Showing papers on "Periocular Region published in 2015"

Spartans : Single-Sample Periocular-Based Alignment-Robust Recognition Technique Applied to Non-Frontal Scenarios

Abstract: In this paper, we investigate a single-sample periocular-based alignment-robust face recognition technique that is pose-tolerant under unconstrained face matching scenarios. Our Spartans framework starts by utilizing one single sample per subject class, and generate new face images under a wide range of 3D rotations using the 3D generic elastic model which is both accurate and computationally economic. Then, we focus on the periocular region where the most stable and discriminant features on human faces are retained, and marginalize out the regions beyond the periocular region since they are more susceptible to expression variations and occlusions. A novel facial descriptor, high-dimensional Walsh local binary patterns, is uniformly sampled on facial images with robustness toward alignment. During the learning stage, subject-dependent advanced correlation filters are learned for pose-tolerant non-linear subspace modeling in kernel feature space followed by a coupled max-pooling mechanism which further improve the performance. Given any unconstrained unseen face image, the Spartans can produce a highly discriminative matching score, thus achieving high verification rate. We have evaluated our method on the challenging Labeled Faces in the Wild database and solidly outperformed the state-of-the-art algorithms under four evaluation protocols with a high accuracy of 89.69%, a top score among image-restricted and unsupervised protocols. The advancement of Spartans is also proven in the Face Recognition Grand Challenge and Multi-PIE databases. In addition, our learning method based on advanced correlation filters is much more effective, in terms of learning subject-dependent pose-tolerant subspaces, compared with many well-established subspace methods in both linear and non-linear cases.

Probabilistic Deformation Models for Challenging Periocular Image Verification

Abstract: The periocular region as a biometric trait has recently gained considerable traction, especially under challenging scenarios where reliable iris information is not available for human authentication. In this paper, we consider the problem of one-to-one (1 : 1) matching of highly nonideal periocular images captured in-the-wild under unconstrained imaging conditions. Such images exhibit considerable appearance variations, including nonuniform illumination variations, motion and defocus blur, off-axis gaze, and nonstationary pattern deformations. To address these challenges, we propose periocular probabilistic deformation models (PPDMs) that: 1) reduce the image matching problem to matching local image regions and 2) approximate the periocular distortions by local patch level spatial translations whose relationships are modeled by a Gaussian Markov random field. Given a periocular image pair, we determine the distortion-tolerant similarity metric by regularizing local match scores by the maximum a posteriori probability estimate of the relative local deformations between them. Unlike the existing global periocular image matching techniques, by accounting for local image deformations in the periocular matching process, PPDM exhibits greater tolerance to pattern variations. We demonstrate the effectiveness of our model via extensive evaluation on a large number of in-the-wild periocular images. We find that PPDMs outperform many benchmark 1 : 1 image matching techniques (improving verification rates at 0.1% false accept rate by ${\sim }30$ % over previous work and ${\sim }40$ % when compared with the best baseline) in challenging scenarios leading to state-of-the-art verification performance on multiple real-world periocular data sets.

Periocular biometrics in mobile environment

Abstract: In this work we study periocular biometrics in a challenging scenario: a mobile environment, where person recognition can take place on a mobile device. The proposed technique, that models session variability, is evaluated for the authentication task on the MOBIO database, previously used in face recognition, and on a novel mobile biometric database named the CPqD Biometric Database, as well as compared to prior work. We show that in this particular mobile environment the periocular region is complementary to face recognition, but not superior, unlike shown in a previous study on a more controlled environment. We show also that a combination with face recognition brings a relative improvement of 7.93% in terms of HTER. Finally, the results of this paper are reproducible using an open software and a novel Web platform.

A novel imaging approach to periocular basal cell carcinoma: in vivo optical coherence tomography and histological correlates.

