Face recognition from a single image per person: A survey

By Xiaoyang Tan, Songcan Chen, Zhi-Hua Zhou, Fuyan Zhang. 2006

753 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, Signal Processing

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. Han-Jia Ye
4. Ming-Hsuan Yang
5. De-chuan Zhan
6. Xiaogang Wang
7. Lei Zhang
8. Jiwen Lu

In Signal Processing

1. Dacheng Tao
2. Changxing Ding
3. Jiwen Lu
4. Yi Ma
5. Mislav Grgic
6. Sonja Grgic
7. Kresimir Delac
8. Xiaozheng Zhang

Citations in the corpus

• Few-Shot Class-Incremental Learning by Sampling Multi-Phase Tasks (2022, background): “For example, when training an incremental model for face recognition, users are unwilling to upload copious images [20]; when training a model to classify rare birds, their images are challenging to collect.”
• Discriminative multi-manifold analysis for face recognition from a single training sample per person (2011, background): “To address the SSPP problem in face recognition, there have been some attempts in the literature, which can be mainly classified into three categories [27]: generic learning, virtual sample generation, and image partitioning.”
• Few-shot learning with adaptively initialized task optimizer: a practical meta-learning approach (2019, background): “…a few reference examples (Wang et al. 2018b); it is cumbersome to require a user recording multiple facial expressions into a system in advance (Tan et al. 2006); for a robot, imitating from one single demonstration of human must become a fantastic characteristic (Finn et al. 2017b).”
• LOTS about attacking deep features (2016, background): “Automatic face recognition has a long history and many different approaches have been proposed in the literature [26, 8, 20, 6].”
• Toward a Practical Face Recognition System: Robust Alignment and Illumination by Sparse Representation (2012, background): “changes, LBP has achieved the state-of-the-art face recognition performance in the scenario when only one sample per person is used for training [38].”
• A Comprehensive Survey on Pose-Invariant Face Recognition (2015, methodology): “To name a few, good surveys exist for illumination-invariant face recognition [Zou et al. 2007], 3D face recognition [Bowyer et al. 2006], single image-based face recognition [Tan et al. 2006], video-based face recognition [Barr et al. 2012], and heterogeneous face recognition [Ouyang et al. 2014].”
• SCface – surveillance cameras face database (2011, background): “Many papers are written and many real-world systems are being developed and distributed [1, 12, 19, 22].”
• A Comparative Study of Local Matching Approach for Face Recognition (2007, background): “Due to increasing interest, in recent surveys stand-alone sections were specifically devoted to local matching methods [43], [54].”
• Face recognition across pose: A review (2009, background): “As holistic face recognition approaches, both FDA and PCA are very sensitive to pose variations [21], because in-depth rotations of 3D human faces almost always cause misalignment of image pixels which are the only classification clues for these holistic approaches.”