Showing papers on "Periocular Region published in 2012"

Human and Machine Performance on Periocular Biometrics Under Near-Infrared Light and Visible Light

Abstract: Periocular biometrics is the recognition of individuals based on the appearance of the region around the eye. Periocular recognition may be useful in applications where it is difficult to obtain a clear picture of an iris for iris biometrics, or a complete picture of a face for face biometrics. Previous periocular research has used either visible-light (VL) or near-infrared (NIR) light images, but no prior research has directly compared the two illuminations using images with similar resolution. We conducted an experiment in which volunteers were asked to compare pairs of periocular images. Some pairs showed images taken in VL, and some showed images taken in NIR light. Participants labeled each pair as belonging to the same person or to different people. Untrained participants with limited viewing times correctly classified VL image pairs with 88% accuracy, and NIR image pairs with 79% accuracy. For comparison, we presented pairs of iris images from the same subjects. In addition, we investigated differences between performance on light and dark eyes and relative helpfulness of various features in the periocular region under different illuminations. We calculated performance of three computer algorithms on the periocular images. Performance for humans and computers was similar.

Periocular cutaneous malignancies: a review of the literature.

Abstract: Background The periocular skin is susceptible to numerous benign and malignant neoplasms. Periocular malignancies may present differently, behave more aggressively, and pose greater challenges for treatment and repair than malignancies at other cutaneous sites. Between 5% and 10% of cutaneous malignancies occur periorbitally, with basal cell carcinoma reported as the most common malignant periocular tumor, followed by squamous cell carcinoma, sebaceous gland carcinoma, cutaneous melanoma, Merkel cell carcinoma, and other rare tumors. Objective To review the current literature on cutaneous malignancies of the periocular region pertaining to etiology, incidence, clinical presentation, differential diagnosis, complications, and treatment options. Materials and methods An extensive literature review was conducted using PubMed, searching for articles on periocular and periorbital cutaneous malignancies. Conclusions Timely diagnosis and management of periocular malignancies is essential because of their proximity to and potential to invade vital structures such as the orbit, sinuses, and brain. Surgical excision remains the standard of care for the majority of periorbital malignancies, but given the sensitive anatomic location, tissue-sparing techniques with margin control such as Mohs micrographic surgery are the preferred method for most nonmelanoma skin cancers. Depending on tumor type, other treatment modalities may include radiation, chemotherapy, cryosurgery, topical medications, and photodynamic therapy.

Unconstrained periocular biometric acquisition and recognition using COTS PTZ camera for uncooperative and non-cooperative subjects

Abstract: We propose an acquisition and recognition system based only on periocular biometric using the COTS PTZ camera to tackle the difficulty that the full face recognition approach has encountered in highly unconstrained real-world scenario, especially for capturing and recognizing uncooperative and non-cooperative subjects with expression, closed eyes, and facial occlusions. We evaluate our algorithm on the periocular region and compare that to the performance of the full face on the Compass database we have collected. The results have shown that the periocular region, when tackling unconstrained matching, is a much better choice than the full face for face recognition even with less than 2/5 the size of the full face. To be more specific, the periocular matching across all facial manners, i.e., neutral expression, smiling expression, closed eyes, and facial occlusion, is able to achieve 60.7% verification rate at 0.1% false accept rate, a 16.9% performance boost over the full face.

Method and system for automatically recognizing facial expressions via algorithmic periocular localization

Abstract: This disclosure provides a method and system for automatically recognizing facial expressions at variable resolutions of video. According to one exemplary method, facial expressions are detected, extracted and classified from a video sequence based on an automatic localization of the periocular region associated with a detected and extracted face.

Person recognition based on fusion of iris and periocular biometrics

Abstract: In this paper we proposed a novel multimodal biometric approach using iris and periocular biometrics to improve the performance of iris recognition in case of non-ideal iris images. Though iris recognition has the highest accuracy among all the available biometrics, still the noises at the image acquisition stage degrade the recognition accuracy. The periocular region can act as a supporting biometric, in case the iris is obstructed by several noises. The periocular region is the part of the face immediately surrounding the eye. The approach is based on fusion of features of iris and periocular region. The approach has shown significant improvement in the performance of iris recognition. The evaluation was done on a test database created from the images of UBIRIS V2 and CASIA iris interval database. We achieved identification accuracy upto 96 % on the test database.

