Open AccessColour Component Analysis Approach for Malaria Parasites Detection Based on Thick Blood Smear Images
Author(s) -
Thaqifah Ahmad Aris,
Aimi Salihah Abdul Nasir,
Zeehaida Mohamed,
Harlina Suzana Jaafar,
Wan Azani Mustafa,
Wan Khairunizam,
Mohd Aminudin Jamlos,
I. Zunaidi,
Z. M. Razlan,
A. B. Shahriman
Publication year - 2019
Publication title -
iop conference series. materials science and engineering
Language(s) - English
Resource type - Journals
eISSN - 1757-899X
pISSN - 1757-8981
DOI - 10.1088/1757-899x/557/1/012007
Subject(s) - ycbcr , blood smear , malaria , artificial intelligence , rgb color model , hsl and hsv , computer science , segmentation , computer vision , blood film , pattern recognition (psychology) , image processing , biology , pathology , medicine , immunology , image (mathematics) , color image , virus
Malaria is a plasmodium parasite disease that affects millions of people in the world every year. Hence, early detection tests are needed to prevent the malaria parasites spread throughout the body. For centuries, manual microscopic blood test remains as the most common method that still being used for malaria detection. However, this procedure contains the probability of miscalculation of parasites due to human error. Computerized system is recognized as a quick and easy ways to analyze a lot of blood samples images by providing direct visualization on the computer screen without the need to examine under the microscope. Therefore, this paper aims to analyze different colour components for improving the parasites counting performance based on thick blood smear images. In this study, five different colour spaces namely YCbCr, RGB, CMY, HSV and HSL have been analyzed and eight colour components which are Y, Cb, R, G, C, M, S and L have been extracted in order to determine which colour component is the best for malaria parasites counting. Overall, experimental results indicate that segmentation using Y component of YCbCr proved to be the best with average counting accuracy of 98.48% for 100 images of malaria thick blood smear.