Multimodal Biometric Person Authentication Using Face, Ear and Periocular Region Based on Convolution Neural Networks

Biometrics is an active area of research because of the increase in need for accurate person identification in numerous applications ranging from entertainment to security. Unimodal and multimodal are the well-known biometric methods. Unimodal biometrics uses one biometric modality of a person for person identification. The performance of an unimodal biometric system is degraded due to certain limitations such as: intra-class variations and nonuniversality. The person identification using more than one biometric modality of a person is multimodal biometrics. This method of identification has gained more interest due to resistance on spoof attacks and more recognition rate. Conventional methods of feature extraction have difficulty in engineering features that are liable to more variations such as illumination, pose and age variations. Feature extraction using convolution neural network (CNN) can overcome these difficulties because large dataset with robust variations can be used for training, where CNN can learn these variations. In this paper, we propose multimodal biometrics at feature level horizontal fusion using face, ear and periocular region biometric modalities and apply deep learning CNN for feature representation and also we propose face, ear and periocular region dataset that are robust to intra-class variations. The evaluation of the system is made by using proposed database. Accuracy, Precision, Recall and [Formula: see text] score are calculated to evaluate the performance of the system and had shown remarkable improvement over existing biometric system.

Clinicopathological Features of 19 Eyelid Pilomatrixomas

Introduction: Pilomatrixoma is a relatively rare, benign tumor arising from the hair root matrix. It is found frequently on the head and neck, with most involving the eyebrow in the periocular region. In contrast, eyelid pilomatrixoma is less common, and often clinically misdiagnosed. Here, we present clinical and histological data from 19 pilomatrixomas arising in the eyelid. Methods: The study represents a retrospective study of eyelid pilomatrixoma diagnosed at our institution since 1981. All slides were reviewed, and demographic as well as clinical data obtained. Results: Patient ages ranged from 2 to 63 years (mean 24 years), including 12 (63%) females and 7(37%) males. Eight (42%) and 4 (21%) cases arose in the first and second decades of life, respectively. Upper eyelid involvement was found in 14 (74 %) of cases. Microscopically, the tumors were characterize by basaloid and shadow cells accompanied by calcification and foreign body giant cells. Conclusions: Eyelid pilomatrixoma is rarely suspected clinically, and can be mistaken for cyst, chalazion, sebaceous carcinoma and other tumors. Physicians should consider the possibility of pilomatrixoma in the eyelid area, especially in children or young female patients. Complete excision is curative, and diagnosis can generally be established by histopathological examination.

Nephronectin-Integrin α8 signaling is required for proper migration of periocular neural crest cells during chick corneal development

During development, cells aggregate at tissue boundaries to form normal tissue architecture of organs. However, how cells are segregated into tissue precursors remains largely unknown. Cornea development is a perfect example of this process whereby neural crest cells aggregate in the periocular region prior to their migration and differentiation into corneal cells. Our recent RNA-Seq analysis identified upregulation of Nephronectin (Npnt) transcripts during early stages of corneal development where its function has not been investigated. We found that Npnt mRNA and protein are expressed by various ocular tissues including the migratory periocular neural crest (pNC), which also express the integrin alpha 8 (Itgα8) receptor. Knockdown of either Npnt or Itgα8 attenuated cornea development, whereas overexpression of Npnt resulted in cornea thickening. Moreover, overexpression of Npnt variants lacking RGD binding sites did not affect corneal thickness. Neither the knockdown or augmentation of Npnt caused significant changes in cell proliferation, suggesting that Npnt directs pNC migration into the cornea. In vitro analyses showed that Npnt promotes pNC migration from explanted periocular mesenchyme, which requires Itgα8. Combined, these findings show that Npnt specifies and tunes cell migration into the presumptive cornea ECM by providing a substrate for Itgα8-positive pNC cells.

Analysis of Facial Muscle Depths to Guide Botulinum Toxin Therapy of the Periocular Region

Purpose: Botulinum toxin (BTX) injections are used in cosmetic surgery to efface facial wrinkles. Botulinum toxin relaxes the muscle by preventing the release of the neurotransmitter acetylcholine at the neuromuscular junction located at the posterior muscle surface causing local muscle paralysis. The purpose of this study is to provide anatomic knowledge of muscle belly depths of the frontalis, corrugator supercilii, procerus, and orbicularis oculi muscles in an attempt to improve the efficacy of BTX treatment of glabellar, forehead, and lateral eyelid rhytides. Methods: Six-millimeter punch biopsies were obtained from 7 fresh cadavers. Biopsies were taken from the corrugator supercilii, frontalis, procerus, and orbicularis oculi muscles at the sites of routine BTX injection. Specimens were fixed in formalin, and representative H&E-stained sections were used to measure muscle surface depths by light microscopy equipped with digital camera that includes a digital micrometer. One-way analysis of variance test analyses were used to identify statistical differences between measured muscle depths. Results: The measured anterior muscle depth of the corrugator supercilii, frontalis, procerus, and orbicularis oculi was found to be 4.2 ± 0.6, 3.9 ± 0.6, 2.9 ± 0.4, and 2.3 ± 0.7 mm, respectively. The anterior muscle surface of the corrugator supercilii and frontalis was found to be deeper than that of the procerus and orbicularis oculi ( P < .001). The posterior surface depth of the corrugator supercilii, frontalis, procerus, and orbicularis oculi was found to be 6.6 ± 0.8, 5.1 ± 0.7, 4.9 ± 0.7, and 3.8 ± 1.0 mm, respectively. The posterior surface depth of the corrugator supercilii was found to be significantly deeper than that of the frontalis, procerus, and orbicularis oculi ( P < .001); the posterior surface depth of the frontalis and procerus was deeper than that of the orbicularis oculi ( P < .001). The muscle belly width of the corrugator supercilii, frontalis, procerus, and orbicularis oculi measured 2.5 ± 0.9, 1.1 ± 0.4, 2.0 ± 0.6, and 1.5 ± 0.5 mm, respectively. The corrugator supercilii was found to be thicker than the frontalis and orbicularis oculi, while the procerus was found to be thicker than the frontalis ( P < .001). Conclusion: The findings above demonstrate statistical differences in the posterior muscle surface depth of the corrugator supercilii, frontalis, procerus, and orbicularis oculi which can be used clinically to improve BTX injection efficacy when used to efface facial rhytides.

