A Machine Learning Framework for Hair Type Categorization to Optimize the Hair Removal Algorithm in Dermatoscopy Images

This work proposes a machine learning (ML) framework to classify the hair type of dermatoscopy images into four classes using the imaging features taken from the binary hair contour masks. Furthermore, the optimal kernel of the black-hat hair removal algorithm is then examined through the structural similarity index measure (SSIM) between the original and the pre-processed image. The best performance of the classification model in terms of ACC and AUC was obtained by the SVM classifier, achieving 80% and 79.8%, respectively. A kernel size of up to 20 by 20 is proposed for image filtering without significant loss of texture information in the lesion.Clinical Relevance: This paper presents an effort to find the optimal kernel size of the black-hat algorithm for hair removal on dermatoscopy images, while maintaining high image quality. This work is proposed as an automated pre-processing step for deep learning in skin disease classification.