Segmentation of skin lesion images using discrete wavelet transform

Abstract

Abstract Skin lesion segmentation is the essential step in automated computer-aided diagnosis of malignant melanoma. However, this task might be challenging when there are variations in appearances of lesion across different patients and it turns more complex when acquired dermoscopic images include some artifacts like dark corner, gel, low contrast and dense skin hair. In this paper, we propose a skin lesion segmentation method using discrete wavelet transform to tackle the complexities present in the dermoscopic images. The proposed method is based on the analysis of different colour components from various colour spaces such as YCbCr, HSV subjected to discrete wavelet decomposition to remove unwanted data in the form of marker ink, colour chart etc. Otsu and Histogram based thresholding is used to separate skin lesion region from the background. The proposed method is tested using publicly available PH2 and Kaggle s Skin Lesion Segmentation dataset. The results are compared with different state-of-the-art methods using evaluation metrics. The results reveal the effectiveness of the proposed method in comparison with other approaches, accordance with quantitative results and visual effects.