Joseph Shelton

Genetic based LBP feature extraction and selection for facial recognition

This paper presents a novel approach to LBP feature extraction. Unlike other LBP feature extraction methods, we evolve the number, position, and the size of the areas of feature extraction. The approach described in this paper also attempts to minimize the number of areas as well as the size in an effort to reduce the total number of features needed for LBP-based face recognition. In addition to reducing the number of features by 63%, our approach also increases recognition accuracy from an average of 99.04% to 99.84%.

Multispectral iris recognition utilizing hough transform and modified LBP.

This paper presents a multispectral iris recognition scheme using Circular Hough Transform (CHT) and a modified Local Binary Pattern (mLBP) feature extraction technique. The CHT is used to localize the iris regions from the multispectral iris images. We also apply the binary thresholding and edge detection techniques in an effort to reduce the effects of over and under segmentation in multispectral iris images in which iris and pupil boundaries are not clearly separable. Furthermore, we apply mLBP in an attempt to elicit the iris feature elements. The mLBP technique combines both the sign and magnitude features for the improvement of iris texture classification performance. The identification and verification performance of the proposed scheme is validated using a multispectral iris dataset of 3120 images.

Genetic & Evolutionary Biometric Security: Disposable Feature Extractors for Mitigating Biometric Replay Attacks

Abstract Biometric-based access control systems (BACSs) are vulnerable to replay attacks. Replay attacks occur when a biometric template is intercepted and maliciously used to gain unauthorized access to a system. In this paper, we introduce a Genetic and Evolutionary Biometric Security (GEBS) application which uses a Genetic and Evolutionary Computation to develop disposable Feature Extractors (FEs) in an effort to mitigate replay attacks. We describe how a previously developed system known as GEFE (Genetic and Evolutionary Feature Extraction) can be used to evolve unique and disposable FEs for users of BACS. Furthermore, we propose two access control protocols based on the use of disposable FEs and/or their resulting templates (also referred to as feature vectors (FVs)). In our proposed protocols, FEs/FVs are used to authenticate the identity of individuals and are then discarded. Our results show that this GEBS application can be successfully used to mitigate biometric replay attacks.

Hybrid GAs for Eigen-based facial recognition

In this paper, we have performed an evaluation of genetic-based feature selection and weighting on the PCA-based face recognition. This work highlights the first attempt of applying Genetic Algorithm (GA) based feature selection on the Eigenface method. The results show that genetic-based feature selection reduces the number of features needed by approximately 50% while improving the identification accuracy over the baseline. Genetic-based feature weighting significantly improves the accuracy from an 87.14% to a 92.5% correct recognition rate.

Fly Wing Biometrics Using Modified Local Binary Pattern, SVMs and Random Forest

This paper presents an efficient approach for classification of the gender of a common fruit fly, Drosophila melanogaster, based on their wings texture. The novelty of this research effort is that a Modified Local Binary Pattern (MLBP), which combines both the sign and magnitude features for the improvement of fly wings texture classification performance, is applied. The extracted features are then used to classify the gender of the fruit fly by using the Support Vector Machines (SVMs) and Random Forest (RF). We validate the performance of the proposed scheme on two fly wing datasets. The highest accuracy achieved by the proposed approach is 94%. In this paper, we limit our approach to gender classification; however, this effort can be extended to explore important characteristics of a fly using wings texture analysis.

A comparison of genetic feature selection and weighting techniques for multi-biometric recognition

In this paper, we compare genetic-based feature selection (GEFeS) and weighting (GEFeW) techniques for multi-biometric recognition using face and periocular biometric modalities. Our results show that fusing face and periocular features outperforms face-only and periocular-only biometric recognition. Of the two genetic-based approaches, GEFeW outperforms GEFeS.

Multibiometric system using fuzzy level set, and genetic and evolutionary feature extraction

This study presents a multimodal system that optimises and integrates the iris and face features based on fusion at the score level. The proposed multibiometric system has two novelties as compared with the previous work. First, the authors deploy a fuzzy C-means clustering with level set (FCMLS) method in an effort to localise the non-ideal iris images accurately. The FCMLS method incorporates the spatial information into the level set (LS)-based curve evolution approach and regularises the LS propagation locally. The proposed iris localisation scheme based on FCMLS avoids over-segmentation and performs well against blurred iris/sclera boundary. Second, genetic and evolutionary feature extraction (GEFE) is applied towards multimodal biometric recognition. GEFE uses genetic and evolutionary computation to evolve local binary pattern feature extractors to elicit distinctive features from the iris and facial images. Different weights for each modality are investigated to determine the significance of each modality. By using the FCMLS method to segment an iris image accurately, as well as using GEFE on a multibiometric dataset, the authors note improved performance of identification and verification accuracies over subjects on a unimodal dataset. More specifically, on the multimodal dataset of face and iris images, GEFE had an identification accuracy of 100%.

Permutation-based biometric authentication protocols for mitigating replay attacks

A biometric replay attack occurs when a victims biometric information (in the form of a template) is stolen by a hacker as it is transmitted over a network and used by the hacker to impersonate the victim to gain unauthorized access. Biometric replay attacks can be particularly devastating because the victims of these attacks cannot easily alter their biometrics or the templates associated with their biometrics [1]. In an effort to mitigate biometric replay attacks, the authors of [2] proposed two biometric authentication protocols. These protocols are based on two principles: (a) it is possible to evolve a set of distinct feature extractors (FEs) and (b) distinct FEs produce distinct templates. These principles gave rise to the concept of disposable FEs (and templates). In this paper, we introduce two additional protocols based on disposable FEs and templates. Our results show that these new protocols can be used more efficiently than the two proposed in [2].

Iris Recognition Using Fuzzy Level Set and GEFE

—This paper presents an efficient algorithm for iris recognition using the spatial fuzzy clustering with level set method, and genetic and evolutionary feature extraction techniques. The novelty of this research effort is that we deploy a fuzzy c-means clustering with level set (FCMLS) method in an effort to localize the nonideal iris images accurately. The FCMLS method incorporates the spatial information into the level set-based curve evolution approach and regularizes the level set propagation locally. The proposed iris localization scheme based on FCMLS avoids the over-segmentation and performs well against blurred iris/sclera boundary. Furthermore, we apply a genetic and evolutionary feature extraction (GEFE) technique, which uses genetic and evolutionary computation to evolve modified local binary pattern (MLBP) feature extractor to elicit the distinctive features from the unwrapped iris images. The MLBP algorithm combines the sign and magnitude features for the improvement of iris texture classification performance. The identification and verification performance of the proposed scheme is validated using the CASIA version 3 interval dataset.

Genetic and evolutionary methods for biometric feature reduction

In this paper, we investigate the use of Genetic and Evolutionary Computations (GECs) for feature selection (GEFeS), weighting (GEFeW), and hybrid weighting/selection (GEFeWS) in an attempt to increase recognition accuracy as well as reduce the number of features needed for biometric recognition. These GEC-based methods were first applied to a subset of 105 subjects taken from the Facial Recognition Grand Challenge (FRGC) dataset (FRGC-105) where several feature masks were evolved. The resulting feature masks were then tested on a larger subset taken from the FRGC dataset (FRGC-209) in an effort to investigate how well they generalise to unseen subjects. The results suggest that our GEC-based methods are effective in increasing the recognition accuracy and reducing the features needed for recognition. In addition, the evolved FRGC-105 feature masks generalised well on the unseen subjects within the FRGC-209 dataset.