Abstract
In appearance based face recognition, lip reading, etc., eigen face and eigen lip are used for recognition. The pose changes of the human head in a video sequence often cause errors in the eigen space comparison stage, because the frontal-pose assumption has been violated. In this paper, we propose a new method to compensate the pose changes by exploiting the general symmetry of human face. From the imaging geometry we show that a frontal pose can be recovered from only one profile view. The resulting pose compensation method has the following advantages: (1) it only requires one profile image; (2) it does not need any 3D model; (3) it does not need accurate feature detection. Experimental results in the context of lip images are given to show the effectiveness of our method.
| Original language | English (US) |
|---|---|
| Pages | 243-246 |
| Number of pages | 4 |
| State | Published - Dec 1 2000 |
| Event | International Conference on Image Processing (ICIP 2000) - Vancouver, BC, Canada Duration: Sep 10 2000 → Sep 13 2000 |
Other
| Other | International Conference on Image Processing (ICIP 2000) |
|---|---|
| Country | Canada |
| City | Vancouver, BC |
| Period | 9/10/00 → 9/13/00 |
Fingerprint
ASJC Scopus subject areas
- Hardware and Architecture
- Computer Vision and Pattern Recognition
- Electrical and Electronic Engineering
Cite this
Recovering frontal-pose image from a single profile image. / Ma, J.; Ahuja, Narendra; Neti, C.; Senior, A. W.
2000. 243-246 Paper presented at International Conference on Image Processing (ICIP 2000), Vancouver, BC, Canada.Research output: Contribution to conference › Paper
}
TY - CONF
T1 - Recovering frontal-pose image from a single profile image
AU - Ma, J.
AU - Ahuja, Narendra
AU - Neti, C.
AU - Senior, A. W.
PY - 2000/12/1
Y1 - 2000/12/1
N2 - In appearance based face recognition, lip reading, etc., eigen face and eigen lip are used for recognition. The pose changes of the human head in a video sequence often cause errors in the eigen space comparison stage, because the frontal-pose assumption has been violated. In this paper, we propose a new method to compensate the pose changes by exploiting the general symmetry of human face. From the imaging geometry we show that a frontal pose can be recovered from only one profile view. The resulting pose compensation method has the following advantages: (1) it only requires one profile image; (2) it does not need any 3D model; (3) it does not need accurate feature detection. Experimental results in the context of lip images are given to show the effectiveness of our method.
AB - In appearance based face recognition, lip reading, etc., eigen face and eigen lip are used for recognition. The pose changes of the human head in a video sequence often cause errors in the eigen space comparison stage, because the frontal-pose assumption has been violated. In this paper, we propose a new method to compensate the pose changes by exploiting the general symmetry of human face. From the imaging geometry we show that a frontal pose can be recovered from only one profile view. The resulting pose compensation method has the following advantages: (1) it only requires one profile image; (2) it does not need any 3D model; (3) it does not need accurate feature detection. Experimental results in the context of lip images are given to show the effectiveness of our method.
UR - http://www.scopus.com/inward/record.url?scp=0034445185&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=0034445185&partnerID=8YFLogxK
M3 - Paper
AN - SCOPUS:0034445185
SP - 243
EP - 246
ER -