Image processing for monitoring obstructive sleep apnea
Obstructive sleep apnea (OSA) is a sleep related breathing disorder that affects people worldwide. OSA patients are prone to hypertension, platelet clotting dysfunction and diabetes – which are in the family of heart disease. 15% of Singapore’s population is affected by OSA, and it is more prevalent...
Saved in:
| Main Author: | |
|---|---|
| Other Authors: | |
| Format: | Final Year Project |
| Language: | English |
| Published: |
2010
|
| Subjects: | |
| Online Access: | http://hdl.handle.net/10356/40887 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Institution: | Nanyang Technological University |
| Language: | English |
| Summary: | Obstructive sleep apnea (OSA) is a sleep related breathing disorder that affects people worldwide. OSA patients are prone to hypertension, platelet clotting dysfunction and diabetes – which are in the family of heart disease. 15% of Singapore’s population is affected by OSA, and it is more prevalent in middle-aged Singapore males as compared to females. The cross section and volume of the pharyngeal region was indicated as the vital areas affecting OSA. This project aims to investigate on the properties of face detection technology that can enhance image analysis and processing.
The author would also educate the readers on OSA and discuss the dangerous effects of this sleep disordered when untreated. Symptoms, diagnostic methods and techniques of evaluation will be discussed. The author has examined the nasopharyngoscopy and discussed its usage for image processing for OSA detections. Accurate and efficient analysis of the structural changes in the upper airway will improve the effectiveness of the nasopharyngoscopy. A real time image showing the cross sectional areas and the volume of the upper airway will be able to achieve the efficiency.
OpenCV codes and C++ program was used to create two programs to track defined locations on still images and on video images. The results obtain for still images are accurate and the detection rate is rapid. Simple square images were used to replicate the pharyngeal regions and the program was able to detect the required images as requested by the author. 7 images (consisting of squares, pentagon, triangles, and irregular geometries) are used to test the performance of the program. Undefined parameters in the program for detecting video images with no conclusive results will be discussed. The limited time duration for the creation of the program, and future improvements that can be implemented in future research were highlighted. |
|---|