> 연구성과 > 국외저널
사용후기
책임교수 |
박강령 |
논문명 |
Comparative Study of Human Age Estimation with or without Preclassification of Gender and Facial Expression |
논문종류 |
SCI |
제1저자 |
Dat Tien Nguyen |
교신저자 |
Kang Ryoung Park |
공동저자 |
So Ra Cho, Kwang Yong Shin, Jae Won Bang |
Impact Factor |
1.219 |
개제학술지명 |
THE SCIENTIFIC WORLD JOURNAL |
Keyword |
human age estimation; in-plane rotation; multi-level local binary pattern; preclassification of gender and facial expression |
게재일 |
2014 년 09 월 |
Age estimation has many useful applications, such as age-based face classification, finding lost children, surveillance monitoring, and face recognition invariant to age progression. Among many factors affecting age estimation accuracy, gender and facial expression can have negative effects. In our research, the effects of gender and facial expression on age estimation using support vector regression (SVR) method are investigated. Our research is novel in the following four ways. First, the accuracies of age estimation using a single-level local binary pattern (LBP) and a multilevel LBP (MLBP) are compared, and MLBP shows better performance as an extractor of texture features globally. Second, we compare the accuracies of age estimation using global features extracted byMLBP, local features extracted by Gabor filtering, and the combination of the twomethods. Results show that the third approach is the most accurate. Third, the accuracies of age estimation with and without preclassification of facial expression are compared and analyzed. Fourth, those with and without preclassification of gender are compared and analyzed. The experimental results show the effectiveness of gender preclassification in age estimation.
*ITRC 기여율 = 1