Facial feature extraction using gradient features and MQDF matching

Wataru Oyama; M. Shridhar; P. Watta

Facial feature extraction using gradient features and MQDF matching

Wataru Oyama, M. Shridhar, P. Watta

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Abstract

In this paper, we propose a novel approach for the extraction of facial features from frontal face images. The proposed approach involves 3 main processing stages. In the first stage, a bounding box is placed over the face. In the second stage, candidate positions for the facial features are identified using a set of MQDF-based distance functions. Finally, in the third stage, the candidate feature positions are evaluated using an MQDF-based verification function, and an optimal configuration is chosen. Results on the FERET database indicate that with a proper setting of parameters, the proposed algorithm can accurately extract facial features over many different scales.

Original language	English
Title of host publication	Proceedings of the 8th IASTED International Conference on Signal and Image Processing, SIP 2006
Pages	329-334
Number of pages	6
Publication status	Published - Dec 1 2006
Externally published	Yes
Event	8th IASTED International Conference on Signal and Image Processing, SIP 2006 and the 10th IASTED International Conference on Internet and Multimedia Systems and Applications, IMSA 2006 - Honolulu, HI, United States Duration: Aug 14 2006 → Aug 16 2006

Other

Other	8th IASTED International Conference on Signal and Image Processing, SIP 2006 and the 10th IASTED International Conference on Internet and Multimedia Systems and Applications, IMSA 2006
Country/Territory	United States
City	Honolulu, HI
Period	8/14/06 → 8/16/06

All Science Journal Classification (ASJC) codes

Computer Vision and Pattern Recognition
Signal Processing

Cite this

Oyama, W, Shridhar, M & Watta, P 2006, Facial feature extraction using gradient features and MQDF matching. in Proceedings of the 8th IASTED International Conference on Signal and Image Processing, SIP 2006. pp. 329-334, 8th IASTED International Conference on Signal and Image Processing, SIP 2006 and the 10th IASTED International Conference on Internet and Multimedia Systems and Applications, IMSA 2006, Honolulu, HI, United States, 8/14/06.

@inproceedings{f82cc14af9174a15ba8db34b542a08e0,

title = "Facial feature extraction using gradient features and MQDF matching",

abstract = "In this paper, we propose a novel approach for the extraction of facial features from frontal face images. The proposed approach involves 3 main processing stages. In the first stage, a bounding box is placed over the face. In the second stage, candidate positions for the facial features are identified using a set of MQDF-based distance functions. Finally, in the third stage, the candidate feature positions are evaluated using an MQDF-based verification function, and an optimal configuration is chosen. Results on the FERET database indicate that with a proper setting of parameters, the proposed algorithm can accurately extract facial features over many different scales.",

author = "Wataru Oyama and M. Shridhar and P. Watta",

year = "2006",

month = dec,

day = "1",

language = "English",

isbn = "0889865833",

pages = "329--334",

booktitle = "Proceedings of the 8th IASTED International Conference on Signal and Image Processing, SIP 2006",

note = "8th IASTED International Conference on Signal and Image Processing, SIP 2006 and the 10th IASTED International Conference on Internet and Multimedia Systems and Applications, IMSA 2006 ; Conference date: 14-08-2006 Through 16-08-2006",

}

TY - GEN

T1 - Facial feature extraction using gradient features and MQDF matching

AU - Oyama, Wataru

AU - Shridhar, M.

AU - Watta, P.

PY - 2006/12/1

Y1 - 2006/12/1

N2 - In this paper, we propose a novel approach for the extraction of facial features from frontal face images. The proposed approach involves 3 main processing stages. In the first stage, a bounding box is placed over the face. In the second stage, candidate positions for the facial features are identified using a set of MQDF-based distance functions. Finally, in the third stage, the candidate feature positions are evaluated using an MQDF-based verification function, and an optimal configuration is chosen. Results on the FERET database indicate that with a proper setting of parameters, the proposed algorithm can accurately extract facial features over many different scales.

AB - In this paper, we propose a novel approach for the extraction of facial features from frontal face images. The proposed approach involves 3 main processing stages. In the first stage, a bounding box is placed over the face. In the second stage, candidate positions for the facial features are identified using a set of MQDF-based distance functions. Finally, in the third stage, the candidate feature positions are evaluated using an MQDF-based verification function, and an optimal configuration is chosen. Results on the FERET database indicate that with a proper setting of parameters, the proposed algorithm can accurately extract facial features over many different scales.

UR - http://www.scopus.com/inward/record.url?scp=56549106027&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=56549106027&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:56549106027

SN - 0889865833

SN - 9780889865839

SP - 329

EP - 334

BT - Proceedings of the 8th IASTED International Conference on Signal and Image Processing, SIP 2006

T2 - 8th IASTED International Conference on Signal and Image Processing, SIP 2006 and the 10th IASTED International Conference on Internet and Multimedia Systems and Applications, IMSA 2006

Y2 - 14 August 2006 through 16 August 2006

ER -

Facial feature extraction using gradient features and MQDF matching

Abstract

Other

All Science Journal Classification (ASJC) codes

Other files and links

Fingerprint

Cite this