사상체질의학회지 (Journal of Sasang Constitutional Medicine)
- 제20권1호
- /
- Pages.34-41
- /
- 2008
- /
- 1226-4075(pISSN)
- /
- 2287-786X(eISSN)
3차원 안면자동인식기(3D-AFRA)의 인식도 연구
Accuracy of 3D Automatic Face Recognition Apparatus(3D-AFRA) Recognition
- 김윤희 (경희대학교 한의과대학 사상체질과) ;
- 양춘석 ((주)맥써러시) ;
- 이준희 (경희대학교 한의과대학 사상체질과) ;
- 정용재 (경희대학교 한의과대학 사상체질과) ;
- 유정희 (경희대학교 한의과대학 사상체질과) ;
- 이승현 ((주)맥써러시) ;
- 고병희 (경희대학교 한의과대학 사상체질과) ;
- 이의주 (경희대학교 한의과대학 사상체질과)
- Kim, Yun-Hee (Dept. of Sasang Constitutional Medicine, College of Oriental Medicine, Kyung-hee Univ.) ;
- Yang, Chun-Seok (Maxuracy. Co., LTD.) ;
- Lee, Jun-Hee (Dept. of Sasang Constitutional Medicine, College of Oriental Medicine, Kyung-hee Univ.) ;
- Jung, Yong-Jae (Dept. of Sasang Constitutional Medicine, College of Oriental Medicine, Kyung-hee Univ.) ;
- Yoo, Jung-Hee (Dept. of Sasang Constitutional Medicine, College of Oriental Medicine, Kyung-hee Univ.) ;
- Lee, Seung-Hyun (Maxuracy. Co., LTD.) ;
- Koh, Byung-Hee (Dept. of Sasang Constitutional Medicine, College of Oriental Medicine, Kyung-hee Univ.) ;
- Lee, Eui-Ju (Dept. of Sasang Constitutional Medicine, College of Oriental Medicine, Kyung-hee Univ.)
- 발행 : 2008.04.30
초록
1. Objectives We had been developing a 3D Automatic Face Recognition Apparatus (3D-AFRA) in order to evaluate the external appearances with more objectivity. This apparatus provides a 3D image and numerical data on facial configuration, and this study aims to evaluate the accuracy of 3D-AFRA recognition. 2. Methods Each scanned pictures were pointed with the 3D Automatic Face Recognition Apparatus(3D-AFRA). And the results were compared with data pointed pictures with manual. And we analysed the difference between Automatic and manual by paired -test. 3. Results and conclusions In frontal face, the P-value was more than 0.05. In conclusion, We assessed that accuracy of recognition of 3D Automatic Face Recognition Apparatus(3D-AFRA) is considerably good. But we should develop methods of measurement for lateral face and indistinct points of frontal face.
키워드