TY  - CONF
EP  - 339
A1  - Ramli, R.
A1  - Malik, A.S.
A1  - Hani, A.F.M.
A1  - Yap, F.B.-B.
UR  - https://www.scopus.com/inward/record.uri?eid=2-s2.0-84857018680&doi=10.1109%2fDICTA.2011.63&partnerID=40&md5=a71f262180d64b385f5938119eb411ff
SN  - 9780769545882
Y1  - 2011///
SP  - 335
ID  - scholars1759
TI  - Segmentation of acne vulgaris lesions
KW  - acne lesions; Acne vulgaris; Chronic disorders; Color features; color space; Computational imaging; Flash photography; K-means clustering; Manual methods; Medical Image Processing; Negative predictive value; Positive predictive values; Segmentation methods; Segmentation results; Visual assessments
KW  -  Color photography; Dermatology; Image processing
KW  -  Image segmentation
N1  - cited By 17; Conference of 2011 International Conference on Digital Image Computing: Techniques and Applications, DICTA 2011 ; Conference Date: 6 December 2011 Through 8 December 2011; Conference Code:88414
N2  - Acne is chronic disorder of the pilosebaceous units with excess sebum production, follicular epidermal hyper proliferation, inflammation and P acnes activity. It affects 85 of adolescents at some time during their lives. Dermatologists use manual methods such as direct visual assessment and ordinary flash photography to assess the acne. These methods are very time consuming and tedious. To address these issues, researchers in recent years have proposed computational imaging methods for aiding in the acne diagnosis. To develop algorithm with an automated acne grading method is the objective of this proposed method. This work presents an image segmentation method for acne lesions based on color features with K-means clustering. The segmentation results from randomly selected images show the sensitivity, specificity, positive predictive value and negative predictive value greater than 81. © 2011 IEEE.
AV  - none
CY  - Noosa, QLD
ER  -