SRLSP: A Face Image Super-Resolution Algorithm Using Smooth Regression With Local Structure Prior

Jiang, Junjun; Chen, Chen; Ma, Jiayi; Wang, Zheng; Wang, Zhongyuan; Hu, Ruimin

doi:10.1109/tmm.2016.2601020

Cited by 141 publications

(48 citation statements)

References 72 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In the experiments, the intensity values of images are converted to the range from 0 (black) to 1 (white) for convenience. We will compare the results of the proposed method with several state-of-art baselines (e.g., LSR [19], WASR [25], LINE [26], SRLSP [28], VDSR [41] and LCGE [37]) in order to validate the effectiveness.…”

Section: Resultsmentioning

confidence: 99%

“…Manifold learning methods were further considered in [26] [27] to preserve the local geometry of image patches. The authors of [28] and [32] learned linear projection models from the training set in order to estimate the details of HR images. Zeng and Huang [33] expanded the training data for improving the quality of face hallucination results.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Hallucinating Face Image by Regularization Models in High-Resolution Feature Space

Shi

Liu

Zong

et al. 2018

IEEE Trans. on Image Process.

View full text Add to dashboard Cite

In this paper, we propose two novel regularization models in patch-wise and pixel-wise respectively, which are efficient to reconstruct high-resolution (HR) face image from low-resolution (LR) input. Unlike the conventional patch-based models which depend on the assumption of local geometry consistency in LR and HR spaces, the proposed method directly regularizes the relationship between the target patch and corresponding training set in the HR space. It avoids to deal with the tough problem of preserving local geometry in various resolutions. Taking advantage of kernel function in efficiently describing intrinsic features, we further conduct the patch-based reconstruction model in the high-dimensional kernel space for capturing nonlinear characteristics. Meanwhile, a pixel-based model is proposed to regularize the relationship of pixels in the local neighborhood, which can be employed to enhance the fuzzy details in the target HR face image. It privileges the reconstruction of pixels along the dominant orientation of structure, which is useful for preserving high-frequency information on complex edges. Finally, we combine the two reconstruction models into a unified framework. The output HR face image can be finally optimized by performing an iterative procedure. Experimental results demonstrate that the proposed face hallucination method produces superior performance than the state-of-the-art methods.

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Hallucinating Face Image by Regularization Models in High-Resolution Feature Space

Shi

Liu

Zong

et al. 2018

IEEE Trans. on Image Process.

View full text Add to dashboard Cite

show abstract

“…It reaches the best performance when the patch size is set to 12 in the FEI database [36] with training sample size of 360. been proposed to iteratively obtain the patch representation and perform neighbor embedding or learn the mapping in correlation spaces [15], [28], [29], [30]. Based on LcR, recently, the low-rank and self-similarity priors are also introduced to regularize patch representation in [31], [32], [33]. In [34], Pei et al incorporated the gradient information of face image to further regularize the patch representation.…”

Section: Introductionmentioning

confidence: 99%

Context-Patch Face Hallucination Based on Thresholding Locality-Constrained Representation and Reproducing Learning

Jiang

Tang

et al. 2020

IEEE Trans. Cybern.

Self Cite

View full text Add to dashboard Cite

Face hallucination is a technique that reconstruct high-resolution (HR) faces from low-resolution (LR) faces, by using the prior knowledge learned from HR/LR face pairs. Most state-of-the-arts leverage position-patch prior knowledge of human face to estimate the optimal representation coefficients for each image patch. However, they focus only the position information and usually ignore the context information of image patch. In addition, when they are confronted with misalignment or the Small Sample Size (SSS) problem, the hallucination performance is very poor. To this end, this study incorporates the contextual information of image patch and proposes a powerful and efficient context-patch based face hallucination approach, namely Thresholding Locality-constrained Representation and Reproducing learning (TLcR-RL). Under the context-patch based framework, we advance a thresholding based representation method to enhance the reconstruction accuracy and reduce the computational complexity. To further improve the performance of the proposed algorithm, we propose a promotion strategy called reproducing learning. By adding the estimated HR face to the training set, which can simulates the case that the HR version of the input LR face is present in the training set, thus iteratively enhancing the final hallucination result. Experiments demonstrate that the proposed TLcR-RL method achieves a substantial increase in the hallucinated results, both subjectively and objectively. Additionally, the proposed framework is more robust to face misalignment and the SSS problem, and its hallucinated HR face is still very good when the LR test face is from the real-world. The MATLAB source code is available at https://github.com/junjun-jiang/TLcR-RL.

show abstract

“…neutral and smile) or resolution. The SRC methods may fail in these cases because of the insufficiency of the labeled samples to model nuisance variables [8]- [12].…”

Section: Introductionmentioning

confidence: 99%

Semi-Supervised Sparse Representation Based Classification for Face Recognition With Insufficient Labeled Samples

Gao

Yuille

2017

IEEE Trans. on Image Process.

Self Cite

226

View full text Add to dashboard Cite

This paper addresses the problem of face recognition when there is only few, or even only a single, labeled examples of the face that we wish to recognize. Moreover, these examples are typically corrupted by nuisance variables, both linear (i.e., additive nuisance variables, such as bad lighting and wearing of glasses) and non-linear (i.e., non-additive pixel-wise nuisance variables, such as expression changes). The small number of labeled examples means that it is hard to remove these nuisance variables between the training and testing faces to obtain good recognition performance. To address the problem, we propose a method called semi-supervised sparse representation-based classification. This is based on recent work on sparsity, where faces are represented in terms of two dictionaries: a gallery dictionary consisting of one or more examples of each person, and a variation dictionary representing linear nuisance variables (e.g., different lighting conditions and different glasses). The main idea is that: 1) we use the variation dictionary to characterize the linear nuisance variables via the sparsity framework and 2) prototype face images are estimated as a gallery dictionary via a Gaussian mixture model, with mixed labeled and unlabeled samples in a semi-supervised manner, to deal with the non-linear nuisance variations between labeled and unlabeled samples. We have done experiments with insufficient labeled samples, even when there is only a single labeled sample per person. Our results on the AR, Multi-PIE, CAS-PEAL, and LFW databases demonstrate that the proposed method is able to deliver significantly improved performance over existing methods.

show abstract

SRLSP: A Face Image Super-Resolution Algorithm Using Smooth Regression With Local Structure Prior

Cited by 141 publications

References 72 publications

Hallucinating Face Image by Regularization Models in High-Resolution Feature Space

Hallucinating Face Image by Regularization Models in High-Resolution Feature Space

Context-Patch Face Hallucination Based on Thresholding Locality-Constrained Representation and Reproducing Learning

Semi-Supervised Sparse Representation Based Classification for Face Recognition With Insufficient Labeled Samples

Contact Info

Product

Resources

About