Loading [MathJax]/extensions/TeX/ieeemacros.js
Synthesizing for face recognition | IEEE Conference Publication | IEEE Xplore

Synthesizing for face recognition

Publisher: IEEE

Abstract:

Pose variance is one of the most challenging problem to 2D face recognition. In this paper, a novel frontal view face synthesizing strategy is introduced to improve the p...View more

Abstract:

Pose variance is one of the most challenging problem to 2D face recognition. In this paper, a novel frontal view face synthesizing strategy is introduced to improve the performance of traditional face recognition methods on non-frontal view input images. Given several non-frontal input faces, our minimum bending synthesizing strategy automatically picks up and merges information, to realize most natural frontal view face synthesizing. It is shown by experiments that our strategy could effectively reduce the influence of pose variance to face recognition, and rather than traditional landmark based approaches, our strategy does not require perfect landmark locating results.
Date of Conference: 11-14 September 2011
Date Added to IEEE Xplore: 29 December 2011
ISBN Information:

ISSN Information:

Publisher: IEEE
Conference Location: Brussels, Belgium

References

References is not available for this document.