Showing papers on "Periocular Region published in 2014"

Subspace-Based Discrete Transform Encoded Local Binary Patterns Representations for Robust Periocular Matching on NIST’s Face Recognition Grand Challenge

Abstract: In this paper, we employ several subspace representations (principal component analysis, unsupervised discriminant projection, kernel class-dependence feature analysis, and kernel discriminant analysis) on our proposd discrete transform encoded local binary patterns (DT-LBP) to match periocular region on a large data set such as NIST's face recognition grand challenge (FRGC) ver2 database. We strictly follow FRGC Experiment 4 protocol, which involves 1-to-1 matching of 8014 uncontrolled probe periocular images to 16 028 controlled target periocular images (~128 million pairwise face match comparisons). The performance of the periocular region is compared with that of full face with different illumination preprocessing schemes. The verification results on periocular region show that subspace representation on DT-LBP outperforms LBP significantly and gains a giant leap from traditional subspace representation on raw pixel intensity. Additionally, our proposed approach using only the periocular region is almost as good as full face with only 2.5% reduction in verification rate at 0.1% false accept rate, yet we gain tolerance to expression, occlusion, and capability of matching partial faces in crowds. In addition, we have compared the best standalone DT-LBP descriptor with eight other state-of-the-art descriptors for facial recognition and achieved the best performance. The two general frameworks are our major contribution: 1) a general framework that employs various generative and discriminative subspace modeling techniques for DT-LBP representation and 2) a general framework that encodes discrete transforms with local binary patterns for the creation of robust descriptors.

Ocular Biometrics by Score-Level Fusion of Disparate Experts

Abstract: The concept of periocular biometrics emerged to improve the robustness of iris recognition to degraded data. Being a relatively recent topic, most of the periocular recognition algorithms work in a holistic way and apply a feature encoding/matching strategy without considering each biological component in the periocular area. This not only augments the correlation between the components in the resulting biometric signature, but also increases the sensitivity to particular data covariates. The main novelty in this paper is to propose a periocular recognition ensemble made of two disparate components: 1) one expert analyses the iris texture and exhaustively exploits the multispectral information in visible-light data and 2) another expert parameterizes the shape of eyelids and defines a surrounding dimensionless region-of-interest, from where statistics of the eyelids, eyelashes, and skin wrinkles/furrows are encoded. Both experts work on disjoint regions of the periocular area and meet three important properties. First, they produce practically independent responses, which is behind the better performance of the ensemble when compared to the best individual recognizer. Second, they do not share particularly sensitivity to any image covariate, which accounts for augmenting the robustness against degraded data. Finally, it should be stressed that we disregard information in the periocular region that can be easily forged (e.g., shape of eyebrows), which constitutes an active anticounterfeit measure. An empirical evaluation was conducted on two public data sets (FRGC and UBIRIS.v2), and points for consistent improvements in performance of the proposed ensemble over the state-of-the-art periocular recognition algorithms.

Hallucinating the Full Face from the Periocular Region via Dimensionally Weighted K-SVD

Abstract: Identifying a suspect wearing a mask (where only the suspect's periocular region is visible) is one of the toughest real-world challenges in biometrics that exist. In this paper, we present a practical method to hallucinate the full frontal face given only the periocular region of a face. This is an important problem faced in many law-enforcement applications on almost a daily basis. In such real-world situations, we only have access to the periocular region of a person's face. Unfortunately commercial matchers are unable to process these images successfully. We propose in this paper, an approach that will reconstruct the entire frontal face using just the periocular region. We empirically show that our reconstruction technique, based on a modified sparsifying dictionary learning algorithm, can effectively reconstruct faces which we show are actually very similar to the original ground-truth faces. Further, our method is open set, thus can reconstruct any face not seen in training. We show the real-world applicability of method by benchmarking face verification results using the reconstructed faces to show that they still match competitively compared to the original faces when evaluated under a large-scale face verification protocol such as NIST's FRGC protocol where over 256 million face matches are made.

Merkel cell carcinoma of the eyelid and periocular region.

Abstract: Merkel cell carcinoma (MCC) in the eyelid and periocular region can be treated surgically, in most cases, with preservation of the eye and reasonable visual function. Adjuvant radiation therapy, sentinel lymph node biopsy, and chemotherapy should be considered for MCC of the eyelid and periocular region, especially for larger tumors that are T2b or more advanced and lesions that present with regional nodal or distant metastasis.

