Periocular Region

About: Periocular Region is a research topic. Over the lifetime, 256 publications have been published within this topic receiving 4424 citations.

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.

Deep-PRWIS: Periocular Recognition Without the Iris and Sclera Using Deep Learning Frameworks

Abstract: This paper is based on a disruptive hypothesis for periocular biometrics—in visible-light data, the recognition performance is optimized when the components inside the ocular globe (the iris and the sclera) are simply discarded, and the recognizer’s response is exclusively based on the information from the surroundings of the eye. As a major novelty, we describe a processing chain based on convolution neural networks (CNNs) that defines the regions-of-interest in the input data that should be privileged in an implicit way, i.e., without masking out any areas in the learning/test samples. By using an ocular segmentation algorithm exclusively in the learning data, we separate the ocular from the periocular parts. Then, we produce a large set of “multi-class” artificial samples, by interchanging the periocular and ocular parts from different subjects. These samples are used for data augmentation purposes and feed the learning phase of the CNN, always considering as label the ID of the periocular part. This way, for every periocular region, the CNN receives multiple samples of different ocular classes, forcing it to conclude that such regions should not be considered in its response. During the test phase, samples are provided without any segmentation mask and the network naturally disregards the ocular components, which contributes for improvements in performance. Our experiments were carried out in full versions of two widely known data sets (UBIRIS.v2 and FRGC) and show that the proposed method consistently advances the state-of-the-art performance in the closed-world setting, reducing the EERs in about 82% (UBIRIS.v2) and 85% (FRGC) and improving the Rank-1 over 41% (UBIRIS.v2) and 12% (FRGC).

Management of Periocular Basal Cell Carcinoma With Modified En Face Frozen Section Controlled Excision

Abstract: Purpose To determine the rate of recurrence of basal cell carcinomas (BCCs) after modified en face frozen section-controlled excision in a high-risk population in Queensland, Australia. Methods Retrospective, noncomparative interventional case series. A review was conducted of all patients with periocular BCCs examined between 1992 to 2001 in a tertiary oculoplastics practice. Basal cell carcinomas were surgically excised, and the recurrence rates under modified en face frozen section control, Mohs micrographic surgery, and no frozen section control were documented. Epidemiologic aspects of periocular BCC in Queensland, Australia were also studied. Results In patients with primary BCCs, 0.71% (3 of 423 lesions) recurred when excised under frozen section control (mean follow-up, 2.6 years). At 5-year follow-up, the recurrence rate was 2.1% (2 of 97 lesions). Excision without frozen section control yielded a recurrence rate of 1.8% (2 of 113 lesions; mean follow-up, 2.6 years). There were 6 additional lesions, however, that were incompletely excised. At 5 years, the recurrence rate was 5%. Six patients had lesions removed with Mohs micrographic surgery. There were no recurrences after a mean follow-up of 1.7 years. Of 653 total lesions, 361 involved the right eye (55%). Most BCCs were on the lower eyelid (53%) and inner canthus (29%). Solid BCCs were the most common type (54%), followed by the infiltrative type (15%). The majority of complications were minor and caused no ocular damage. Conclusions Carefully performed, modified en face frozen section controlled excision of periocular BCCs yields cure rates comparable to Mohs micrographic surgery at 5-year follow-up. Close communication with a skilled pathologist is essential to achieve these low recurrence rates. The fact that lesions involved the right periocular region more than the left may reflect greater sun exposure on that side from driving.