Title :
Robust low-resolution face identification and verification using high-resolution features
Author :
Hennings-Yeomans, Pablo H. ; Kumar, B. V K Vijaya ; Baker, Simon
Author_Institution :
Dept. of Biomed. Eng., Carnegie Mellon Univ., Pittsburgh, PA, USA
Abstract :
In this work, we elaborate on a rather intuitive hypothesis: face recognition of low-resolution faces can be improved if the processes of reconstruction and recognition are considered simultaneously, instead of sequentially, without feedback or any interaction. Given a high-resolution training set, matching low-resolution probe images with good accuracy is an open problem. We have recently introduced [Hennings-Yeomans, Baker, and Kumar, CVPR, June 2008] a new framework for low-resolution face recognition that uses models from an image formation process, super-resolution priors and face feature extraction methods. By measuring how well an intermediate super-resolution reconstruction of the probe image fits into the models used in the process, the proposed matching algorithm extracts new features for recognition. In this paper, we present results for an improved design of these new features. We show that the proposed algorithm improves performance in both, identification and verification tasks on a large database of 337 subjects that also captures illumination variations.
Keywords :
face recognition; feature extraction; image matching; image reconstruction; image resolution; face feature extraction methods; face recognition; face reconstruction; face verification; high-resolution features; image formation process; low-resolution probe image matching; probe image reconstruction; robust low-resolution face identification; super-resolution priors; super-resolution reconstruction; Face recognition; Feature extraction; Feedback; Image databases; Image recognition; Image reconstruction; Image resolution; Probes; Robustness; Spatial databases; Face recognition; biometrics; face models; feature extraction; super-resolution;
Conference_Titel :
Image Processing (ICIP), 2009 16th IEEE International Conference on
Conference_Location :
Cairo
Print_ISBN :
978-1-4244-5653-6
Electronic_ISBN :
1522-4880
DOI :
10.1109/ICIP.2009.5413920