Title: Colour space-based thresholding for segmentation of skin lesion images

Authors: Sudhriti Sengupta; Neetu Mittal; Megha Modi

Addresses: Amity Institute of Information Technology, Amity University, Uttar Pradesh, Noida, India ' Amity Institute of Information Technology, Amity University, Uttar Pradesh, Noida, India ' Yashoda Super Speciality Hospital, Vasundhara, Ghaziabad, UP 201001, India

Abstract: In computer aided diagnosis (CAD) of various skin diseases, the skin lesion image segmentation is an important phase. The quality of skin lesion images is affected by poor contrast, low illumination, complexity of texture and presence of artefacts like hair etc. For better skin lesion detection, an improved colour space-based split and merge process in combination with global thresholding segmentation technique has been proposed. The obtained results have been further enhanced by self-guided edge smoothing-colour space technique. The effectiveness of the proposed self-guided edge smoothing-colour space technique has been verified by quantitatively comparing the obtained results with the existing Otsu thresholding, adaptive thresholding and colour space techniques. The computed results show much better values of performance measuring parameters viz. entropy, dice similarity index and structural content for edge smoothing-colour space technique. This indicates far superior quality of images obtained by the proposed self-guided edge smoothing-colour space technique.

Keywords: skin lesions; segmentation; colour space; thresholding; entropy; merging; split; adaptive thresholding; Otsu thresholding; global thresholding; skin diseases; self-guided edge smoothing.

DOI: 10.1504/IJBET.2022.124663

International Journal of Biomedical Engineering and Technology, 2022 Vol.39 No.4, pp.347 - 368

Received: 12 Feb 2019
Accepted: 05 Jul 2019
Published online: 05 Aug 2022 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article