Color Image Super-Resolution Reconstruction Based on Sparse Representation

Shen, Min; Zhang, Long Shan; Fu, Huai Zheng

doi:10.4028/www.scientific.net/amm.278-280.1221

Cited by 3 publications

(4 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Belekos et al proposed multi channel video super resolution in [31] and general color dictionary learning for image restoration is proposed in [32]- [34]. Other methods that use color channel information are proposed in [35]- [42].…”

Section: B Motivation and Contributionsmentioning

confidence: 99%

Sparsity-Based Color Image Super Resolution via Exploiting Cross Channel Constraints

Mousavi

Monga

2017

IEEE Trans. on Image Process.

View full text Add to dashboard Cite

Sparsity constrained single image super-resolution (SR) has been of much recent interest. A typical approach involves sparsely representing patches in a low-resolution (LR) input image via a dictionary of example LR patches, and then using the coefficients of this representation to generate the high-resolution (HR) output via an analogous HR dictionary. However, most existing sparse representation methods for SR focus on the luminance channel information and do not capture interactions between color channels. In this paper, we extend sparsity-based SR to multiple color channels by taking the color information into account. Edge similarities amongst RGB color bands are exploited as cross channel correlation constraints. These additional constraints lead to a new optimization problem, which is not easily solvable; however, a tractable solution is proposed to solve it efficiently. Moreover, to fully exploit the complementary information among color channels, a dictionary learning method is also proposed specifically to learn color dictionaries that encourage edge similarities. Merits of the proposed method over state of the art are demonstrated both visually and quantitatively using image quality metrics.

show abstract

Section: B Motivation and Contributionsmentioning

confidence: 99%

Sparsity-Based Color Image Super Resolution via Exploiting Cross Channel Constraints

Mousavi

Monga

2017

IEEE Trans. on Image Process.

View full text Add to dashboard Cite

show abstract

“…7, No. 2;2014 effective in CubeSat applications. The CPBD metric, which is based on human blur perception for varying contrast values, exhibits better consistency as a performance metric to evaluate different distortion types.…”

Section: Resultsmentioning

confidence: 99%

“…7, No. 2;2014 difference-of-Gaussian (DoG) images are computed from adjacent Gaussian-blurred images in each octave. After the DoG images are obtained, candidate keypoints are identified as local extrema of DoG images across the scales.…”

Section: Algorithmmentioning

confidence: 99%

“…Park et al (2003)gives an overview of several SR algorithms available in the literature. Some of the latest contributions include color image super-resolution reconstruction based on sparse representation proposed by Kim (Shen, Zhang, & Fu, Jan. 2013) and morphable model space-based face super-resolution reconstruction and recognition by Zhang (D. Zhang, He, & Du, 2012). Such SR algorithms have been successfully applied to areas such as digital photography, surveillance, and machine vision.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Robust Spatial-Domain Based Super-Resolution Mosaicing of CubeSat Video Frames: Algorithm and Evaluation

Ghosh¹,

Kaabouch²,

Fevig³

2014

CIS

View full text Add to dashboard Cite

In this paper, a spatial domain based super-resolution mosaicing system and its evaluation results are presented. This algorithm incorporates two main algorithms, an image mosaicing algorithm and a super-resolution-reconstruction algorithm. Huber-based prior information is used to address the ill-posed nature of the super resolution problem. To test the efficiency of the proposed algorithm, four performance metrics are used: mean square error, peak signal-to-noise ratio, singular value decomposition based measure, and cumulative probability of blur detection. Testing is performed using datasets generated from both a high altitude balloon and an Unmanned Aerial Vehicle (UAV). Results show that the proposed algorithm is highly efficient in real-time applications, such as remote sensing on a small satellite (i.e., CubeSat.) Furthermore, the performance metrics are proven to be accurate in quantitative evaluation.

show abstract

A deep residual compensation extreme learning machine and applications

Chen

Xie

Zhang

et al. 2020

Journal of Forecasting

View full text Add to dashboard Cite

The extreme learning machine (ELM) is a type of machine learning algorithm for training a single hidden layer feedforward neural network. Randomly initializing the weight between the input layer and the hidden layer and the threshold of each hidden layer neuron, the weight matrix of the hidden layer can be calculated by the least squares method. The efficient learning ability in ELM makes it widely applicable in classification, regression, and more. However, owing to some unutilized information in the residual, there are relatively huge prediction errors involving ELM. In this paper, a deep residual compensation extreme learning machine model (DRC‐ELM) of multilayer structures applied to regression is presented. The first layer is the basic ELM layer, which helps in obtaining an approximation of the objective function by learning the characteristics of the sample. The other layers are the residual compensation layers in which the learned residual is corrected layer by layer to the predicted value obtained in the previous layer by constructing a feature mapping between the input layer and the output of the upper layer. This model is applied to two practical problems: gold price forecasting and airfoil self‐noise prediction. We used the DRC‐ELM with 50, 100, and 200 residual compensation layers respectively for experiments, which show that DRC‐ELM does better in generalization and robustness than classical ELM, improved ELM models such as GA‐RELM and OS‐ELM, and other traditional machine learning algorithms such as support vector machine (SVM) and back‐propagation neural network (BPNN).

show abstract

Color Image Super-Resolution Reconstruction Based on Sparse Representation

Cited by 3 publications

References 7 publications

Sparsity-Based Color Image Super Resolution via Exploiting Cross Channel Constraints

Sparsity-Based Color Image Super Resolution via Exploiting Cross Channel Constraints

Robust Spatial-Domain Based Super-Resolution Mosaicing of CubeSat Video Frames: Algorithm and Evaluation

A deep residual compensation extreme learning machine and applications

Contact Info

Product

Resources

About