Application of photometric stereo in dermatology
A computational approach is adopted to redesign a device to inspect the skin primarily for dermatological uses.
It is capable of capturing images of the skin, generating 3D views to display on a host or client screen and analyzing the images to detect the presence of skin cancer - specifically malignant melanoma.
The device should be able to help experts differentiate between malignant melanoma and benign skin lesions.
The image right and above shows a the device designed and built at the CMV . The housing contains a camera and six LED light sources. A separate image is captured with each of the LEDs independently illuminated.
The proposed method for classifying the skin lesion (malignant or benign) is summarised in a flow diagram as follows.
The photometric stereo stage of the algorithm is performed using the complete colour matrix equation:
The tool is to be used to inspect the skin via local or remote terminals. It produces images through a combination of photometric stereo, bump map generation and perspective projection. An example of the captured image set is shown below. Application of photometric stereo methods yields the results shown to the right of the figure, i.e. the field of surface normals, the albedo map and the bump map.
Characterizing the skin by using images obtained with the device is an indispensable intermediate step in this project. Good features extracted from geometric or colour information should be invariant or almost invariant to object position and pose, lighting condition and camera setup. Features might include asymmetry, border, colour variation, diameter which are summarized as ABCD features. As an example of feature extraction consider the two figures below. To the left is a picture of a real skin sample. The right shows a skin pattern isolated using image processing techniques.
Building a classifier is to combine several heuristic rules together used by the dermatologists to identify malignant melanoma. The ABCD rules might be simple and inaccurate if treated separately. But by combining them together using techniques like boosting, the final classifier would be highly accurate and has a good generalization capability.
The image below illustrates an effort to isolate suspicious regions of a lesion. In future, these regions will be detected and analysed robustly, using our classifier algorithm.