SCALE INVARIANT DESCRIPTORS IN PATTERN ANALYSIS OF MELANOCYTIC LESIONS

In this paper we introduce the importance of scale invariance in properly discriminating some of the typical patterns found in melanocytic lesions, by dermatoscopic image analysis. Pattern discrimination is a necessary step before pattern irregularity (an indicator of malignancy) can be quantified. We propose a set of features that allows for the discrimination of such patterns even when they appear in different degrees of magnification. We show how an automated feature selection stage produces a preferred scale invariant set of features among non-invariant features, yielding the best classification rate for those features. The average correct classification rate for the five kinds of classified patterns rises up to 94%.