Partial Face Recognition: Alignment-Free Approach

By Shengcai Liao, Anil K. Jain, S. Li. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2013

308 citations recorded by the source corpus.

Numerous methods have been developed for holistic face recognition with impressive performance. However, few studies have tackled how to recognize an arbitrary patch of a face image. Partial faces frequently appear in unconstrained scenarios, with images captured by surveillance cameras or handheld devices (e.g., mobile phones) in particular. In this paper, we propose a general partial face recognition approach that does not require face alignment by eye coordinates or any other fiducial points. We develop an alignment-free face representation method based on Multi-Keypoint Descriptors (MKD), where the descriptor size of a face is determined by the actual content of the image. In this way, any probe face image, holistic or partial, can be sparsely represented by a large dictionary of gallery descriptors. A new keypoint descriptor called Gabor Ternary Pattern (GTP) is also developed for robust and discriminative face recognition. Experimental results are reported on four public domain face databases (FRGCv2.0, AR, LFW, and PubFig) under both the open-set identification and verification scenarios. Comparisons with two leading commercial face recognition SDKs (PittPatt and FaceVACS) and two baseline algorithms (PCA+LDA and LBP) show that the proposed method, overall, is superior in recognizing both holistic and partial faces without requiring alignment.

Subfields: Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/a769060e51db4874cfc30f84d9b3b6aead1812bc

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. Xiaogang Wang
3. Yi Yang
4. Shaogang Gong
5. Tao A. Xiang
6. Luc Van Gool
7. Qi Tian
8. Liang Zheng

Citations in the corpus

• Pose-Guided Feature Alignment for Occluded Person Re-Identification (2019, methodology): “We compare the results on Partial-REID and Partial-iLIDS with several existing partial person re-id methods, including MTRC [19], AMC+SWM [45], DSR [11], and SFR [12].”
• A Comprehensive Survey on Pose-Invariant Face Recognition (2015, background): “Another group of learning-based approaches is based on the face similarity of one face image to N template subjects [M¨uller et al. 2007; Schroff et al. 2011; Liao et al. 2013b].”
• Deep Spatial Feature Reconstruction for Partial Person Re-identification: Alignment-free Approach (2018, methodology): “Motivated by the remarkable successes achieved by dictionary learning in face recognition [12, 22, 27], we develop an end-to-end model named Deep Spatial feature Reconstruction (DSR), which expects that each pixel in the probe spatial maps can be sparsely reconstructed on the basis of spatial maps o”
• Face Recognition Systems: A Survey (2020, background): “They are more sensitive to facial expressions, occlusions, and pose [1].”
• Partial Person Re-Identification (2015, methodology): “It shows that our proposed method (AMC, denoted in red bar) can retrieve more similar patches from the right gallery person image against clutter background, compared to the standard sparse method without ambiguity modelling (MTSR [17], denoted in blue) .”