Very low resolution face recognition problem

By Wilman W. W. Zou, Pong Chi Yuen. 2010

547 citations recorded by the source corpus.

Subfields: Computational Mechanics, 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 Computational Mechanics

1. Zhangyang Wang
2. Yong Xu
3. Tien-Ping Tan
4. Ying Tai
5. Zhen Lei
6. Yu Kong
7. Yanyun Qu
8. Thomas Baltzer Moeslund

In Computer Vision and Pattern Recognition

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

In Media Technology

1. Kai Zhang
2. Yulun Zhang
3. Lei Zhang
4. Radu Timofte
5. Chao Dong
6. Yun Raymond Fu
7. Wangmeng Zuo
8. Yapeng Tian

Citations in the corpus

• Effects of Degradations on Deep Neural Network Architectures (2018, background): “Zou and Yuen [8] addressed the same problem of face recogni-”
• Understanding how image quality affects deep neural networks (2016, background): “There are many works that attempt to recognize low-resolution faces [7], [8].”
• Image Super-Resolution Using Very Deep Residual Channel Attention Networks (2018, methodology): “Image SR is used in various computer vision applications, ranging from security and surveillance imaging [13], medical imaging [14] to object recognition [8].”
• Residual Dense Network for Image Restoration (2018, background): “Image restoration is used in various computer vision tasks, such as security and surveillance imaging [1], medical imaging [2], and image generation [3].”
• Super-resolution: a comprehensive survey (2014, background): “Super-resolution (SR) is a process for obtaining one or more High-Resolution (HR) images from one or more Low-Resolution (LR) observations [1]-[618].”
• Residual Dense Network for Image Super-Resolution (2018, methodology): “SISR is used in various computer vision tasks, such as security and surveillance imaging [38], medical imaging [22], and image generation [9].”
• Advancing Image Understanding in Poor Visibility Environments: A Collective Benchmark Study (2019, background): “In [135], the boundary where the face recognition performance is largely degraded is 16×16 pixels.”
• Meta-SR: A Magnification-Arbitrary Network for Super-Resolution (2019, background): “And it has very wide application on security and surveillance imaging [7, 36], medical imaging [22], as well as satellite and aerial imaging [31].”
• Low-Resolution Face Recognition in the Wild via Selective Knowledge Distillation (2018, background): “transforming both high-resolution and low-resolution faces into a unified feature space for matching [25]–[31], while in [32], [33] the multi-scale (multi-resolution) faces were simultaneously analyzed to extract better features.”
• Image Super-Resolution via Deep Recursive Residual Network (2017, background): “Since SISR restores the high-frequency information, it is widely used in applications such as medical imaging [26], satellite imaging [29], security and surveillance [37], where high-frequency details are greatly desired.”