Image super-resolution based on multi-grained cascade forests

2019 ◽  
Vol 17 (04) ◽  
pp. 1950019
Author(s):  
Yaming Wang ◽  
Zhikang Luo ◽  
Weqing Huang ◽  
Yonghua Han
Keyword(s):  
Super Resolution ◽  
Image Features ◽  
Divide And Conquer ◽  
Learning Ability ◽  
Generalization Capability ◽  
Reconstruction Process ◽  
High Quality Image ◽  
Reconstruction Quality ◽  
Image Super Resolution ◽  
The Many

Although neural networks are most commonly used in the field of image super-resolution (SR), methods based on decision trees are still discussed. These kinds of algorithm need less time to compute than others because of their simple structure but still yield high quality image SR. In this paper, we propose an SR algorithm using the multi-grained cascade forest (SRGCF) method. Our algorithm first uses multi-grained scanning to process the spatial relationships of image features, thus the representational learning ability is improved. During the reconstruction process, the image obtained by cascade forest training is used as the input of the next training, therefore, the image features are continuously emphasized. The training of the cascade forest ends when the evaluation value is optimal. Because the decision tree uses a divide-and-conquer strategy, the SR of an image is improved in an iterative manner simply and quickly. Compared with existing methods, our method not only avoids the tradeoff between reconstruction quality and run time, but also has a good generalization capability. It can be quickly applied to the many cases of image SR.

scholarly journals Single Image Super-Resolution: Depthwise Separable Convolution Super-Resolution Generative Adversarial Network

2020 ◽  
Vol 10 (1) ◽  
pp. 375 ◽  
Author(s):  
Zetao Jiang ◽  
Yongsong Huang ◽  
Lirui Hu
Keyword(s):  
Similarity Index ◽  
Super Resolution ◽  
Structural Similarity ◽  
Image Features ◽  
Single Image ◽  
Generative Adversarial Network ◽  
Visual Evaluation ◽  
Adversarial Network ◽  
Image Super Resolution ◽  
Single Image Super Resolution

The super-resolution generative adversarial network (SRGAN) is a seminal work that is capable of generating realistic textures during single image super-resolution. However, the hallucinated details are often accompanied by unpleasant artifacts. To further enhance the visual quality, we propose a deep learning method for single image super-resolution (SR). Our method directly learns an end-to-end mapping between the low/high-resolution images. The method is based on depthwise separable convolution super-resolution generative adversarial network (DSCSRGAN). A new depthwise separable convolution dense block (DSC Dense Block) was designed for the generator network, which improved the ability to represent and extract image features, while greatly reducing the total amount of parameters. For the discriminator network, the batch normalization (BN) layer was discarded, and the problem of artifacts was reduced. A frequency energy similarity loss function was designed to constrain the generator network to generate better super-resolution images. Experiments on several different datasets showed that the peak signal-to-noise ratio (PSNR) was improved by more than 3 dB, structural similarity index (SSIM) was increased by 16%, and the total parameter was reduced to 42.8% compared with the original model. Combining various objective indicators and subjective visual evaluation, the algorithm was shown to generate richer image details, clearer texture, and lower complexity.

scholarly journals Image Super-Resolution Based on Sparse Representation via Direction and Edge Dictionaries

2017 ◽  
Vol 2017 ◽  
pp. 1-11 ◽  
Author(s):  
Xuan Zhu ◽  
Xianxian Wang ◽  
Jun Wang ◽  
Peng Jin ◽  
Li Liu ◽  
...  
Keyword(s):  
Sparse Representation ◽  
Super Resolution ◽  
Training Image ◽  
Image Features ◽  
Single Image ◽  
Edge Structure ◽  
Image Patches ◽  
Image Super Resolution ◽  
Single Image Super Resolution ◽  
Edge Features

Sparse representation has recently attracted enormous interests in the field of image super-resolution. The sparsity-based methods usually train a pair of global dictionaries. However, only a pair of global dictionaries cannot best sparsely represent different kinds of image patches, as it neglects two most important image features: edge and direction. In this paper, we propose to train two novel pairs of Direction and Edge dictionaries for super-resolution. For single-image super-resolution, the training image patches are, respectively, divided into two clusters by two new templates representing direction and edge features. For each cluster, a pair of Direction and Edge dictionaries is learned. Sparse coding is combined with the Direction and Edge dictionaries to realize super-resolution. The above single-image super-resolution can restore the faithful high-frequency details, and the POCS is convenient for incorporating any kind of constraints or priors. Therefore, we combine the two methods to realize multiframe super-resolution. Extensive experiments on image super-resolution are carried out to validate the generality, effectiveness, and robustness of the proposed method. Experimental results demonstrate that our method can recover better edge structure and details.

