Automated Computer Vision System for Urine Color Detection
Urine color analysis is one of the most helpful indicators of health status, and any changes in urine color might be a symptom of serious disease, dehydration of the body, or caused by drugs. To get better assistance for urine color detection in the proposed system, a urine color automatic identifi...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
middle technical university
2023-03-01
|
| Series: | Journal of Techniques |
| Subjects: | |
| Online Access: | https://journal.mtu.edu.iq/index.php/MTU/article/view/896 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832595122063147008 |
|---|---|
| author | Ban Shamil Abdulwahed Ali Al-Naji Izzat Al-Rayahi Ammar Yahya Asanka G. Perera |
| author_facet | Ban Shamil Abdulwahed Ali Al-Naji Izzat Al-Rayahi Ammar Yahya Asanka G. Perera |
| author_sort | Ban Shamil Abdulwahed |
| collection | DOAJ |
| description |
Urine color analysis is one of the most helpful indicators of health status, and any changes in urine color might be a symptom of serious disease, dehydration of the body, or caused by drugs. To get better assistance for urine color detection in the proposed system, a urine color automatic identification has been developed based on computer vision. The proposed system uses a web camera to capture an image in real-time, analyze it, and then classify the color of urine by using the random forest (RF) algorithm and show the result via the Graphical User Interface (GUI). In addition, the proposed system can send the results to the mobile phone of the patient or care provider by using an Arduino microcontroller and GSM module. Moreover, sending a voice message about the color of urine is related to pathological conditions. The results showed that the proposed system has high accuracy (approximately about 97%) in detecting urine color under different light conditions, with low cost, short time, and easy implementation. In the comparison with the current methods the proposed system has maximum accuracy and minimum error rate. This methodology can pave the way for an additional case study in medical applications, particularly in diagnosis, and patient health monitoring.
|
| format | Article |
| id | doaj-art-6ab463676d79489eaca7a5d8a0e3e93b |
| institution | Kabale University |
| issn | 1818-653X 2708-8383 |
| language | English |
| publishDate | 2023-03-01 |
| publisher | middle technical university |
| record_format | Article |
| series | Journal of Techniques |
| spelling | doaj-art-6ab463676d79489eaca7a5d8a0e3e93b2025-01-19T11:01:58Zengmiddle technical universityJournal of Techniques1818-653X2708-83832023-03-015110.51173/jt.v5i1.896Automated Computer Vision System for Urine Color DetectionBan Shamil Abdulwahed0Ali Al-Naji 1Izzat Al-Rayahi 2Ammar Yahya3Asanka G. Perera4Electrical Engineering Technical College, Middle Technical University, Baghdad, Iraq.School of Engineering, University of South Australia, Mawson Lakes SA 5095, AustraliaCollege of Health & Medical Technology - Baghdad, Middle Technical University, Baghdad, IraqTechnical Institute for Administration, Middle Technical University, Baghdad, Iraq.Centre for Intelligent Systems, Central Queensland University, Brisbane, QLD 4000, Australia Urine color analysis is one of the most helpful indicators of health status, and any changes in urine color might be a symptom of serious disease, dehydration of the body, or caused by drugs. To get better assistance for urine color detection in the proposed system, a urine color automatic identification has been developed based on computer vision. The proposed system uses a web camera to capture an image in real-time, analyze it, and then classify the color of urine by using the random forest (RF) algorithm and show the result via the Graphical User Interface (GUI). In addition, the proposed system can send the results to the mobile phone of the patient or care provider by using an Arduino microcontroller and GSM module. Moreover, sending a voice message about the color of urine is related to pathological conditions. The results showed that the proposed system has high accuracy (approximately about 97%) in detecting urine color under different light conditions, with low cost, short time, and easy implementation. In the comparison with the current methods the proposed system has maximum accuracy and minimum error rate. This methodology can pave the way for an additional case study in medical applications, particularly in diagnosis, and patient health monitoring. https://journal.mtu.edu.iq/index.php/MTU/article/view/896Urine Color DetectionImages ProcessingMachine LearningRandom ForestGraphical User Interface |
| spellingShingle | Ban Shamil Abdulwahed Ali Al-Naji Izzat Al-Rayahi Ammar Yahya Asanka G. Perera Automated Computer Vision System for Urine Color Detection Journal of Techniques Urine Color Detection Images Processing Machine Learning Random Forest Graphical User Interface |
| title | Automated Computer Vision System for Urine Color Detection |
| title_full | Automated Computer Vision System for Urine Color Detection |
| title_fullStr | Automated Computer Vision System for Urine Color Detection |
| title_full_unstemmed | Automated Computer Vision System for Urine Color Detection |
| title_short | Automated Computer Vision System for Urine Color Detection |
| title_sort | automated computer vision system for urine color detection |
| topic | Urine Color Detection Images Processing Machine Learning Random Forest Graphical User Interface |
| url | https://journal.mtu.edu.iq/index.php/MTU/article/view/896 |
| work_keys_str_mv | AT banshamilabdulwahed automatedcomputervisionsystemforurinecolordetection AT alialnaji automatedcomputervisionsystemforurinecolordetection AT izzatalrayahi automatedcomputervisionsystemforurinecolordetection AT ammaryahya automatedcomputervisionsystemforurinecolordetection AT asankagperera automatedcomputervisionsystemforurinecolordetection |