Psychological research indicates that humans recognize faces of their own race more accurately than faces of other races. This "other-race effect" occurs for algorithms tested in the Face Recognition Vendor Test 2006. We report results for a Western algorithm made by fusing eight algorithms from Western countries and an East Asian algorithm made by fusing five algorithms from East Asian countries. At the low false accept rates required for most security applications, the Western algorithm recognized Caucasian faces more accurately than East Asian faces and the East Asian algorithm recognized East Asian faces more accurately than Caucasian faces. Next, using a test that spanned all false alarm rates, we compared the algorithms with humans of Caucasian and East Asian descent matching face identity in an identical stimulus set. In this case, both algorithms performed better on the Caucasian faces-the "majority" race in the database. The Caucasian face advantage, however, was far larger for the Western algorithm than for the East Asian algorithm. Humans showed the standard other-race effect for these faces, but showed more stable performance than the algorithms over changes in the race of the test faces. State-of-the-art face recognition algorithms, like humans, struggle with "other-race face" recognition. Index Termsface and gesture recognition, performance evaluation of algorithms and systems, human information processing

BackgroundSymptom relief for the duration of 24 hours after treatment would benefit patients with allergic conjunctivitis.ObjectiveTo compare the safety and efficacy of olopatadine 0.77% with vehicle or olopatadine 0.2% in patients with allergic conjunctivitis in a conjunctival allergen-challenge clinical study.Patients and methodsIn this Phase III, multicenter, double-masked, parallel-group, randomized trial, patients with allergic conjunctivitis received olopatadine 0.77%, its vehicle, or olopatadine 0.2%, administered once at visits 3A (day 0), 4A (day 14 ±2), and 5 (day 21 +3). Allergic conjunctivitis-associated sign and symptom assessments included ocular itching, conjunctival redness, total redness, chemosis, and tearing scores. Adverse events and ocular safety parameters were also assessed.ResultsA total of 202 qualifying patients were randomized. Olopatadine 0.77% was superior (P<0.001) to vehicle for treatment of ocular itching at 3, 5, and 7 minutes postchallenge at onset of action and 16- and 24-hour duration of action. Conjunctival redness mean scores were significantly lower for olopatadine 0.77% versus vehicle at all three post-conjunctival allergen-challenge time points: onset (−1.52 to −1.48; P<0.001), 16 hours (−1.50 to −1.38; P<0.01), and 24 hours (−1.58 to −1.38; P<0.05). At 24 hours, olopatadine 0.77% was superior to olopatadine 0.2% at all three postchallenge time points for ocular itching (P<0.05), conjunctival redness (P<0.05), and total redness (P<0.05). No clinically relevant differences in safety parameters or adverse events were observed between the treatment groups.ConclusionOlopatadine 0.77% is superior to both its vehicle and olopatadine 0.2% for the treatment of allergen-mediated ocular itching and conjunctival redness. Ocular itching symptom relief is maintained over 24 hours, supporting once-daily dosing and demonstrating a comparable safety profile to olopatadine 0.2%.

Olopatadine 0.77% demonstrated a rapid onset and prolonged duration of action. It was superior to all comparators in alleviating AC-associated ocular itching with a favorable safety profile.Clinical Trial Registration-URL: http://www.clinicaltrials.gov. Unique identifier: NCT01743027.