The image ray transform is a novel technique to aid extraction of circular and tubular structural features and image symmetry. It uses a subset of the laws of optics (refraction and total internal reflection) and a simple ray casting algorithm to use the paths of rays through an image to produce a transformed image. It has successfully been used to enhance detection of ears, circle and retinal vascalature.
Available here is a python implementation of the transform, a definition of the transform (although reading the publications on it is a better idea), some examples, and a Java demo.