Abstract: Optical coherence tomography (OCT) is a non-invasive imaging method widely used in ophthalmology. Recent developments have produced OCT devices for imaging the skin. The purpose of this study was to investigate Fourier Domain OCT morphological features of periocular basal cell carcinoma (BCC) in correlation with conventional histopathology. Consecutive patients with periocular nodular BCC were prospectively examined with VivoSight OCT (Michelson Ltd) prior to surgical excision. OCT slice mode images were analysed using criteria defined for conventional and HD-OCT; the images were correlated to haematoxylin and eosin stained histology sections. A total of 15 patients with periocular BCC were recruited. Three categories of BCC morphological features were identified from slice mode OCT images: 1) Epidermal changes included epidermal thinning (15/15; 100%), ulceration and crusting (5/15, 33.3%) and decreased density of hair follicles (8/15; 53.3%); 2) Intralesional features included hyporeflective nodules (15/15; 100%), hyper-reflective edges (15/15; 100%) and hyporeflective central necrosis (3/15; 20%) 3) Perilesional features included hyporeflective borders (11/15; 73%), hypereflective margins (15/15; 100%) and dilated blood vessels (5/15; 33%). This study demonstrated that Fourier Domain OCT imaging offers additional information in the identification of morphological features of nodular BCC compared to conventional OCT diagnostic criteria. VivoSight produced fast, non-invasive imaging of skin lesions in the periocular region and high correlation with histology. Further studies are necessary to investigate OCT features of different histological subtypes of BCC.

Retrospective Study of Periocular Non Melanoma Skin Cancer Treated with the Combination of IFN alpha2b and Gamma (HeberPAG)

Abstract: Background: Non-melanoma skin cancer can cause considerable morbidity when located on the eyelids and periocular skin. Basal cell carcinoma is the commonest periocular malignancy and although metastases are extremely rare, local invasion can cause significant and sometimes severe morbidity. Interferons may provide a nonsurgical approach to the management of these tumors. The aim of this work was to evaluate retrospectively, the effect of a formulation containing IFNs alpha2b and gamma in synergistic proportions (HeberPAG) on patients with periocular NMSC. Methods: The patients were identified from the data base from Department of Peripheral Tumors at “National Institute of Oncology and Radiobiology” in Havana; Dermatological Department at “Hermanos Ameijeiras” and “Enrique Cabrera” Hospitals; and policlinics from rural zone in Mayabeque; Cuba. The applications of IFN combination were practiced by medical doctors specialized in dermato-oncology. The employed doses for IFN combination were from 0.875 × 106 IU to 27 × 106 IU. Results: The series include 18 basal cell carcinoma and 3 squamous cell carcinoma of the skin with predominant clinical forms mixed (33.3%) and nodular (38.1%), 3 cases were terebrant, 2 ulcerated and 1 pigmented. The median time of tumor evolution was 16.5 months with an initial diameter of 8.25 cm. At week 12 after the end of treatment, a 47.6% complete response rate was obtained. A partial response was achieved in 5 patients (23.8%). A high response rate was obtained with overall response (CR+PR) in 71.4%. All patients reported at least 1 adverse event. The most frequent (>20%) were fever, chills, anorexia, cephalea, perilesional erythema and edema, asthenia, arthralgia and general discomfort. Conclusions: HeberPAG is an alternative useful to surgery in patients with periocular non-melanoma skin cancer when other therapies have failed or are not possible. The encouraging result justifies further confirmatory trials in periocular region.

Periocular pilomatrixoma: a retrospective analysis of 16 cases.

Abstract: Purpose Pilomatrixoma is a benign tumor of the hair follicle, occurring more frequently in the head and neck. There are relatively few published large case series in the ophthalmic literature. The purpose of this study was to evaluate additional case series of patients with periocular pilomatrixoma, treated in the institute from 1995 to 2011. Methods A retrospective analysis of all cases with periocular pilomatrixoma treated during 16 years was made. Data were collected regarding the age at the time of excision, gender, tumor location, tumor dimensions, suspected clinical diagnosis before biopsy, gross appearance, histopathological features, treatment, recurrence, and other syndromes related and family occurrence. Results Only 16 cases with pilomatrixoma were treated during 16 years. Most of the cases (69%) presented in the first 2 decades of life with female predilection (62.5%). The most common affected site was the upper eyelid (62.5%). All patients were asymptomatic. Various diagnoses were suspected clinically prior to surgical removal and histopathological confirmation of the tumor, and only in 18.75%, pilomatrixoma was suspected. Simple resection was carried out in all cases. No recurrence or malignant transformation was reported. Conclusion Pilomatrixoma is a relatively infrequent periocular tumor, which isn't usually recognized clinically. The findings of the current case series, which is one of the largest published thus far in the ophthalmic literature, are in concordance with the other series of pilomatrixoma, confirming the epidemiologic, clinical, and histopathological features of this tumor in the periocular region.

