Philip E. Miller

Bio: Philip E. Miller is an academic researcher from Clemson University. The author has contributed to research in topics: Periocular Region & Biometrics. The author has an hindex of 11, co-authored 13 publications receiving 828 citations.

On the Fusion of Periocular and Iris Biometrics in Non-ideal Imagery

Abstract: Human recognition based on the iris biometric is severely impacted when encountering non-ideal images of the eye characterized by occluded irises, motion and spatial blur, poor contrast, and illumination artifacts. This paper discusses the use of the periocular region surrounding the iris, along with the iris texture patterns, in order to improve the overall recognition performance in such images. Periocular texture is extracted from a small, fixed region of the skin surrounding the eye. Experiments on the images extracted from the Near Infra-Red (NIR) face videos of the Multi Biometric Grand Challenge (MBGC) dataset demonstrate that valuable information is contained in the periocular region and it can be fused with the iris texture to improve the overall identification accuracy in non-ideal situations.

Periocular region appearance cues for biometric identification

Abstract: We evaluate the utility of the periocular region appearance cues for biometric identification. Even though periocular region is considered to be a highly discriminative part of a face, its utility as an independent modality or as a soft biometric is still an open ended question. It is our goal to establish a performance metric for the periocular region features so that their potential use in conjunction with iris or face can be evaluated. In this approach, we employ the local appearance based feature representation, where the image is divided into spatially salient patches, and histograms of texture and color are computed for each patch. The images are matched by computing the distance between the corresponding feature representations using various distance metrics. We report recognition results on images captured in the visible and near-infrared (NIR) spectrum. For the color periocular region data consisting of about 410 subjects and the NIR images of 85 subjects, we obtain the Rank-1 recognition rate of 91% and 87% respectively. Furthermore, we also demonstrate that recognition performance of the periocular region images is comparable to that of face.

Personal identification using periocular skin texture

Abstract: In this paper, we propose the use of periocular skin texture as a biometric modality. Salient skin texture features are extracted and represented using Local Binary Patterns (LBPs). Matching is performed using CityBlock distance as a measure of similarity. We investigate the use of each periocular region separately in addition to their use in conjunction. Verification and identification experiments involving over 400 subjects were performed using a datasets constructed from the FRGC and FERET datasets. Reported recognition rates of nearly 90%, demonstrate the effectiveness of this novel technique.

Soft biometric classification using periocular region features

Abstract: With periocular biometrics gaining attention recently, the goal of this paper is to investigate the effectiveness of local appearance features extracted from the periocular region images for soft biometrie classification. We extract gender and ethnicity information from the periocular region images using grayscale pixel intensities and periocular texture computed by Local Binary Patterns as our features and a SVM classifier. Results are presented on the visible spectrum periocular images obtained from the FRGC face dataset. For 4232 periocular images of 404 subjects, we obtain a baseline gender and ethnicity classification accuracy of 93% and 91%, respectively, using 5-fold cross validation. Furthermore, we show that fusion of the soft biometrie information obtained from our classification approach with the texture based periocular recognition approach results in an overall performance improvement.

Genetic-Based Type II Feature Extraction for Periocular Biometric Recognition: Less is More

Abstract: Given an image from a biometric sensor, it is important for the feature extraction module to extract an original set of features that can be used for identity recognition. This form of feature extraction has been referred to as Type I feature extraction. For some biometric systems, Type I feature extraction is used exclusively. However, a second form of feature extraction does exist and is concerned with optimizing/minimizing the original feature set given by a Type I feature extraction method. This second form of feature extraction has been referred to as Type II feature extraction (feature selection). In this paper, we present a genetic-based Type II feature extraction system, referred to as GEFE (Genetic & Evolutionary Feature Extraction), for optimizing the feature sets returned by Loocal Binary Pattern Type I feature extraction for periocular biometric recognition. Our results show that not only does GEFE dramatically reduce the number of features needed but the evolved features sets also have higher recognition rates.

