Toward Unconstrained Ear Recognition From Two-Dimensional Images

Ear recognition, as a biometric, has several advantages. In particular, ears can be measured remotely and are also relatively static in size and structure for each individual. Unfortunately, at present, good recognition rates require controlled conditions. For commercial use, these systems need to be much more robust. In particular, ears have to be recognized from different angles ( poses), under different lighting conditions, and with different cameras. It must also be possible to distinguish ears from background clutter and identify them when partly occluded by hair, hats, or other objects. The purpose of this paper is to suggest how progress toward such robustness might be achieved through a technique that improves ear registration. The approach focuses on 2-D images, treating the ear as a planar surface that is registered to a gallery using a homography transform calculated from scale-invariant feature-transform feature matches. The feature matches reduce the gallery size and enable a precise ranking using a simple 2-D distance algorithm. Analysis on a range of data sets demonstrates the technique to be robust to background clutter, viewing angles up to +/- 13 degrees, and up to 18% occlusion. In addition, recognition remains accurate with masked ear images as small as 20 x 35 pixels.

3D Morphable Model Construction for Robust Ear and Face Recognition

Recent work suggests that the human ear varies significantly between different subjects and can be used for identification. In principle, therefore, using ears in addition to the face within a recognition system could improve accuracy and robustness, particularly for non-frontal views. The paper describes work that investigates this hypothesis using an approach based on the construction of a 3D morphable model of the head and ear. One issue with creating a model that includes the ear is that existing training datasets contain noise and partial occlusion. Rather than exclude these regions manually, a classifier has been developed which automates this process. When combined with a robust registration algorithm the resulting system enables full head morphable models to be constructed efficiently using less constrained datasets. The algorithm has been evaluated using registration consistency, model coverage and minimalism metrics, which together demonstrate the accuracy of the approach. To make it easier to build on this work, the source code has been made available online.

Robust 2D Ear Registration and Recognition Based on SIFT Point Matching

Significant recent progress has shown ear recognition to be a viable biometric. Good recognition rates have been demonstrated under controlled conditions, using manual registration or with specialised equipment. This paper describes a new technique which improves the robustness of ear registration and recognition, addressing issues of pose variation, background clutter and occlusion. By treating the ear as a planar surface and creating a homography transform using SIFT feature matches, ears can be registered accurately. The feature matches reduce the gallery size and enable a precise ranking using a simple 2D distance algorithm. When applied to the XM2VTS database it gives results comparable to PCA with manual registration. Further analysis on more challenging datasets demonstrates the technique to be robust to background clutter, viewing angles up to +/- 13 degrees and with over 20% occlusion.

Predictors of therapy resistant asthma: outcome of a systematic evaluation protocol

Background: It has been suggested that asthmatic subjects with persisting symptoms despite adequate maintenance therapy should be systematically evaluated to identify factors contributing to poor control. The aims of this study were to examine the prevalence of these factors in a cohort of sequentially referred poorly controlled asthmatics, and to determine if any factor or combination of factors predicted true therapy resistant asthma (TRA).

Methods: Patients were evaluated using a systematic evaluation protocol including induced sputum analysis, psychiatric assessment, ear, nose and throat examination, pulmonary function testing, high resolution CT scan of the thorax, and 24 hour dual probe ambulatory oesophageal pH monitoring; any identified provoking factor was treated. Asthma was managed according to BTS guidelines.

Results: Of 73 subjects who completed the assessment, 39 responded to intervention and 34 had TRA. Subjects with TRA had a greater period of instability, a higher dose of inhaled steroids at referral, more rescue steroid use, and a lower best percentage forced expiratory volume in 1 second (FEV1%). Oesophageal reflux, upper airway disease, and psychiatric morbidity were common (57%, 95%, 49%, respectively) but were not more prevalent in either group. Using multivariate logistic regression analysis, inhaled steroid dose >2000 µg BDP, previous assessment by a respiratory specialist, and initial FEV1% of <70% at referral predicted a final diagnosis of TRA.

Conclusions: In poorly controlled asthmatics there is a high prevalence of co-morbidity, identified by detailed systematic assessment, but no difference in prevalence between those who respond to intervention and those with TRA. Targeted treatment of identified co-morbidities has minimal impact on asthma related quality of life in those with therapy resistant disease.

