Paper Info
Title
Recognition at a long distance: Very low resolution face recognition and hallucination
Abstract
In real-world video surveillance applications, one often needs to recognize face images from a very long distance. Such recognition tasks are very challenging, since such images are typically with very low resolution (VLR). However, if one simply downsamples high-resolution (HR) training images for recognizing the VLR test inputs, or if one directly upsamples the VLR inputs for matching the HR training data, the resulting recognition performance would not be satisfactory. In this paper, we propose a joint face hallucination and recognition approach based on sparse representation. Given a VLR input image, our method is able to synthesize its person-specific HR version with recognition guarantees. In our experiments, we consider two different face image datasets. Empirical results will support the use of our approach for both VLR face recognition. In addition, compared to state-of-the-art super-resolution (SR) methods, we will also show that our method results in improved quality for the recovered HR face images.
Year
DOI
Venue
2015
10.1109/ICB.2015.7139090
2015 International Conference on Biometrics (ICB)
Keywords
Field
DocType
real-world video surveillance applications,face image recognition,very low resolution face recognition,high-resolution images,HR training image,face hallucination,sparse representation,VLR input image,face image datasets,VLR face recognition,super-resolution methods,SR methods,HR face image quality
Training set,Computer vision,Facial recognition system,Face hallucination,Three-dimensional face recognition,Pattern recognition,Computer science,Sparse approximation,Speech recognition,Artificial intelligence,Face detection,Image resolution
Conference
ISSN
Citations 
PageRank 
2376-4201
8
0.46
References 
Authors
16
4
Name
Order
Citations
PageRank
Min-Chun Yang11195.11
chiapo wei21767.66
Yi-Ren Yeh329814.38
Yu-Chiang Frank Wang491461.63