Skip to main content

Research Repository

Advanced Search

Machine vision 3D skin texture analysis for detection of melanoma

Ding, Y.; Smith, Lyndon; Smith, Melvyn; Farooq, Abdul; Sun, Jiuai; Warr, Robert


Y. Ding

Lyndon Smith
Professor in Computer Simulation and Machine

Profile Image

Melvyn Smith
Research Centre Director Vision Lab/Prof

Abdul Farooq
Associate Head of Departmemt Business Engagement and Partnerships

Jiuai Sun

Robert Warr


Pur ose - The ur ose of this a er is to describe innovative machine vision methods that have been em loyed for the ca ture and analysis of 3D skin textures; and the resulting otential for assisting with identification of sus icious lesions in the detection of skin cancer. Design/methodology/a roach - A machine vision a roach has been em loyed for analysis of 3D skin textures. This involves an innovative a lication of hotometric stereo for the ca ture of the textures, and a range of methods for analysing and quantifying them, including statistical methods and neural networks. Findings - 3D skin texture has been identified as a useful indicator of skin cancer. It can be used to im rove realism of virtual skin reconstructions in tele-dermatology. 3D texture features can also be combined with 2D features to obtain a more robust classifier for im roving diagnostic accuracy, thereby assisting with the long-term goal of im lementing com uter-aided diagnostics for skin cancer. Originality/value - The device develo ed for ca turing 3D skin textures is known as the "Skin Analyser", and as far as the authors know it is unique in the world in being able to recover 3D textures from igmented lesions in vivo. There currently exist numerous methods for analysing lesions, including manual ins ection (using established heuristics commonly known as ABCD rules), dermosco y and SIAosco y. The ability to ca ture and analyse 3D lesion textures com lements these existing techniques and forms a valuable additional indicator for assisting with the early detection of dangerous skin cancers such as melanoma. © Emerald Group Publishing Limited.


Warr, R., Ding, Y., Sun, J., Farooq, A. R., Smith, M. L., Smith, L. N., …Warr, R. (2011). Machine vision 3D skin texture analysis for detection of melanoma. Sensor Review, 31(2), 111-119.

Journal Article Type Article
Publication Date May 11, 2011
Journal Sensor Review
Publisher Emerald
Peer Reviewed Peer Reviewed
Volume 31
Issue 2
Pages 111-119
Keywords 3D skin texture, visualisation, cancer detection, melanoma
Public URL
Publisher URL