Phase Intensive Global Pattern for periocular recognition

Abstract: Partially constrained human recognition through periocular region has emerged as a new paradigm in biometric security. This article proposes Phase Intensive Global Pattern (PIGP): a novel global feature based on variation of intensity of a pixel-neighbours with respect to different phases. The feature thus extracted is claimed to be rotation invariant and hence useful to identify human from images with face-tilt. The performance of proposed feature is experimented on UBIRISv2 database, which is a very large standard dataset with unconstrained periocular images captured under visible spectrum. The proposed work has been compared with Circular Local Binary Pattern (CLBP), and Walsh Transform, and experimentally found to yield higher accuracy, though with increased computation complexity and increased size of the feature vector.

Periocular recognition based on Gabor and Parzen PNN

Abstract: Recently periocular biometrics has drawn lot of attention of researchers and some efforts have been presented in the literature. In this paper, we propose a novel and robust approach for periocular recognition. In the approach face is detected in still face images which is then aligned and normalized. We utilized entire strip containing both the eyes as periocular region. For feature extraction, we computed the magnitude responses of the image filtered with a filter bank of complex Gabor filters. Feature dimensions are reduced by applying Direct Linear Discriminant Analysis (DLDA). The reduced feature vector is classified using Parzen Probabilistic Neural Network (PPNN). The experimental results demonstrate a promising verification and identification accuracy, also the robustness of the proposed approach is ascertained by providing comprehensive comparison with some of the well known state-of-the-art methods using publicly available face databases; MBGC v2.0, GTDB, IITK and PUT.

Segmenting the periocular region using a hierarchical graphical model fed by texture / shape information and geometrical constraints

Abstract: Using the periocular region for biometric recognition is an interesting possibility: this area of the human body is highly discriminative among subjects and relatively stable in appearance. In this paper, the main idea is that improved solutions for defining the periocular region-of-interest and better pose / gaze estimates can be obtained by segmenting (labelling) all the components in the periocular vicinity. Accordingly, we describe an integrated algorithm for labelling the periocular region, that uses a unique model to discriminate between seven components in a single-shot: iris, sclera, eyelashes, eyebrows, hair, skin and glasses. Our solution fuses texture / shape descriptors and geometrical constraints to feed a two-layered graphical model (Markov Random Field), which energy minimization provides a robust solution against uncontrolled lighting conditions and variations in subjects pose and gaze.

On identification from periocular region utilizing SIFT and SURF

Abstract: We concentrate on utilization of facial periocular region for biometric identification. Although this region has superior discriminative characteristics, as compared to mouth and nose, it has not been frequently used as an independent modality for personal identification. We employ a featurebased representation, where the associated periocular image is divided into left and right sides, and descriptor vectors are extracted from these using popular feature extraction algorithms SIFT, SURF, BRISK, ORB, and LBP. We also concatenate descriptor vectors. Utilizing FLANN and Brute Force matchers, we report recognition rates and ROC. For the periocular region image data, obtained from widely used FERET database consisting of 865 subjects, we obtain Rank-1 recognition rate of 96.8% for full frontal and different facial expressions in same session cases. We include a summary of existing methods, and show that the proposed method produces lower/comparable error rates with respect to the current state of the art.

Recognition Performance of Cross-Spectral Periocular Biometrics and Partial Face at Short and Long Standoff Distance

Abstract: Matching partial heterogeneous face images to a gallery of visible images is a challenging research problem. This scenario is motivated by a number of surveillance applications such as recognition of subjects at night or in the presence of challenging environmental conditions. Standoff distances may range from a meter to hundred meters. Our latest experiments have shown that a face recognition software recently developed in our research group can be adapted to perform cross spectral matching of partial face images. The images are encoded with Gabor Generalized Local Binary Patterns and Gabor Weber operators and matched by means of a Kullbuck-Leibler metric. Our analysis has shown that three separate face regions such as (1) eyes and nasal bridge, (2) cheeks and nasal tip, and (3) mouth and a part of the chin display similar matching performance. Furthermore, we have evaluated performance of periocular regions. For a short standoff distance of 1.5 meters and a database of 48 classes, matching a Short Wave Infrared (SWIR) periocular region against visible regions resulted in 0.7 Genuine Accept Rate (GAR) at False Accept Rate (FAR) set to 0.01. For a long standoff distance of 106 meters and a database of 48 classes, matching SWIR against visible periocular regions yielded 0.4 GAR at FAR equal to 0.1. For a short standoff distance of 1.5 meters and a database of 200 classes, matching a Medium Wave Infrared (MWIR) periocular region against visible regions resulted in 0.35 GAR at FAR set to 0.1.

Nonsurgical periocular rejuvenation: Advanced cosmetic uses of neuromodulators and fillers

Abstract: Purpose of review To review the current literature regarding aesthetic enhancement using facial neuromodulators and fillers and to present advanced techniques using facial injectables for periocular rejuvenation. Recent findings The authors provide a summary of traditional periocular locations for the injection of neuromodulators and dermal fillers. The authors also present novel and advanced techniques utilizing injectables in the periocular region. Summary Minimally invasive procedures with little-to-no recovery time are continuing to increase in popularity. Neuromodulators and hyaluronic acid gel fillers have been shown to be well tolerated and efficacious nonsurgical alternatives in periocular rejuvenation.

