Search

This paper concerns a method to automatically detect drusen in a retinal image without human supervision or interaction. We use a multi-level approach, beginning with classification at the pixel level and proceeding to the region level, area level, and then image level. This allows the lowest levels of classification to be tuned to detect even the faintest and most difficult to discern drusen, relying upon the higher levels of classification to use an ever broadening context to refine the segmentation. We test our methods on a set of 119 images containing all types of drusen as well as images containing no drusen or other potentially confusing lesions. Our overall correct detection rate is 87%.

We describe and analyze several techniques to parallelize a novel algorithm that fuses intensity data from multiple video cameras to create a spatial-temporal occupancy map. Instead of tracking objects, the algorithm operates by recognizing free space. The brevity of operations in the algorithm allows a dense spatial occupancy map to be temporally computed at real-time video rates. Since each input image pixel is processed independently, we demonstrate parallel implementations that achieve nearly ideal speedup on a four processor shared memory architecture. Potential applications include surveillance, robotics, virtual reality, and manufacturing environments.

Image similarity can be defined in a number of different semantic contexts. At the lowest common denominator, images may be classified as similar according to geometric properties, such as color and shape distributions. At the mid-level, a deeper image similarity may be defined according to semantic properties, such as scene content or description. We propose an even higher level of image similarity, in which domain knowledge is used to reason about semantic properties, and similarity is based on the results of reasoning. At this level, images with only slightly different (or similar) semantic descriptions may be classified as radically different (or similar), based upon the execution of the domain knowledge. For demonstration, we show experiments performed on a small database of 300 images of the retina, classified according to fourteen diagnoses.