Research on Protein Level in Medical Latex Glove Images using Color Kernel Regression Method

Citation

Toa, Chean Khim and Sim, Kok Swee and Tan, Joon Liang (2019) Research on Protein Level in Medical Latex Glove Images using Color Kernel Regression Method. International Journal of Engineering and Advanced Technology, 8 (6S). pp. 612-616. ISSN 2249-8958

[img] Text
25.pdf - Published Version
Restricted to Repository staff only

Download (1MB)

Abstract

In the healthcare environment, medical latex gloves are a necessary medical item for healthcare workers as it offers excellent hand barrier protection against dangerous microorganism. However, if the healthcare workers repeated exposure to the latex gloves which contain high protein level, it will increase the possibility of the workers to have a risk for latex allergy. Thus, the objective of this project is to develop a color kernel regression (CKR) method for estimating protein level through the analyses of color difference in glove images. Initially, the gloves will go through an uncomplicated chemical test for protein detection. A blue color will appear on the surface of a glove sample that contains protein. After that, the chemical binded sample will be digitally converted into a sample image using the flatbed scanner. The image will then undergo image processing to improve its quality and to calculate the color difference values of the sample. Those calculated values with the pre-defined protein levels will be used to plot a standard graph. A high coefficient of determination with R2 > 98% has been obtained from the experimental graph. This indicates that the proposed CKR method contributes significantly toward the estimation of protein level

Item Type: Article
Uncontrolled Keywords: Latex
Subjects: Q Science > QK Botany
Divisions: Faculty of Engineering and Technology (FET)
Depositing User: Ms Rosnani Abd Wahab
Date Deposited: 15 May 2021 12:29
Last Modified: 24 Feb 2023 06:00
URII: http://shdl.mmu.edu.my/id/eprint/8711

Downloads

Downloads per month over past year

View ItemEdit (login required)