HOME
Full Articles List
Search by Author
Title: COLOUR HISTOGRAM ANALYSIS FOR SKIN LESIONS DISCRIMINATION
BibTex 
Open this article in the author's DB |
|
COLOUR HISTOGRAM ANALYSIS FOR SKIN LESIONS DISCRIMINATION
|
|
|
|
|
|
|
|
||
|
|
|
|
|
|
1314-2704
|
|
|
|
||
|
|
English
|
|
|
|
19
|
|
|
|
6.3
|
|
|
|
|
|
|
|
||
|
|
One of the risk factors in skin cancer is unprotected exposure to UV radiation. Melanoma is the deadliest form of skin cancer but also curable if it is diagnosed in the early stages. This study uses a histogram analysis technique to investigate and classify two common skin lesions, nevi and melanoma. The colour feature investigated is the optimal threshold values in RGB space. Also, a boundary limit of the skin lesions is performed using a colour histogram analysis and the optimal threshold determination. A statistical analysis of the relevant threshold values for R, G and B histograms to establish a sound colour separation between benign and malignant lesions is performed. Monochromatic channel threshold values are clustered using K-means and the validity of clustering is assessed by silhouette method. The proposed method technique is evaluated using 120 colour digital images (60 melanomas and 60 nevi) from the Digital Archive of the Department of Dermatology of the University Medical Center in Groningen (UMCG)1. The reported results suggest red as the lesion representative colour in dermoscopic images. The pixel values for red channel are strongly related to the skin lesion type.
|
|
|
|
conference
|
|
|
|
||
|
|
||
|
|
19th International Multidisciplinary Scientific GeoConference SGEM 2019
|
|
|
|
19th International Multidisciplinary Scientific GeoConference SGEM 2019, 9 - 11 December, 2019
|
|
|
|
Proceedings Paper
|
|
|
|
STEF92 Technology
|
|
|
|
International Multidisciplinary Scientific GeoConference-SGEM
|
|
|
|
Bulgarian Acad Sci; Acad Sci Czech Republ; Latvian Acad Sci; Polish Acad Sci; Russian Acad Sci; Serbian Acad Sci & Arts; Slovak Acad Sci; Natl Acad Sci Ukraine; Natl Acad Sci Armenia; Sci Council Japan; World Acad Sci; European Acad Sci, Arts & Letters; Ac
|
|
|
|
75-82
|
|
|
|
9 - 11 December, 2019
|
|
|
|
website
|
|
|
|
cdrom
|
|
|
|
6665
|
|
|
|
segmentation; histogram; statistical analysis
|
|
Download PDF