Person identification at a distance via ocular biometrics

Abstract: The performance of iris recognition reduces when the images are captured at a distance. However, such images generally contain periocular region which can be utilized for person recognition. In this research, we propose a novel context switching algorithm that dynamically selects the best descriptor for color iris and periocular regions. Using predefined protocols, the performance of the proposed algorithm is evaluated on UBIRIS V2 and FRGC datasets, and the results show improved performance compared to existing algorithms.

Methods and software for hallucinating facial features by prioritizing reconstruction errors

Abstract: Identifying a masked suspect is one of the toughest challenges in biometrics that exist. This is an important problem faced in many law-enforcement applications on almost a daily basis. In such situations, investigators often only have access to the periocular region of a suspect's face and, unfortunately, conventional commercial matchers are unable to process these images in such a way that the suspect can be identified. Herein, a practical method to hallucinate a full frontal face given only a periocular region of a face is presented. This approach reconstructs the entire frontal face based on an image of an individual's periocular region. By using an approach based on a modified sparsifying dictionary learning algorithm, faces can be effectively reconstructed more accurately than with conventional methods. Further, various methods presented herein are open set, and thus can reconstruct faces even if the algorithms are not specifically trained using those faces.

Combining 3D and 2D for less constrained periocular recognition

Abstract: Periocular recognition has recently become an active topic in biometrics. Typically it uses 2D image data of the periocular region. This paper is the first description of combining 3D shape structure with 2D texture. A simple and effective technique using iterative closest point (ICP) was applied for 3D periocular region matching. It proved its strength for relatively unconstrained eye region capture, and does not require any training. Local binary patterns (LBP) were applied for 2D image based periocular matching. The two modalities were combined at the score-level. This approach was evaluated using the Bosphorus 3D face database, which contains large variations in facial expressions, head poses and occlusions. The rank-1 accuracy achieved from the 3D data (80%) was better than that for 2D (58%), and the best accuracy (83%) was achieved by fusing the two types of data. This suggests that significant improvements to periocular recognition systems could be achieved using the 3D structure information that is now available from small and inexpensive sensors.

Luminate eye gel

Abstract: The present invention features novel cosmetic skin care compositions for improving the appearance of skin, particularly the periocular region.

Favre-Racouchot Disease of the Periocular Region.

Abstract: This study details the case of periocular Favre-Racouchot disease an often underdiagnosed entity with a complex differential diagnosis. This is an unusual condition that can potentially affect the periocular region; however, there is little information regarding Favre-Racouchot disease reported in the peer-reviewed ophthalmology literature. Increased awareness of Favre-Racouchot disease among ophthalmologists, oculofacial surgeons, and other specialists can lead to proper diagnosis impacting treatment options and patient outcome.

Eyelid and Periocular Skin Tumors

Abstract: Malignant skin neoplasias commonly affect the eyelids and periocular region, particularly in high UV exposure zones. Secondary orbital invasion is a serious and potentially fatal complication of cutaneous tumors. The most frequent skin tumors resulting in orbital invasion are basal cell carcinoma, squamous cell carcinoma, sebaceous gland carcinoma, and malignant melanomas. Orbital invasion from eyelid tumors usually results from a delayed presentation/diagnosis, incomplete treatment with subsequent recurrences, and highly aggressive invasive tumors.

Improving Cross-Smartphone Periocular Verification in Visible Spectrum Using Time-Frequency Features of Laplacian Decomposition

Abstract: Smartphones are gaining popularity as a biometric authentication device for many applications like banking and e-commerce. While multiple smartphone manufacturers providing phones with new features, consumers venture to try new phones or use multiple devices to sign into secure applications leading to a situation, in which they have to deal with data emerging from various smartphones along with manifold capture conditions. Recognition processes involving such cross-smartphone data leads to degraded biometric performance. In this work, we propose a novel technique to extract texture features from the periocular region by decomposing the images into Laplacian pyramids of various scales and obtain frequency responses in different orientations. Further, we propose to encode the features sparsely as a means to increase the cross-smartphone authentication using periocular region. From the extensive set of experiments conducted on a publicly available smartphone periocular database, we demonstrate the improvement using the proposed feature encoding and comparison for authentication scenarios. An average gain in Equal Error Rate of around 10 % is achieved while the best gain of 16% is obtained for various comparisons as compared to previously reported verification scores. The obtained gain in performance indicates the applicability of the proposed feature extraction technique for real-life authentication scenarios employing data from different smartphones in the visible spectrum.

