No abstract

No abstract

No abstract

The compensation comparison method for measuring retinal straylight is suited for clinical use to diagnose patients with complaints caused by large angle light scattering in the eye such as early cataract.

We address the problem of large-scale fine-grained visual categorization, describing new methods we have used to produce an online field guide to 500 North American bird species. We focus on the challenges raised when such a system is asked to distinguish between highly similar species of birds. First, we introduce one-vs-most classifiers. By eliminating highly similar species during training, these classifiers achieve more accurate and intuitive results than common one-vs-all classifiers. Second, we show how to estimate spatio-temporal class priors from observations that are sampled at irregular and biased locations. We show how these priors can be used to significantly improve performance. We then show state-of-the-art recognition performance on a new, large dataset that we make publicly available. These recognition methods are integrated into the online field guide, which is also publicly available.

The direct compensation method allows for an accurate (standard deviation below 0.05 log unit) determination of intraocular light scattering between 3.5 and 25 deg of scattering angle and is suitable for untrained subjects. The method was used to study population behaviour and individual variation in 129 volunteers between 20 and 82 yr of age, visual acuity equal to or better than one and no apparent eye pathology. The results indicate straylight to increase with the 4th power of age, doubling at 70. In addition to the age dependence, there was great variation between individuals. Part of this is due to negative correlation with pigmentation.

We propose a method of face verification that takes advantage of a reference set of faces, disjoint by identity from the test faces, labeled with identity and face part locations. The reference set is used in two ways. First, we use it to perform an "identity-preserving" alignment, warping the faces in a way that reduces differences due to pose and expression but preserves differences that indicate identity. Second, using the aligned faces, we learn a large set of identity classifiers, each trained on images of just two people. We call these "Tom-vs-Pete" classifiers to stress their binary nature. We assemble a collection of these classifiers able to discriminate among a wide variety of subjects and use their outputs as features in a same-or-different classifier on face pairs. We evaluate our method on the Labeled Faces in the Wild benchmark, achieving an accuracy of 93.10%, significantly improving on the published state of the art.

No abstract