Spectral filter optimization for the recovery of parameters which describe human skin

• Published in: IEEE transactions on pattern analysis and machine intelligence 2004-07, Vol.26 (7), p.913-922
• Main Authors: Preece, S.J., Claridge, E.
• Format: Article
• Language: English
• Subjects: Algorithms; Application software; Artificial Intelligence; Biomedical imaging; Color; Colorimetry - methods; Computer graphics; Dermoscopy - methods; Humans; image analysis; Image color analysis; Image Enhancement - methods; Image Interpretation, Computer-Assisted - methods; Image reconstruction; medical imaging; Optical filters; optimization; Optimization methods; Pattern Recognition, Automated - methods; Pigmentation; Skin; skin color; Skin Physiological Phenomena; spectral filters
• ISSN: 0162-8828; 1939-3539
• DOI: 10.1109/TPAMI.2004.36

The paper presents a method for finding spectral filters that minimize the error associated with histological parameters characterizing normal skin tissue. These parameters can be recovered from digital images of the skin using a physics-based model of skin coloration. The relationship between the image data and histological parameter values is defined as a mapping function from the image space to the parameter space. The accuracy of this function is determined by the choice of optical filters. An optimization criterion for finding the optimal filters is defined by combing methodology from differential geometry with statistical error analysis. It is shown that the magnitude of errors associated with the optimal filters is typically half of that for typical RGB filters on a three-parameter model of human skin coloration. Finally, other medical image applications are identified to which this generic methodology could be applied.