Cochlin in the eye: Functional implications

Aqueous humor is actively produced in the ciliary epithelium of the anterior chamber and has important functions for the eye. Under normal physiological conditions, the inflow and outflow of the aqueous humor are tightly regulated, but in the pathologic state this balance is lost. Aqueous outflow involves structures of the anterior chamber and experiences most resistance at the level of the trabecular meshwork (TM) that acts as a filter. The modulation of the TM structure regulates the filter and its mechanism remains poorly understood. Proteomic analyses have identified cochlin, a protein of poorly understood function, in the glaucomatous TM but not in healthy control TM from human cadaver eyes. The presence of cochlin has subsequently been confirmed by Western and immunohistochemical analyses. Functionally, cochlin undergoes multimerization induced by shear stress and other changes in the microenvironment. Cochlin along with mucopolysaccharide deposits have been found in the TM of glaucoma patients and in the inner ear of subjects affected by the hearing disorder DNFA9, a late onset, progressive disease that also involves alterations in fluid shear regimes. In vitro, cochlin induces aggregation of primary TM cells suggesting a role in cell adhesion, possibly in mechanosensation, and in modulation of the TM filter.

Langerin expressing cells promote skin immune responses under defined conditions.

There are conflicting data in the literature regarding the role of epidermal Langerhans cells (LC) in promoting skin immune responses. On one hand, LC can be extremely potent APCs in vitro, and are thought to be involved in contact hypersensitivity (CHS). On the other hand, it seems counterintuitive that a cell type continually exposed to pathogens at the organism\'s barrier surfaces should readily trigger potent T cell responses. Indeed, LC depletion in one model led to enhanced contact hypersensitivity, suggesting they play a negative regulatory role. However, apparently similar LC depletion models did not show enhanced CHS, and in one case showed reduced CHS. In this study we found that acute depletion of mouse LC reduced CHS, but the timing of toxin administration was critical: toxin administration 3 days before priming did not impair CHS, whereas toxin administration 1 day before priming did. We also show that LC elimination reduced the T cell response to epicutaneous immunization with OVA protein Ag. However, this reduction was only observed when OVA was applied on the flank skin, and not on the ear. Additionally, peptide immunization was not blocked by depletion, regardless of the site. Finally we show that conditions which eliminate epidermal LC but spare other Langerin(+) DC do not impair the epicutaneous immunization response to OVA. Overall, our results reconcile previous conflicting data in the literature, and suggest that Langerin(+) cells do promote T cell responses to skin Ags, but only under defined conditions.

Evaluation and outcome of patients with chronic non-productive cough using a comprehensive diagnostic protocol

Background-Asthma, post-nasal drip syndrome (PNDS), and gastrooesophageal reflux (GOR) account for many cases of chronic non-productive cough (CNPC). Each may simultaneously contribute to cough even when clinically silent, and failure to recognise their contribution may lead to unsuccessful treatment.

Methods—Patients (all lifetime non-smokers with normal chest radiographs and spirometric measurements) referred with CNPC persisting for more than three weeks as their sole respiratory symptom underwent histamine challenge, home peak flow measurements, ear, nose and throat (ENT) examination, sinus CT scanning, and 24 hour oesophageal pH monitoring. Treatment was prescribed on the basis of diagnoses informed by investigation results.

RESULTS—Forty three patients (29 women) of mean age 47.5 years (range 18-77) and mean cough duration 67 months (range 2-240) were evaluated. On the basis of a successful response to treatment, a cause for the cough was identified in 35 patients (82%) as follows: cough variant asthma (CVA) (10 cases), PNDS (9 cases), GOR (8cases), and dual aetiologies (8 cases). Histamine challenge correctly predicted CVA in 15 of 17 (88%) positive tests. ENT examination and sinus CT scans each had low positive predictive values for PNDS (10 of 16 (63%) and 12 of 18 (67%) positive cases, respectively), suggesting that upper airways disease frequently co-exists but does not always contribute to cough. When negative, histamine challenge and 24 hour oesophageal pH monitoring effectively ruled out CVA and GOR, respectively, as a cause for cough.

CONCLUSION—This comprehensive approach aids the accurate direction of treatment and, while CVA, PNDS and GOR remain the most important causes of CNPC to consider, a group with no identifiable aetiology remains.