Two-dimensional maximum local variation based on image euclidean distance for face recognition
Manifold learning concerns the local manifold structure of high dimensional data, and many related algorithms are developed to improve image classification performance. None of them, however, consider both the relationships among pixels in images and the geometrical properties of various images duri...
| Publié dans: | IEEE transactions on image processing : a publication of the IEEE Signal Processing Society. - 1992. - 22(2013), 10 vom: 14. Okt., Seite 3807-17 |
|---|---|
| Auteur principal: | |
| Autres auteurs: | , , , |
| Format: | Article en ligne |
| Langue: | English |
| Publié: |
2013
|
| Accès à la collection: | IEEE transactions on image processing : a publication of the IEEE Signal Processing Society |
| Sujets: | Journal Article Research Support, Non-U.S. Gov't |
| Résumé: | Manifold learning concerns the local manifold structure of high dimensional data, and many related algorithms are developed to improve image classification performance. None of them, however, consider both the relationships among pixels in images and the geometrical properties of various images during learning the reduced space. In this paper, we propose a linear approach, called two-dimensional maximum local variation (2DMLV), for face recognition. In 2DMLV, we encode the relationships among pixels in images using the image Euclidean distance instead of conventional Euclidean distance in estimating the variation of values of images, and then incorporate the local variation, which characterizes the diversity of images and discriminating information, into the objective function of dimensionality reduction. Extensive experiments demonstrate the effectiveness of our approach |
|---|---|
| Description: | Date Completed 01.04.2014 Date Revised 02.09.2013 published: Print-Electronic Citation Status MEDLINE |
| ISSN: | 1941-0042 |
| DOI: | 10.1109/TIP.2013.2262286 |