Periocular Granuloma Annulare: A Case Report and Review of Literature

Abstract: Granuloma annulare (GA) is a granulomatous dermatosis that rarely presents on the face and is extremely uncommon in the periocular region. We report our experience with the presentation and management of GA lesions on the eyelids of a 17-year-old girl. We performed a review of published literature and identified 13 cases of pediatric periocular GA. One additional case was identified upon review of all pediatric GA cases at the Cleveland Clinic Foundation. Review of these cases suggests that periocular GA is a benign condition that spontaneously regresses within a few months. GA nodules have a predilection for the upper eyelids. A greater incidence is noted in African American children. Awareness of the self-resolving nature of this condition can prevent unnecessary surgical excisions in affected children.

Nonsurgical Considerations for Addressing Periocular Aesthetics: A Conceptual Dimensional Approach

Abstract: The periocular region serves to frame the eyes and provides a focal point of facial aesthetics. Periocular aesthetics can be evaluated by 2-dimensional (2-D) (x,y coordinate) frontal plane considerations or by 3-dimensional (3-D) considerations, in which the z coordinate is significantly affected by volume considerations. Millimeter differences between the right and left periocular regions, particularly when viewed in the 2-D frontal plane, can result in significant asymmetry and periocular disharmony. Nonsurgical modalities in the form of fillers and toxins provide the tools for subtle aesthetic modifications in the second and third dimension in a reversible, modifiable manner. 2-D Aesthetics Two-dimensional aesthetics are a particularly important consideration in the periocular region. Asymmetry in the 2-D frontal view plane of the eyebrow, upper eyelid, and lower eyelid positions has a significant impact on periocular aesthetics. Millimeter differences in the 2-D frontal view position of the eyebrows, upper eyelid position in the form of subtle degrees of blepharoptosis or, conversely, retraction quantitated by the margin reflex distance 1 (MRD1), and lower eyelid position in the form of retraction and scleral show affect periocular symmetry and aesthetics. More complex 2-D periocular parameters can have also have an impact on periocular aesthetics. Goldberg et al 1 and Papageorgiou et al 2 have eloquently described additional parameters in the form of tarsal platform show (TPS) and brow fat span (BFS), which convey considerable importance to the judged aesthetic quality of the periocular region. All of these parameters are judged in the 2-D plane, although they are significantly affected by 3-D considerations, particularly volume (Figure 1).

Empirical evaluation of visible spectrum iris versus periocular recognition in unconstrained scenario on smartphones

Abstract: Smartphones are increasingly used as biometrie sensor for many authentication applications due to the computational ability and high resolution cameras that can be used to capture biometrie information. The objective of this paper is to assess the performance of iris versus periocular recognition for smartphones in non ideal conditions (change of illumination, highly pigmented iris, shadows on iris pattern) in real-life for verification in visible spectrum. We introduce various protocols for real-life verification scenarios using smartphones for iris and periocular recognition. Further, we also study the verification performance where enrollment and probe data originate from different smartphones. From the extensive set of experiments conducted on a publicly available smartphone database, it can be observed that the information from periocular region provides substantially good performance in terms of recognition accuracy in cross sensor and varying illumination scenarios as compared to iris under same conditions.

An efficient age-invariant face recognition

Abstract: This paper proposes an efficient face recognition system which is invariant to aging. It makes use of the periocular region of an individual. Local Binary Patterns are used to extract these local features from the enhanced periocular region. Chi square distance is used to compute similarity between two facial images. It has been tested on a publicly available, FGNET database and self scanned and created Browns database.

Fast Approximate Eyelid Detection for Periocular Localization

Abstract: Iris is considered to be one of the most reliable traits and is widely used in the present state-of-the-art biometric systems. However, iris recognition fails for unconstrained image acquisition. More precisely, the system cannot properly localize the iris from low quality noisy unconstrained image, and hence, the successive modules of biometric system fails. To achieve recognition from unconstrained iris images, the periocular region is considered. The periocular (periphery of ocular) region is proven to be a trait in itself and can serve as a biometric to recognize human, though with a lower accuracy compared to iris. In this paper, we propose a novel technique to localize periocular region on the basis of eyelid information extracted from eye image. The proposed method will perform periocular localization successfully even when iris detection fails. Our method detects the horizontal edges as eyelids and the rough map of eyelids gives the radius of iris, which is used to anthropometrically derive the periocular region. The proposed method has been validated on standard publicly available databases : UBIRISv1 and UBIRISv2, and is found to be satisfactory.