New Freeware for Image Analysis of Lissamine Green Conjunctival Staining.

PURPOSE: Lissamine green (LG) is often used in addition to fluorescein to assess the severity of conjunctival damage in dry eye syndrome, which is graded manually. Our purpose was to describe an algorithm designed for image analysis of LG conjunctival staining. METHODS: Twenty pictures of patients suffering from dry eye with visible LG conjunctival staining were selected. The images were taken by 2 different digital slit lamps with a white light source and a red filter transmitting over the wavelengths absorbed by LG. Conjunctival staining appeared in black on a red background. The red channel was extracted from the original image. Stained areas were then detected using a Laplacian of Gaussian filter and applying a threshold whose value was determined manually on a subset of images. The same algorithm parameters remained constant thereafter. LG-stained areas were also drawn manually by 2 experts as a reference. RESULTS: The delineation obtained by the algorithm closely matched the actual contours of the punctate dots. In 19 cases of 20 (95%), the algorithm found the same Oxford grade as the experts, even for confluent staining that was detected as a multitude of dots by the algorithm but not by the experts, resulting in a high overestimation of the total number of dots (without mismatching the Oxford grade estimated by the experts). The results were similar for the 2 slit-lamp imaging systems. CONCLUSIONS: This efficient new image-analysis algorithm yields results consistent with subjective grading and may offer advantages of automation and scalability in clinical trials.

Local low rank approximation with a parametric disparity model for light field compression.

We address the problem of light field dimensionality reduction for compression. We describe a local low rank approximation method using a parametric disparity model. The local support of the approximation is defined by super-rays. A super-ray can be seen as a set of super-pixels that are coherent across all light field views. A dedicated super-ray construction method is first described that constrains the super-pixels forming a given super-ray to be all of the same shape and size, dealing with occlusions. This constraint is needed so that the super-rays can be used as supports of angular dimensionality reduction based on low rank matrix approximation. The light field low rank assumption depends on how much the views are correlated, i.e. on how well they can be aligned by disparity compensation. We first introduce a parametric model describing the local variations of disparity within each super-ray. We then consider two methods for estimating the model parameters. The first method simply fits the model on an input disparity map. We then introduce a disparity estimation method using a low rank prior. This method alternatively searches for the best parameters of the disparity model and of the low rank approximation. We assess the proposed disparity parametric model, first assuming that the disparity is constant within a super-ray, and second by considering an affine disparity model. We show that using the proposed disparity parametric model and estimation algorithm gives an alignment of super-pixels across views that favours the low rank approximation compared with using disparity estimated with classical computer vision methods. The low rank matrix approximation is computed on the disparity compensated super-rays using a singular value decomposition (SVD). A coding algorithm is then described for the different components of the proposed disparity-compensated low rank approximation. Experimental results show performance gains, with a rate saving going up to 92.61%, compared with the JPEG Pleno anchor, for real light fields captured by a Lytro Illum camera. The rate saving goes up to 37.72% with synthetic light fields. The approach is also shown to outperform an HEVC-based light field compression scheme.