Class distance weighted locality preserving projection for automatic age estimation

Kazuya Ueki, Masakazu Miya, Tetsuji Ogawa, Tetsunori Kobayashi

研究成果: Conference contribution

6 被引用数 (Scopus)

抄録

We have developed new dimensionality reduction methods, extended from locality preserving projection (LPP), to estimate age using facial images. LPP seeks a linear transformation matrix such that optimally preserves the neighborhood structure of the data. Our focus has been on expanding LPP by making use of class label information. Specifically, one of our ideas is to assign weights only to the data with close class labels. A local scaling method is used for each class to compute the LPP affinity matrix. Another idea is to assign large weights to two samples with close class labels, i.e., close ages. By doing this, class label information for original data (i.e., age information) can be preserved. We thus call this "class distance weighted linear preserving projection" (CDLPP). Experimental results on a large database showed that CDLPP has more discriminative power than conventional methods such as PCA and LPP.

本文言語English
ホスト出版物のタイトルBTAS 2008 - IEEE 2nd International Conference on Biometrics
ホスト出版物のサブタイトルTheory, Applications and Systems
DOI
出版ステータスPublished - 2008 12 1
イベントBTAS 2008 - IEEE 2nd International Conference on Biometrics: Theory, Applications and Systems - Arlington, VA, United States
継続期間: 2008 9 292008 10 1

出版物シリーズ

名前BTAS 2008 - IEEE 2nd International Conference on Biometrics: Theory, Applications and Systems

Conference

ConferenceBTAS 2008 - IEEE 2nd International Conference on Biometrics: Theory, Applications and Systems
CountryUnited States
CityArlington, VA
Period08/9/2908/10/1

ASJC Scopus subject areas

  • Biotechnology

フィンガープリント 「Class distance weighted locality preserving projection for automatic age estimation」の研究トピックを掘り下げます。これらがまとまってユニークなフィンガープリントを構成します。

引用スタイル