Laplacian-Uniform Mixture-Driven Iterative Robust Coding With Applications to Face Recognition Against Dense Errors

Zheng, Huicheng; Da-jun, Lin; Lian, Lina; Dong, Jiayu; Zhang, Peipei

doi:10.1109/tnnls.2019.2945372

Cited by 8 publications

(9 citation statements)

References 65 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It is robust to severe illumination variation, occlusion and random pixel noise destruction [14] 2020 Solve the problem that robust statistics are not robust enough to dense coarse errors [15] 2013 Automatically utilize every area that is not covered [16] 2010 It has good illumination robustness…”

Section: Robust Error Codingmentioning

confidence: 99%

Research advanced in occluded face recognition

Zhou

Lei²,

Yuan

2023

Fifth International Conference on Computer Information Science and Artificial Intelligence (CISAI 2022)

View full text Add to dashboard Cite

The domain of computer vision's most popular study area has always been face recognition which aims to identify different face images and predict the corresponding identity information through feature analysis and modeling. In practical applications, a number of variables, including lighting, posture, and clarity, have an impact on facial recognition accuracy. Among them, the most challenging scene is occlusion face recognition, which will cause feature loss, local coherence and alignment errors to greatly inhibit the accuracy and generalization ability of the face model. Based on detailed literature research and analysis, this paper provides a comprehensive evaluation of the research progress of occluded face recognition. Specifically, based on the introduction of classical face recognition technology, we further discuss the design ideas, basic framework, advantages and disadvantages of representative occlusion face recognition methods from two aspects: robust feature extraction and robust classifier. Finally, we summarize the main challenges and give an outlook on the future research development of object detection.

show abstract

Section: Robust Error Codingmentioning

confidence: 99%

Research advanced in occluded face recognition

Zhou

Lei²,

Yuan

2023

Fifth International Conference on Computer Information Science and Artificial Intelligence (CISAI 2022)

View full text Add to dashboard Cite

show abstract

“…Yang et al (Yang et al 2016) converted the rank minimization problem into the nuclear norm minimization problem for optimization. Laplacian-uniform mixture-driven iterative robust coding (LUMIRC) (Zheng et al 2020) modeled the distribution of the reconstruction residuals with a Laplacian-uniform mixture function. Although their theoretical contributions are sound, the practical values are limited by the complexity in real-world scenarios.…”

Section: Related Workmentioning

confidence: 99%

MSML: Enhancing Occlusion-Robustness by Multi-Scale Segmentation-Based Mask Learning for Face Recognition

Yuan

Zheng

Dong³

2022

AAAI

Self Cite

View full text Add to dashboard Cite

In unconstrained scenarios, face recognition remains challenging, particularly when faces are occluded. Existing methods generalize poorly due to the distribution distortion induced by unpredictable occlusions. To tackle this problem, we propose a hierarchical segmentation-based mask learning strategy for face recognition, enhancing occlusion-robustness by integrating segmentation representations of occlusion into face recognition in the latent space. We present a novel multi-scale segmentation-based mask learning (MSML) network, which consists of a face recognition branch (FRB), an occlusion segmentation branch (OSB), and hierarchical elaborate feature masking (FM) operators. With the guidance of hierarchical segmentation representations of occlusion learned by the OSB, the FM operators can generate multi-scale latent masks to eliminate mistaken responses introduced by occlusions and purify the contaminated facial features at multiple layers. In this way, the proposed MSML network can effectively identify and remove the occlusions from feature representations at multiple levels and aggregate features from visible facial areas. Experiments on face verification and recognition under synthetic or realistic occlusions demonstrate the effectiveness of our method compared to state-of-the-art methods.

show abstract

“…Whereas, the low-rank modeling is unrealistic in practice when samples are subjected to disperse corruption. Recently, the half-quadratic (HQ) method and Laplacian-uniform mixture-driven iterative robust coding (LUMIRC) method were proposed for error detection and correction [ 32 , 33 ]. However, both of them neglected the fact that the robustness of the regression-based methods relies not only on the error estimator but also on the sparsity regularizer.…”

Section: Introductionmentioning

confidence: 99%

“…All the work analyzed above has a common intention of attempting to get rid of the flawed entries in the contaminated sample and obtain promising recognition performance with the partial pure entries [ 19 , 20 , 21 , 22 , 23 , 24 , 25 , 26 , 27 , 28 , 29 , 30 , 31 , 32 , 33 , 34 ]. However, when the features of different classes are similar, partial information is insufficient to support us to correctly distinguish one class from the others.…”

Section: Introductionmentioning

confidence: 99%

“…Correntropy was demonstrated to be particularly robust to non-Gaussian noises and large outliers was successfully applied for feature selection and signal processing [ 39 , 40 ]. Compared with the methods in [ 28 , 31 , 32 , 33 ] that detected errors in a heuristic way, correntropy provided a realistic metric approach that was theoretically promised to have desirable measure properties and approximate solution by the information theory and HQ optimization theory [ 40 ].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Correntropy-Induced Discriminative Nonnegative Sparse Coding for Robust Palmprint Recognition

Jing

Zhang

Song³

2020

Sensors

View full text Add to dashboard Cite

Palmprint recognition has been widely studied for security applications. However, there is a lack of in-depth investigations on robust palmprint recognition. Regression analysis being intuitively interpretable on robustness design inspires us to propose a correntropy-induced discriminative nonnegative sparse coding method for robust palmprint recognition. Specifically, we combine the correntropy metric and l1-norm to present a powerful error estimator that gains flexibility and robustness to various contaminations by cooperatively detecting and correcting errors. Furthermore, we equip the error estimator with a tailored discriminative nonnegative sparse regularizer to extract significant nonnegative features. We manage to explore an analytical optimization approach regarding this unified scheme and figure out a novel efficient method to address the challenging non-negative constraint. Finally, the proposed coding method is extended for robust multispectral palmprint recognition. Namely, we develop a constrained particle swarm optimizer to search for the feasible parameters to fuse the extracted robust features of different spectrums. Extensive experimental results on both contactless and contact-based multispectral palmprint databases verify the flexibility and robustness of our methods.

show abstract

Laplacian-Uniform Mixture-Driven Iterative Robust Coding With Applications to Face Recognition Against Dense Errors

Cited by 8 publications

References 65 publications

Research advanced in occluded face recognition

Research advanced in occluded face recognition

MSML: Enhancing Occlusion-Robustness by Multi-Scale Segmentation-Based Mask Learning for Face Recognition

Correntropy-Induced Discriminative Nonnegative Sparse Coding for Robust Palmprint Recognition

Contact Info

Product

Resources

About