Detecting Jaundice with Image Processing

BUDIANTO, MARTIN (2021) Detecting Jaundice with Image Processing. Other thesis, Universitas Katholik Soegijapranata Semarang.

[img] Text
17.K1.0017-MARTIN BUDIANTO-COVER_a.pdf

Download (462kB)
[img] Text
17.K1.0017-MARTIN BUDIANTO-BAB I_a.pdf

Download (208kB)
[img] Text
17.K1.0017-MARTIN BUDIANTO-BAB II_a.pdf
Restricted to Registered users only

Download (682kB)
[img] Text
17.K1.0017-MARTIN BUDIANTO-BAB III_a.pdf

Download (204kB)
[img] Text
17.K1.0017-MARTIN BUDIANTO-BAB IV_a.pdf

Download (1MB)
[img] Text
17.K1.0017-MARTIN BUDIANTO-BAB V_a.pdf

Download (989kB)
[img] Text
17.K1.0017-MARTIN BUDIANTO-BAB VI_a.pdf

Download (202kB)
[img] Text
17.K1.0017-MARTIN BUDIANTO-DAPUS_a.pdf

Download (225kB)
[img] Text
17.K1.0017-MARTIN BUDIANTO-LAMP_a.pdf

Download (550kB)

Abstract

This research was conducted for how to detect jaundice using image processing, where Jaundice is a condition in which the skin, sclera (whites of the eyes) and mucous membranes turn yellow because of high bilirubin. Because if jaundice is not detected quickly it will cause kernicterus and can also cause death, My proposed method to solve this problem is by using color detection algorithm to my program with using HSV color space and kernel method as classification, while the only existing project is made by Ashish Sardana, in overcoming jaundice by using his proposed method using the YCbCR color space and Logistic regression as the classification method, where my program has an average success rate of 90% and Ashish Sardana's program is below 50% which was tested with the same 100 datasets because Ashish Sardana program failed to find right value of yellow jaundice color,so the result of his program failed to differentiate between negative or positive data.

Item Type: Thesis (Other)
Subjects: 000 Computer Science, Information and General Works > 004 Data processing & computer science
Divisions: Faculty of Computer Science > Department of Informatics Engineering
Depositing User: mr AM. Pudja Adjie Sudoso
Date Deposited: 15 Oct 2021 02:28
Last Modified: 15 Oct 2021 02:28
URI: http://repository.unika.ac.id/id/eprint/27126

Actions (login required)

View Item View Item