18 January 2005 Performance of digital RGB reflectance color extraction for plaque lesion
Author Affiliations +
Abstract
Several clinical psoriasis lesion groups are been studied for digital RGB color features extraction. Previous works have used samples size that included all the outliers lying beyond the standard deviation factors from the peak histograms. This paper described the statistical performances of the RGB model with and without removing these outliers. Plaque lesion is experimented with other types of psoriasis. The statistical tests are compared with respect to three samples size; the original 90 samples, the first size reduction by removing outliers from 2 standard deviation distances (2SD) and the second size reduction by removing outliers from 1 standard deviation distance (1SD). Quantification of data images through the normal/direct and differential of the conventional reflectance method is considered. Results performances are concluded by observing the error plots with 95% confidence interval and findings of the inference T-tests applied. The statistical tests outcomes have shown that B component for conventional differential method can be used to distinctively classify plaque from the other psoriasis groups in consistent with the error plots finding with an improvement in p-value greater than 0.5.
© (2005) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Hadzli Hashim, Hadzli Hashim, Mohd Nasir Taib, Mohd Nasir Taib, Rozita Jailani, Rozita Jailani, Saadiah Sulaiman, Saadiah Sulaiman, Roshidah Baba, Roshidah Baba, } "Performance of digital RGB reflectance color extraction for plaque lesion", Proc. SPIE 5630, Optics in Health Care and Biomedical Optics: Diagnostics and Treatment II, (18 January 2005); doi: 10.1117/12.572423; https://doi.org/10.1117/12.572423
PROCEEDINGS
12 PAGES


SHARE
Back to Top