Periocular Feature Extraction Based on LBP and DLDA

Abstract: Periocular recognition is an emerging field of research and people have experimented with some feature extraction techniques to extract robust and unique features from the periocular region. In this paper, we propose a novel feature extraction approach to use periocular region as a biometric trait. In this approach we first applied Local Binary Patterns (LBPs) to extract the texture information from the periocular region of the image and then applied Direct Linear Discriminant Analysis (DLDA) to produce discriminative low-dimensional feature vectors. The approach is evaluated on the UBIRIS v2 database and we achieved 94% accuracy which is a significant improvement in the performance of periocular recognition.

A prospective, multicentre study of malignant and premalignant lesions at the base of periocular cutaneous horns.

Abstract: Purpose: The primary objective of the study was to determine the incidence of the various pathological conditions present at the base of the periocular cutaneous horns. The secondary objective was to study the presentation of these cutaneous horns with a view to finding any clinical indicators for premalignant, malignant and benign lesions at the base.Methods: Prospective multicentre study of patients presenting with cutaneous horns. Informed consent followed by excision biopsy of the base lesion was performed in all the cases included for the study. The biopsy specimens were examined histologically and results analysed.Results: Twenty-six patients presented with cutaneous horns in the periocular region over a period of 2 years, of these two patients presented with more than one cutaneous horn. 23 patients underwent excision biopsy. There were a total of 25 specimens. Of the base lesions 2/25 (8%) were malignant, 7/25 (28%) were pre-malignant and the remaining 16/25 (64%) were benign. Analysis of the find...

Management of periocular actinic keratosis: a review of practice patterns among ophthalmic plastic surgeons.

Abstract: Purpose To determine the practice patterns of ophthalmic plastic surgeons regarding the management of actinic keratosis (AK) of the eyelid and periocular area. Methods A brief electronic survey was distributed to members of the American Society of Ophthalmic Plastic and Reconstructive Surgery requesting their demographic information and treatment approaches to AK. Results One hundred and seven of 523 (20.5%) American Society of Ophthalmic Plastic and Reconstructive Surgery members completed the survey. Most respondents treat AK 2 mm from the eyelid margin, with most respondents treating by excision with permanent pathology (56.1%), followed by referral to dermatology for Mohs or non-Mohs treatment and topical chemotherapy (8.4% each). Conclusion Although most American Society of Ophthalmic Plastic and Reconstructive Surgery members use excisional biopsy with permanent section pathology control of margins for the treatment of AK of the eyelid and periocular region, multiple alternative treatment approaches are also used.

The eye says it all: Periocular region methodologies

Abstract: In the field of secure communication, an explosive growth is observed in biometric personal authentication and recognition systems for the last few decades. Biometric system involves establishing the human identity based on a physical or behavioral trait. In the recent studies, various biometric traits including face, iris, ear, gait, palm and knuckle joints have been investigated. Inaccuracy due to noisy sensor data, intra class variation and susceptibility to spoofing attacks evaluate the performance of these biometric systems. Human periocular region is known to be one of the most discriminative regions of the face. The periocular region is rich in texture and is quantified as a useful biometric trait. Acquisition of the periocular region requires less subject cooperation compared to other ocular biometric traits. The field of periocular biometrics includes enormous research and is currently gaining importance. In the paper an attempt has been made to present an insight of different periocular region methodologies.

Skin grafts in the periocular region without a bolstered dressing.

Abstract: Dear editor, In their article entitled skin grafts in the periocular region without a bolstered dressing,1 the authors claim that this is the first literature report doing away altogether with using tie-over bolsters. A more accurate rephrasing would be that this is the first report in the literature where a bolster was not applied when perimeter sutures alone were used, because in 2004 Thomas Naugle and associates immobilized eyelid skin grafts with direct graft-to-bed quilting sutures alone and without the use of a sutured dressing in some of their patients.2 I find the encouraging results of the authors with grafts up to 3 cm interesting but rather antithetical. A well-established concept of graft survival is that skin grafts vascularize from the bed not just from the edges,3 and this is possibly why we could safely remove the sutured bolster from the equation when using direct tacking sutures. Otherwise I would restrict the use of such technique to grafts considerably smaller than 3 cm.

Periocular Region Classifiers

Abstract: Biometrics is the science of establishing human identity based on the physical or behavioral traits of an individual such as face, iris, ear, hand geometry, finger print, gait, knuckle joints and conjunctival vasculature among others. The enormous attention drawn towards the ocular biometrics during the recent years has led to the exploration of newer traits such as the periocular region. With the preliminary exploration of the feasibility of periocular region to be used as an independent biometric trait or in combination of face/iris, research towards periocular region is currently gaining lot of prominence. Over the last few years many researchers have investigated various techniques of feature extraction and classification in the periocular region. This paper attempts to review a few of these classifier techniques useful for developing robust classification algorithms.