抄録
3D face models provide more robust shape information of facial features than intensity or color in 2D images. However, many current facial feature extraction methods on 3D face models still depend on human instruction. This paper proposes an automatic human face feature extraction method adaptive to 3D face models in various poses and various scales based on analysis of surface curvature and a priori knowledge of human face structure. Moreover, during processing of segmented regions on 3D model, a novel region processing approach, called "Combine and Split", is proposed to significantly reduce undependable candidate regions for facial organs from hundreds to around ten. Experimental results demonstrate that proposed method can effectively extract eye, nose, mouth and ear regions from various 3D face models.
| 元の言語 | English |
|---|---|
| ホスト出版物のタイトル | Proceedings of 2005 International Symposium on Intelligent Signal Processing and Communication Systems, ISPACS 2005 |
| ページ | 69-72 |
| ページ数 | 4 |
| 巻 | 2005 |
| 出版物ステータス | Published - 2005 |
| イベント | 2005 International Symposium on Intelligent Signal Processing and Communication Systems, ISPACS 2005 - Hong Kong 継続期間: 2005 12 13 → 2005 12 16 |
Other
| Other | 2005 International Symposium on Intelligent Signal Processing and Communication Systems, ISPACS 2005 |
|---|---|
| 市 | Hong Kong |
| 期間 | 05/12/13 → 05/12/16 |
Fingerprint
ASJC Scopus subject areas
- Engineering(all)
これを引用
Surface curvature based automatic human face feature extraction. / Wang, Jing; Zhang, Vanning; Goto, Satoshi.
Proceedings of 2005 International Symposium on Intelligent Signal Processing and Communication Systems, ISPACS 2005. 巻 2005 2005. p. 69-72 1595348.研究成果: Conference contribution
}
TY - GEN
T1 - Surface curvature based automatic human face feature extraction
AU - Wang, Jing
AU - Zhang, Vanning
AU - Goto, Satoshi
PY - 2005
Y1 - 2005
N2 - 3D face models provide more robust shape information of facial features than intensity or color in 2D images. However, many current facial feature extraction methods on 3D face models still depend on human instruction. This paper proposes an automatic human face feature extraction method adaptive to 3D face models in various poses and various scales based on analysis of surface curvature and a priori knowledge of human face structure. Moreover, during processing of segmented regions on 3D model, a novel region processing approach, called "Combine and Split", is proposed to significantly reduce undependable candidate regions for facial organs from hundreds to around ten. Experimental results demonstrate that proposed method can effectively extract eye, nose, mouth and ear regions from various 3D face models.
AB - 3D face models provide more robust shape information of facial features than intensity or color in 2D images. However, many current facial feature extraction methods on 3D face models still depend on human instruction. This paper proposes an automatic human face feature extraction method adaptive to 3D face models in various poses and various scales based on analysis of surface curvature and a priori knowledge of human face structure. Moreover, during processing of segmented regions on 3D model, a novel region processing approach, called "Combine and Split", is proposed to significantly reduce undependable candidate regions for facial organs from hundreds to around ten. Experimental results demonstrate that proposed method can effectively extract eye, nose, mouth and ear regions from various 3D face models.
UR - http://www.scopus.com/inward/record.url?scp=33847182812&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=33847182812&partnerID=8YFLogxK
M3 - Conference contribution
AN - SCOPUS:33847182812
SN - 0780392663
SN - 9780780392663
VL - 2005
SP - 69
EP - 72
BT - Proceedings of 2005 International Symposium on Intelligent Signal Processing and Communication Systems, ISPACS 2005
ER -