The iris of a human is not only relevant for biometry; it is also relevant for the prediction and diagnosis of human health. One understands by iris diagnosis (Iridology) the investigation and analysis of the colored part of the eye, the iris, to discover factors which play an important role for the prevention and treatment of illnesses. Up-to-date the iris diagnosis is done manually and is concerned with the know problems, objectivities and reproducibility. An automatic system would pave the way for much wider use of the iris diagnosis for the diagnosis of ill-nesses and for the purpose of individual health protection. In this paper we describe the state-of-the-art of the Iridology. Different ways of image acquisition and image preprocessing are explained. We describe the image analysis method for the detection of the iris. This method is based on our novel case-based object recognition and case mining method.

Petra Perner
Institute of Computer Vision and applied Computer Sciences, IBaI
Kohlenstr. 2, 04107 Leipzig, Germany