Periocular Biometrics in the Visible Spectrum

Abstract: The term periocular refers to the facial region in the immediate vicinity of the eye. Acquisition of the periocular biometric is expected to require less subject cooperation while permitting a larger depth of field compared to traditional ocular biometric traits (viz., iris, retina, and sclera). In this work, we study the feasibility of using the periocular region as a biometric trait. Global and local information are extracted from the periocular region using texture and point operators resulting in a feature set for representing and matching this region. A number of aspects are studied in this work, including the 1) effectiveness of incorporating the eyebrows, 2) use of side information (left or right) in matching, 3) manual versus automatic segmentation schemes, 4) local versus global feature extraction schemes, 5) fusion of face and periocular biometrics, 6) use of the periocular biometric in partially occluded face images, 7) effect of disguising the eyebrows, 8) effect of pose variation and occlusion, 9) effect of masking the iris and eye region, and 10) effect of template aging on matching performance. Experimental results show a rank-one recognition accuracy of 87.32% using 1136 probe and 1136 gallery periocular images taken from 568 different subjects (2 images/subject) in the Face Recognition Grand Challenge (version 2.0) database with the fusion of three different matchers.

Deep Learning for Biometrics: A Survey

Abstract: In the recent past, deep learning methods have demonstrated remarkable success for supervised learning tasks in multiple domains including computer vision, natural language processing, and speech processing. In this article, we investigate the impact of deep learning in the field of biometrics, given its success in other domains. Since biometrics deals with identifying people by using their characteristics, it primarily involves supervised learning and can leverage the success of deep learning in other related domains. In this article, we survey 100 different approaches that explore deep learning for recognizing individuals using various biometric modalities. We find that most deep learning research in biometrics has been focused on face and speaker recognition. Based on inferences from these approaches, we discuss how deep learning methods can benefit the field of biometrics and the potential gaps that deep learning approaches need to address for real-world biometric applications.

Adversarial Attacks Against Medical Deep Learning Systems

Abstract: The discovery of adversarial examples has raised concerns about the practical deployment of deep learning systems. In this paper, we demonstrate that adversarial examples are capable of manipulating deep learning systems across three clinical domains. For each of our representative medical deep learning classifiers, both white and black box attacks were highly successful. Our models are representative of the current state of the art in medical computer vision and, in some cases, directly reflect architectures already seeing deployment in real world clinical settings. In addition to the technical contribution of our paper, we synthesize a large body of knowledge about the healthcare system to argue that medicine may be uniquely susceptible to adversarial attacks, both in terms of monetary incentives and technical vulnerability. To this end, we outline the healthcare economy and the incentives it creates for fraud and provide concrete examples of how and why such attacks could be realistically carried out. We urge practitioners to be aware of current vulnerabilities when deploying deep learning systems in clinical settings, and encourage the machine learning community to further investigate the domain-specific characteristics of medical learning systems.

Towards Online Iris and Periocular Recognition Under Relaxed Imaging Constraints

Abstract: Online iris recognition using distantly acquired images in a less imaging constrained environment requires the development of a efficient iris segmentation approach and recognition strategy that can exploit multiple features available for the potential identification. This paper presents an effective solution toward addressing such a problem. The developed iris segmentation approach exploits a random walker algorithm to efficiently estimate coarsely segmented iris images. These coarsely segmented iris images are postprocessed using a sequence of operations that can effectively improve the segmentation accuracy. The robustness of the proposed iris segmentation approach is ascertained by providing comparison with other state-of-the-art algorithms using publicly available UBIRIS.v2, FRGC, and CASIA.v4-distance databases. Our experimental results achieve improvement of 9.5%, 4.3%, and 25.7% in the average segmentation accuracy, respectively, for the UBIRIS.v2, FRGC, and CASIA.v4-distance databases, as compared with most competing approaches. We also exploit the simultaneously extracted periocular features to achieve significant performance improvement. The joint segmentation and combination strategy suggest promising results and achieve average improvement of 132.3%, 7.45%, and 17.5% in the recognition performance, respectively, from the UBIRIS.v2, FRGC, and CASIA.v4-distance databases, as compared with the related competing approaches.