatically segments the mandible from dental panoramic images to extract the representative feature vectors for each mandible, which are later used for matching and identification. The experimental results of the proposed system using a database of 120 ante-mortem and 90 post-mortem panoramic dental images show that the system is robust and effective in identifying individuals and exhibits a high recognition rate (RR) up to 98.79%, low equal error rate (EER) of 1.5% and a remarkable identification performance.
Keywords: odontology; forensic identification; mandible; dental radiographs; dental biometrics.
Face detection cum recognition system using novel techniques for human authentication
by A. Parivazhagan, A. Brintha Therese
Abstract: Face biometric plays a significant role in human authentication system; today in several sectors to recognise a person face biometrics are used. Still, in accuracy point of view, there is a lag in the perfect recognition system. In this work, ideas are proposed to develop novel face recognition, face detection, and face detection cum recognition system. A novel Gray-averaging technique is combined with blooming feature extraction techniques called location averaging technique and max-min comparison technique for face recognition and face detection. An existing frequency domain process DCT is also joined with this system. In this system spatial domain and frequency domain techniques are united, hence it acts as a bridge between these two techniques. The face detection cum recognition system is validated using parameters like image size, runtime, and accuracy with few face databases. This novel system is examined through five standard face databases and 300 real-life face images.
Keywords: face recognition; face detection; location averaging technique; max-min comparison; Gray-averaging technique; discrete cosine transform; feature extraction; human authentication; face biometric; face detection cum recognition.
Bidirectional aggregated features fusion from CNN for palmprint recognition
by Jianxin Zhang, Aoqi Yang, Mingli Zhang, Qiang Zhang
Abstract: In this paper, we present a novel bidirectional aggregated features representation from convolutional neural networks (CNNs) with score-level fusion for palmprint recognition. Our method adopts the vector of locally aggregated descriptors (VLAD) to encode the convolutional features from two directions, i.e., vertical and horizontal directions, to mine both the local and global descriptions of palmprint image. Then, three score-level fusion rules are respectively employed to integrate the matching scores of the bidirectional features. We extensively evaluate the performance of convolutional features, vertical and horizontal encoding together with the score-level fusion rules through recent deep network VGG-F on the PolyU palmprint and multispectral palmprint databases. Experiments demonstrate that horizontal encoding significantly outperforms vertical encoding on red, green, blue and near-infrared (NIR) palmprint image subsets while it is slightly worse on PolyU palmprint database, moreover, the effective performance improvement can be achieved after the fusions.
Keywords: convolutional neural network; CNN; VLAD; bidirectional features; score-level fusion; palmprint recognition.
Fusing iris and periocular recognition using discrete orthogonal moment-based invariant feature-set
by Bineet Kaur, Sukhwinder Singh, Jagdish Kumar
Abstract: Iris recognition in uncontrolled environment poses a challenge due to occlusion noise, specular reflections and poor resolution. Therefore, periocular recognition has become a popular biometric modality which when used with iris recognition makes the system suitable for high security applications. The paper introduces discrete orthogonal moment-based invariant features: Tchebichef, Krawtchouk and Dual-Hahn moments which provide discriminative features with compact information and minimum redundancy for non-ideal conditions. The proposed techniques are applied on two publicly available iris databases: IITD v1 and UBIRIS v2 and our own PEC, Chandigarh periocular database. Results demonstrate that the moment-based feature-set outperforms existing approaches available in the literature.
Keywords: biometrics; Dual-Hahn moments; iris recognition; Krawtchouk moments; orthogonal moments; periocular recognition; Tchebichef moments.
Fusion of hand-shape and palm-print traits using morphology for bi-modal biometric authentication
by Wen-Shiung Chen, Wei-Chang Wang
Abstract: This paper presents a bimodal biometric recognition technique fusing hand-shape and palm-print traits of a human hand for personal authentication. In this fusion scheme, a novel feature extraction based on morphology, called broken mirror method, is designed and two-stage recognition is proposed. We utilise the image morphology and concept of Voronoi diagram to slice the image of the front of the whole palm into several strips in which each strip is then decomposed into irregular blocks in accordance with the hand geometry. Furthermore, statistic characteristics of the grey level in each of the blocks are employed as feature values. In the final stage, a coarse recognition followed by a fine recognition will be adopted to recognise the identity. The experimental results show that the proposed biometric fusion system has an encouraging performance on recognition. The false acceptance rate (FAR) and false rejection rate (FRR) are reduced efficiently down to 0.0035% and 5.7692%, respectively. Our approach achieves the EER of about 7% which is better than that of other methods.
Keywords: personal (identity) authentication; biometric recognition; multimodal biometrics; bimodal; handshape; palm-print; morphology.