Intense Pulse Laser Therapy and Dry Eye Disease

The high and increasing prevalence of Dry Eye Disease (DED) highlights the need for new treatment treatments and more effective management strategies for this chronic disease. After training, lid grooming, and various ocular lubricants, the Tear Film & Ocular Surface Society Dry Eye Workshop II (TFOS DEWS II) Management and Therapy Subcommittee recently proposed Intense Pulsed Light (IPL) as the second phase of therapy. Brief flashes of non-coherent light (400–1,200 nm) are delivered to the skin’s surface using IPL technology. Toyos et al. found in 2005 that rosacea sufferers who were treated with IPL in the periocular region had a significant increase in their dry eye symptoms.

Periocular rejuvenation using a unique non-ablative long-pulse 2940 nm Er:YAG laser

The periocular region is challenging for cosmetic laser surgeons. Surgery and laser resurfacing have traditionally been used to correct periorbital lines and wrinkles. Although effective, the associated downtime with these methods has made many people reluctant to decide for such treatments. More recently, the non-ablative long-pulse 2940 nm Er:YAG laser is being used to improve the structure and function and hence the appearance of skin in the periorbital region. The objective of this study is to evaluate the safety and efficacy of long-pulse 2940 nm Er:YAG laser for non-ablative treatment of periorbital static wrinkles and skin laxity. This is a prospective analysis of 30 patients treated for periorbital rejuvenation using three sessions of non-ablative long-pulse Er:YAG laser over a 3-month period. All patients were assessed according to Fitzpatrick’s classification of periorbital wrinkles to class I, II, or III and were treated with 2940 nm Er:YAG laser using a fluence of 3.75 J/cm2, a repetition rate of 1.7–2 Hz, and with the SMOOTH™ pulse mode (250 ms). The treatment sessions were performed on each patient, 4 weeks apart. Patient improvement was assessed before each laser session as well as at 12 months after the final treatment. Blind photographic evaluations were performed by three independent physicians using unlabeled before and after photos arranged in non-chronological order. Reviewers were asked to determine the before and after photos. Patients were asked to answer a questionnaire measuring satisfaction 4 weeks after each session, and to report any adverse reactions. There was statistically and clinically significant improvement in the Fitzpatrick classification of the periorbital wrinkles. Blinded evaluators correctly identified the before and after photos in all cases. All patients reported mild edema and erythema, which persisted for 1 to 2 days, and superficial peeling of the skin for 4 to 6 days after each laser treatment. No long-term adverse effects were reported. The non-ablative long-pulse 2940 nm Er:YAG laser seems to be a safe and effective treatment for periocular rejuvenation with minimal and tolerable adverse reaction. The improvement attained from the laser sessions was persisting after 1 year denoting the long-term efficacy of the procedure.

Reliability of Stereophotogrammetry for Area Measurement in the Periocular Region

Three-dimensional (3D) stereophotography area measurements are essential for describing morphology in the periocular region. However, its reliability has not yet been sufficiently validated. The objective of this study was to evaluate the reliability of 3D stereophotogrammetric area measurements in the periocular region. Forty healthy volunteers had five flat paper objects placed at each of the seven periocular positions including the endocanthion and the upper medial, upper middle, upper lateral, lower medial, lower middle, and the lower lateral eyelid. Two series of photographic images were captured twice by the same investigator. Each image of the first series was measured twice by the same rater, while images of both series were measured once by a second rater. Differences between these measurements were calculated, and the intrarater, interrater, and intramethod reliability was evaluated for intraclass correlation coefficients (ICCs), mean absolute differences (MADs), technical errors of measurements (TEMs), relative errors of measurements (REMs), and relative TEM (rTEM). Our results showed that 21.2% of all ICCs were considered as excellent, 45.5% were good, 27.3% were moderate, and 6.1% were poor. The interrater ICC for the endocanthion location was 0.4% on a low level. MAD values for all objects were less than 0.3 mm2, all TEM were less than 1 mm2, the REM and rTEM were less than 2% for all objects, showing high reliability. 3D stereophotogrammetry is a highly reliable system for periocular area measurements and may be used in the clinical routine for planning oculoplastic surgeries and for evaluating changes in periocular morphology.Level of Evidence IV This journal requires that authors assign a level of evidence to each article. For a full description of these Evidence-Based Medicine ratings, please refer to the Table of Contents or the online Instructions to Authors www.springer.com/00266.