Background: In this study, a novel and fully automatic skin disease classification approach is proposed using statistical feature extraction and Artificial Neural Network (ANN) based classification using first and second order statistical moments, the entropy of different color channels and texture-based features.
Aims: The basic aim of our study is to develop an automated system for skin disease classification that can help a general physician to automatically detect the lesion and classify it to disease types.
Method: The performance of the proposed approach is corroborated by extensive experiments performed on a dataset of 588 images containing 6907 lesion regions.
Results: The results show that the proposed methodology can be effectively used to construct a skin disease classification system.
Conclusion: Our proposed method is designed for a specific skin tone. Future investigation is needed to analyze the impact of different skin tones on the performance of lesions detection and classification system.
[http://dx.doi.org/10.1046/j.1365-2133.2000.03468.x] [PMID: 10809845]
[http://dx.doi.org/10.1016/j.compmedimag.2008.11.002] [PMID: 19121917]
[http://dx.doi.org/10.1111/j.1600-0846.2008.00301.x] [PMID: 19159382]
[http://dx.doi.org/10.1016/j.compbiomed.2011.01.003] [PMID: 21316042]
[http://dx.doi.org/10.1111/j.1600-0846.2011.00603.x] [PMID: 22211360]