Image Set-Based Collaborative Representation for Face Recognition

Zhu, Pengfei; Zuo, Wangmeng; Zhang, Lei; Shiu, Simon

doi:10.1109/tifs.2014.2324277

Cited by 123 publications

(6 citation statements)

References 43 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…These modeling methods usually rely on learning of sparse or collaborative representation coefficients. For instance, in the ISCRC [3] algorithm, each probe image set or video was modeled as affine or convex hulls; then, these models were collaboratively reconstructed using all gallery image sets or videos. In the RNP [4] algorithm, the image sets were also modeled as affine hulls.…”

Section: Dynamic Modeling Methodsmentioning

confidence: 99%

“…So far, many research works have been made in computer vision [7][8][9][10][11], especially in the image set classification [1][2][3][4][12][13][14][15][16][17][18] field. In this subsection, as shown in Figure 2, we briefly review two types of image set classification methods: static and dynamic modeling methods.…”

Section: Image Set Classificationmentioning

confidence: 99%

“…Classical dynamic modeling methods include Image-Set-based Collaborative Representation and Classification (ISCRC) [3], Regularized Nearest Points (RNP) [4], etc. With this type of method, sparse representation or collaborative representation is usually used to simultaneously learn the representation coefficients (which is also known as dynamic modeling) and the distance between different image sets.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Manifolds-Based Low-Rank Dictionary Pair Learning for Efficient Set-Based Video Recognition

et al. 2023

View full text Add to dashboard Cite

As an important research direction in image and video processing, set-based video recognition requires speed and accuracy. However, the existing static modeling methods focus on computational speed but ignore accuracy, whereas the dynamic modeling methods are higher-accuracy but ignore the computational speed. Combining these two types of methods to obtain fast and accurate recognition results remains a challenging problem. Motivated by this, in this study, a novel Manifolds-based Low-Rank Dictionary Pair Learning (MbLRDPL) method was developed for a set-based video recognition/image set classification task. Specifically, each video or image set was first modeled as a covariance matrix or linear subspace, which can be seen as a point on a Riemannian manifold. Second, the proposed MbLRDPL learned discriminative class-specific synthesis and analysis dictionaries by clearly imposing the nuclear norm on the synthesis dictionaries. The experimental results show that our method achieved the best classification accuracy (100%, 72.16%, 95%) on three datasets with the fastest computing time, reducing the errors of state-of-the-art methods (JMLC, DML, CEBSR) by 0.96–75.69%.

show abstract

Section: Dynamic Modeling Methodsmentioning

confidence: 99%

Section: Image Set Classificationmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Manifolds-Based Low-Rank Dictionary Pair Learning for Efficient Set-Based Video Recognition

et al. 2023

View full text Add to dashboard Cite

show abstract

“…In solving the nonlinear problems encountered in image classification, the KAHISD/KCHISD of the Cevikalp and Triggs [31] article is an extension of the affine/convex hull-based image classification task to its kernel version. Zhu et al [32] proposed the KCH-ISCRC with kernel tricks, which well addresses collaborative image set-based representation and classification (ISCRC). It is easy to see that Gaussian kernels can successfully solve nonlinear problems in various applications [28,29,31,32].…”

Section: Related Workmentioning

confidence: 99%

Kernel Reverse Neighborhood Discriminant Analysis

Tan

Feng

et al. 2023

Electronics

View full text Add to dashboard Cite

Currently, neighborhood linear discriminant analysis (nLDA) exploits reverse nearest neighbors (RNN) to avoid the assumption of linear discriminant analysis (LDA) that all samples from the same class should be independently and identically distributed (i.i.d.). nLDA performs well when a dataset contains multimodal classes. However, in complex pattern recognition tasks, such as visual classification, the complex appearance variations caused by deformation, illumination and visual angle often generate non-linearity. Furthermore, it is not easy to separate the multimodal classes in lower-dimensional feature space. One solution to these problems is to map the feature to a higher-dimensional feature space for discriminant learning. Hence, in this paper, we employ kernel functions to map the original data to a higher-dimensional feature space, where the nonlinear multimodal classes can be better classified. We give the details of the deduction of the proposed kernel reverse neighborhood discriminant analysis (KRNDA) with the kernel tricks. The proposed KRNDA outperforms the original nLDA on most datasets of the UCI benchmark database. In high-dimensional visual recognition tasks of handwritten digit recognition, object categorization and face recognition, our KRNDA achieves the best recognition results compared to several sophisticated LDA-based discriminators.

show abstract

“…The attainment of effectiveness in set based facial recognition methodologies relies on the consideration of two pivotal factors: the selection of models tasked with approximating facial image sets, and the discernment of an appropriate distance metric designated for the quantification of similarity among these models. In this vein, a multitude of distinct models for image sets have been introduced, encompassing linear and affine subspaces [1][2][3][4], convex hulls [1,5,6], Gaussian mixture models [7], Grassmannian manifolds [8,9], as well as manifolds comprised of symmetric positive definite (SPD) matrices [10,11]. These model formulations have been advanced to approximate image sets while concurrently establishing congruous similarity metrics tailored to each respective model instantiation.…”

Section: Introductionmentioning

confidence: 99%

Discriminative Frontal Face Synthesis by Using Attention and Metric Learning

Cevikalp,

Turgut,

Topal

2024

Preprint

View full text Add to dashboard Cite

This paper introduces a novel approach for obtaining distinctive frontal facial representations from collections of multiple facial images. The primary objective is to ensure that the profound features extracted through a deep Convolutional Neural Network (CNN) from these learned facial representations exhibit notable separability within the feature space. The acquisition of frontal facial representations capable of effectively representing entire sets of images holds significant value as it considerably reduces the number of image samples requiring processing. This acceleration proves especially advantageous during the classification testing phase. The proposed method combines three fundamental components: attention mechanisms, adversarial methodologies, and metric learning strategies. We adopt a U-Net architecture enhanced by attention modules for the facial aggregation network that generates frontal faces that approximate multiple face images within image sets. Furthermore, we employ both a discriminator network and a pre-trained facial classification network to successfully achieve the goals of adversarial and metric learning. The experimental studies on different face recognition datasets demonstrate that using only attention mechanisms and metric learning strategy is sufficient to synthesize discriminative frontal face images yielding high classification accuracies.

show abstract

Image Set-Based Collaborative Representation for Face Recognition

Cited by 123 publications

References 43 publications

Manifolds-Based Low-Rank Dictionary Pair Learning for Efficient Set-Based Video Recognition

Manifolds-Based Low-Rank Dictionary Pair Learning for Efficient Set-Based Video Recognition

Kernel Reverse Neighborhood Discriminant Analysis

Discriminative Frontal Face Synthesis by Using Attention and Metric Learning

Contact Info

Product

Resources

About