Increasing performance of digital image analysis and development of new classification algorithms, like neural networks, has led to new technological approaches in the diagnosis of skin cancer by analyzing digitized images of clinical or dermatoscopic pictures. Taking into account epidemiological data and risk factors an automatic diagnostic system should allow to distinguish between benign and malignant pigmented skin lesions. To overcome the problem of a small amount of standardized data 14 European departments of Dermatology (Bochum, M³nster, Dortmund, Cologne, Maastricht, Nice, Siena, Glasgow, Leeds, Paris, Crete, Madrid, Copenhagen) are working together in the DANAOS (Diagnostic And Neuronal Analysis of Skin Cancer) project to collect standardized data of many thousands of suspicious skin lesions. Therefore a new data aquisition unit was constructed which consists if a high resolution,specially calibrated 3-Chip CCD handheld video camera with a microprocessor controlled ring of white light LED's which allows to take a series of standardized images in 10-, 20- and 30-fold magnification under different illuminating directions. A computer program was developed, to gather consistent data to case history and risk factors. We demonstrate first results in examining the surface structure of the skin lesions by means of sideward illumination.