Periocular localization and feature extraction for human recognition

Abstract: The advent of biometric system as a next-generation solution towards bringing social and national security to a technically-achievable scenario. This paradigm of authentication has easily taken over the classical token-based and knowledge-based systems. The last decade has seen researches claiming face and iris to be the most promising two traits. Iris produces high accuracy with extremely high-resolution near-infrared (NIR) images, and face is capable of producing moderate accuracy even from low resolution images. To bridge the gap between these two, periocular (periphery of ocular) biometric came into highlight and researchers have initially established its ability to yield accurate recognition. This thesis attempts to design a periocular biometric system. Periocular region can be considered as the region around eye where features, that can participate in uniquely identifying an individual, are existing. So, starting from eye, while moving away from eye, periocular region ranges up to the portion where the skin becomes smooth and no feature is available. Hence periocular biometric, unlike most common segmentation application, cannot be localized through edge detection. The first part of the thesis investigates to identify four trait-specific localization techniques. For achieving perfect localization, (a) conformation of the localization to human anthropometry, (b) high accuracy from a localized image, (c) conformation to human judgement, and (d) subdivision of eye portion are done. The second part concentrates to design a suitable feature extraction method for periocular biometric. The thesis presents a novel Phase Intensive Global Pattern (PIGP) which is shown to able to extract gross as well as subtle features and work well for images without rotation. The next part of the thesis incorporates and ensures scale-invariant and rotation-invariant properties into PIGP, and this modified version is termed as Phase Intensive Local Pattern (PILP). PILP is experimentally proven to work well for NIR databases as well as visual-spectrum (VS) databases. Ability of PILP to identify large number of potential keypoints and extraction of high-dimensional (128D) feature from them results into the high accurate performance of PILP. However, this type of phase-difference based keypoint detection and oriented histogram based large feature extraction is extremely time-consuming and the feature vector, being so large, invites a reduction technique to be employed. The next part of the thesis hence develops a post-reduction technique to reduce the feature vector size and thereby the matching time. Reduced PILP (R-PILP) is developed from PILP by classifying keypoints through verifying the degree of monotonic nature in them. Experiments show that R-PILP is a little less accurate than PILP but R-PILP is faster as compared. All results in the thesis have been derived on four standard publicly available databases: BATH and CASIAv3 (NIR databases), and UBIRISv2 and FERETv4 (VS databases). Comparative analysis have been made with existing landmark techniques like Circular Local Binary Pattern (CLBP), Walsh Mask, Scale Invariant Feature Transform (SIFT), and Speeded Up Robust Features (SURF). It has been observed that these features consistently work equally well on NIR databases. However, performance of existing techniques degrade rapidly when experimented on VS databases. Though the proposed techniques suffers degradation, but outperforms the existing techniques with a high margin. The localization technique, and three progressively developed features PIGP, PILP, and R-PILP complete the objective of developing the periocular biometric system.

Periocular Region-Based Biometric Identification

Abstract: As biometrics become more prevalent in society, the research area is expected to address an ever widening field of problems and conditions. Traditional biometric modalities and approaches are reaching a state of maturity, and their limits are clearly defined. Since the needs of a biometric system administrator might extend beyond those limits, new modalities and techniques must address such concerns. The goal of the work presented here is to explore the periocular region, the region surrounding the eye, and evaluate its usability and limitations in addressing these concerns. First, a study of the periocular region was performed to examine its feasibility in addressing problems that affect traditional faceand iris-based biometric systems. Second, the physical structure of the periocular region was analyzed to determine the kinds of features found there and how they influence the performance of a biometric recognition system. Third, the use of local appearance based approaches in periocular recognition was explored. Lastly, the knowledge gained from the previous experiments was used to develop a novel feature representation technique that is specific to the periocular region. This work is significant because it provides a novel analysis of the features found in the periocular region and produces a feature extraction method that resulted in higher recognition performance over traditional techniques.

Fusion of Sclera and Periocular Features for Biometric System

Abstract: This paper proposes the biometric verification system based on ocular features. We form the multimodal biometric system considering two recent biometric traits in ocular region- sclera region and periocular region. For feature extraction of sclera part we use simple technique which eliminates the expensive image enhancement process i.e Local Binary Pattern (LBP) and the matching scores are generated. For feature extraction of periocular region we use structured random projections and matching score are generated. From these matching scores the score level fusion is done with Extreme Learning Machine (ELM). This method has shown 94.40% of accuracy.