Facial feature extraction based on private energy map in DCT domain

被引:7
作者
Kim, Ki Hyun
Chung, Yun-Su
Ybo, Jang-Hee
Ro, Yong Man
机构
[1] ETRI, Informat Secur Res Div, Taejon, South Korea
[2] ICU, Sch Engn, Taejon, South Korea
关键词
face recognition; private energy map; energy probability; discrete cosine transform;
D O I
10.4218/etrij.07.0206.0218
中图分类号
TM [电工技术]; TN [电子技术、通信技术];
学科分类号
0808 ; 0809 ;
摘要
This letter presents a new feature extraction method based on the private energy map (PEM) technique to utilize the energy characteristics of a facial image. Compared with a non-facial image, a facial image shows large energy congestion in special regions of discrete cosine transform (DCT) coefficients. The PEM is generated by energy probability of the DCT coefficients of facial images. In experiments, higher face recognition performance figures of 100% for the ORL database and 98.8% for the ETRI database have been achieved.
引用
收藏
页码:243 / 245
页数:3
相关论文
共 4 条
[1]   PCA and LDA in DCT domain [J].
Chen, WL ;
Er, MJ ;
Wu, SQ .
PATTERN RECOGNITION LETTERS, 2005, 26 (15) :2474-2482
[2]   A probabilistic network for facial feature verification [J].
Choi, KH ;
Yoo, JJ ;
Hwang, TH ;
Park, JH ;
Lee, JH .
ETRI JOURNAL, 2003, 25 (02) :140-143
[3]   Efficient content-based image retrieval methods using color and texture [J].
Lee, SM ;
Bae, HJ ;
Jung, SH .
ETRI JOURNAL, 1998, 20 (03) :272-283
[4]  
Pratt W.K., 2001, DIGITAL IMAGE PROCES