Eigenface-domain super-resolution for face recognition

By Bahadir K. Gunturk, A. U. Batur, Yucel Altunbasak, M. Hayes, R. Mersereau. 2003

357 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, Media Technology

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

1. Dacheng Tao
2. Luc Van Gool
3. Ming-Hsuan Yang
4. Chen Change Loy
5. Lei Zhang
6. Radu Timofte
7. Yun Raymond Fu
8. Xiaogang Wang

In Media Technology

1. Ferenc Huszár
2. Chao Dong
3. Wenzhe Shi
4. Xinbo Gao
5. Radu Timofte
6. Jose Caballero
7. Dacheng Tao
8. Yulun Zhang

Citations in the corpus

• A Comprehensive guide to Bayesian Convolutional Neural Network with Variational Inference (2019, background): “It is applicable to many areas like medical imaging [54], face recognition [21] and so on.”
• Real-Time Single Image and Video Super-Resolution Using an Efficient Sub-Pixel Convolutional Neural Network (2016, background): “This task, referred to as super-resolution (SR), finds direct applications in many areas such as HDTV [15], medical imaging [28, 33], satellite imaging [38], face recognition [17] and surveillance [53].”
• A Comprehensive Survey to Face Hallucination (2013, methodology): “Classical full reference metrics such as PSNR, MSE, and RMSE are holistic and cannot yet reflect the detailed information that is needed to assess image quality.”
• Very low resolution face recognition problem (2010, methodology): “[13] applied MAP-based SR method to reconstruct the eigenface coefficients for face recognition.”
• Real-Time Video Super-Resolution with Spatio-Temporal Networks and Motion Compensation (2016, background): “SR aims at recovering a high-resolution (HR) image or video from its low-resolution (LR) version, and finds direct applications ranging from medical imaging [38, 34] to satellite imaging [5], as well as facilitating tasks such as face recognition [13].”
• Dissimilarity-based people re-identification and search for intelligent video surveillance (2013, background): “As low resolution face images are not directly usable for recognition, many approaches attempted to address the problem through the obvious way of trying to increase image resolution, using super-resolution techniques [60, 66, 74, 118].”