키넥트 센서를 이용한 실용적인 3차원 안면 진단기 연구
Study on the Practical 3D Facial Diagnosis using Kinect Sensors
0
조회
0
다운로드
2
인용
0
참고문헌
키워드
초록
Facial diagnosis based on quantitative facial features has been studied in many Korean medicine fields, especially in Sasang constitutional medicine. By the rapid growing of 3D measuring technology, generic and cheap 3D sensors, such as Microsoft Kinect, is popular in many research fields. In this study, the possibility of using Kinect in facial diagnosis is examined. We introduce the development of facial feature extraction system and verify its accuracy and repeatability of measurement. Furthermore, we compare Sasang constitution diagnosis results between DSLR-based system and the developed Kinect-based system. A Sasang constitution diagnosis algorithm applied in the experiment was previously developed by a huge database containing 2D facial images acquired by DSLR cameras. Interrater reliability analysis result shows almost perfect agreement (Kappa = 0.818) between the two systems. This means that Kinect can be utilized to the diagnosis algorithm, even though it was originally derived from 2D facial image data. We conclude that Kinect can be successfully applicable to practical facial diagnosis.
Abstract
Facial diagnosis based on quantitative facial features has been studied in many Korean medicine fields, especially in Sasang constitutional medicine. By the rapid growing of 3D measuring technology, generic and cheap 3D sensors, such as Microsoft Kinect, is popular in many research fields. In this study, the possibility of using Kinect in facial diagnosis is examined. We introduce the development of facial feature extraction system and verify its accuracy and repeatability of measurement. Furthermore, we compare Sasang constitution diagnosis results between DSLR-based system and the developed Kinect-based system. A Sasang constitution diagnosis algorithm applied in the experiment was previously developed by a huge database containing 2D facial images acquired by DSLR cameras. Interrater reliability analysis result shows almost perfect agreement (Kappa = 0.818) between the two systems. This means that Kinect can be utilized to the diagnosis algorithm, even though it was originally derived from 2D facial image data. We conclude that Kinect can be successfully applicable to practical facial diagnosis.
참고문헌 (16)
- 이의주, "四象人의 容貌에 관한 문헌적 연구", 사상체질의학회지, 17(3), pp.55~68 (2005), 사상체질의학회
- 장아름, "사상의학과 형상의학의 유형분류의 연관성에 관한 연구", 사상체질의학회지, 22(3), pp.75~86 (2010), 사상체질의학회
- 이선영, "안면형상을 활용한 사상체질 진단 연구에 관한 체계적 고찰", 사상체질의학회지, 24(4), pp.17~27 (2012), 사상체질의학회[DOI]
- Koh, B. H., "A Morphologic Study of head and face for Sasang Constitution", J. of Sasang Constitutional Medicine, 8(1), pp.101~186 (1996)
- Hong, S. C., "A morphological study for objectification of the Sasang Constitution diagnosis On the So-eumin", J. of Sasang Constitutional Medicine, 10(1), pp.171~180 (1998)
- Do, J. H., "Development of an integrated Sasang constitution diagnosis method using face, body shape, voice, and questionnaire information", BMC Complementary and Alternative Medicine, 12, pp.85~ (2012)
- Hong, S. C., "A morphological study of upper face according to the sasang constitution", J. of Sasang Constitutional Medicine, 10(1), pp.161~170 (1998)
- 석재화, "3차원 안면자동인식기의 형상복원 오차검사", 사상체질의학회지, 18(2), pp.41~49 (2006), 사상체질의학회
- 도준형, "Analysis of Sasang constitutional types using facial features with compensation for photographic distance", Integrative Medicine Research, 1(1), pp.26~35 (2012), 한국한의학연구원[DOI]
- Khoshelham, K., "Accuracy and resolution of Kinect depth data for indoor mapping applications", Sensors, 12, pp.1437~1454 (2012)
- Wang, R., "Accurate 3D face and body modeling from a single fixed Kinect", Proc. of the 4th International Conference on 3D Body Scanning Technologies (3DBST 2013) (2013)
- 백영화, "체질정보은행 구축현황에 관한 소고", 사상체질의학회지, 24(2), pp.47~53 (2012), 사상체질의학회[DOI]
- Jang, J. S., "Upper eyelid shape extraction using polynomial curves", Proc. of IEEK summer, pp.1726~1727 (2011)
- Do, J. H., "Detection of iris center point by means of Histogram-based filtered mask and donut-shaped template", Proc. of IEEK summer Conf, 1724(1725) (2011)