Open AccessEuclidean distance digital image processing for jaundice detect
Author(s) -
Etika Putri Rahayu,
Melyaurul Widyawati,
S Suryono
Publication year - 2021
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/1108/1/012022
Subject(s) - jaundice , artificial intelligence , rgb color model , euclidean distance , computer vision , computer science , medicine , psychology , gastroenterology
Jaundice is a serious health issue. Late treatment of jaundice cases in babies may result in neurodevelopmental disorder and irreversible brain damage. Diagnosis inaccuracy is usually caused by the fact that health professionals and health service providers often rely on visual observation instead of laboratory examination. Lack of expertise in detecting jaundice is a serious matter. This research proposes a method of web-based digital image processing as an alternative for early detection of jaundice based on babies’ complexion. Images of babies’ complexion and color calibration cards are taken to obtain images for online analysis. Determination of bilirubin levels is carried out using the method of Euclidean approximate distance of RGB values from babies’ complexion and those of color calibration cards. Results show correlation of Euclidean distance to bilirubin level of babies of 0.93596 and web-based digital image processing accuracy of 90%. These mean that the information system developed here is capable of detecting jaundice cases. This research was performed observationally in high-risk prenatal ward involving 30 infants as samples.