scholarly journals A New Optimized Recurrent Feedback Deep Convolutional Neural Net for Image Super Resolution

2019 ◽  
Vol 8 (3) ◽  
pp. 5958-5965
Keyword(s):  
Structural Information ◽  
Super Resolution ◽  
Ground Truth ◽  
Cost Effective ◽  
Structural Similarity ◽  
Neural Net ◽  
Reconstruction Process ◽  
Network Activation ◽  
Image Super Resolution ◽  
A New Technique

Now-a-days many applications dealing with visual content need to access underlying details in the image or video of interest. For instance, detailing is required to take life critical decisions for further action plans by a doctor. Clarity and structural information are some of the aspects of detailing. It can be achieved by cost effective software solution like super resolution reconstruction of an image. Super resolution (SR) deals in increasing resolution of an image to make it more clear and valid for use. Many SR techniques exist with variable goals to achieve. With this intension a new technique for preserving structural information in the reconstruction process is proposed. The system extends a deep convolution neural network by adding a new optimization layer at the end of network activation layer. This new layer maintains permissible error threshold in the acquired signal and tries to improve the signal by feeding back latest reconstructed frame. The proposed system shows noticeable improvement in structural similarity of reconstructed images as compared with the ground truth.

scholarly journals Super-Resolution Network with Information Distillation and Multi-Scale Attention for Medical CT Image

Sensors ◽  
2021 ◽  
Vol 21 (20) ◽  
pp. 6870
Author(s):  
Tianliu Zhao ◽  
Lei Hu ◽  
Yongmei Zhang ◽  
Jianying Fang
Keyword(s):  
Super Resolution ◽  
Objective Evaluation ◽  
Learning Ability ◽  
Ct Image ◽  
Residual Network ◽  
Multi Scale ◽  
Series Of Experiments ◽  
Feature Information ◽  
Image Super Resolution ◽  
Feature Utilization

The CT image is an important reference for clinical diagnosis. However, due to the external influence and equipment limitation in the imaging, the CT image often has problems such as blurring, a lack of detail and unclear edges, which affect the subsequent diagnosis. In order to obtain high-quality medical CT images, we propose an information distillation and multi-scale attention network (IDMAN) for medical CT image super-resolution reconstruction. In a deep residual network, instead of only adding the convolution layer repeatedly, we introduce information distillation to make full use of the feature information. In addition, in order to better capture information and focus on more important features, we use a multi-scale attention block with multiple branches, which can automatically generate weights to adjust the network. Through these improvements, our model effectively solves the problems of insufficient feature utilization and single attention source, improves the learning ability and expression ability, and thus can reconstruct the higher quality medical CT image. We conduct a series of experiments; the results show that our method outperforms the previous algorithms and has a better performance of medical CT image reconstruction in the objective evaluation and visual effect.

scholarly journals Deeply Recursive Low- and High-Frequency Fusing Networks for Single Image Super-Resolution

Sensors ◽  
2020 ◽  
Vol 20 (24) ◽  
pp. 7268
Author(s):  
Cheng Yang ◽  
Guanming Lu
Keyword(s):  
High Frequency ◽  
Super Resolution ◽  
Single Image ◽  
Feature Representations ◽  
Prediction Time ◽  
Reconstruction Quality ◽  
Benchmark Datasets ◽  
Image Super Resolution ◽  
Single Image Super Resolution ◽  
Memory Resources

With the development of researches on single image super-resolution (SISR) based on convolutional neural networks (CNN), the quality of recovered images has been remarkably promoted. Since then, many deep learning-based models have been proposed, which have outperformed the traditional SISR algorithms. According to the results of extensive experiments, the feature representations of the model can be enhanced by increasing the depth and width of the network, which can ultimately improve the image reconstruction quality. However, a larger network generally consumes more computational and memory resources, making it difficult to train the network and increasing the prediction time. In view of the above problems, a novel deeply-recursive low- and high-frequency fusing network (DRFFN) for SISR tasks is proposed in this paper, which adopts the structure of parallel branches to extract the low- and high-frequency information of the image, respectively. The different complexities of the branches can reflect the frequency characteristic of the diverse image information. Moreover, an effective channel-wise attention mechanism based on variance (VCA) is designed to make the information distribution of each feature map more reasonably with different variances. Owing to model structure (i.e., cascading recursive learning of recursive units), DRFFN and DRFFN-L are very compact, where the weights are shared by all convolutional recursions. Comprehensive benchmark evaluations in standard benchmark datasets well demonstrate that DRFFN outperforms the most existing models and has achieved competitive, quantitative, and visual results.

scholarly journals Component Divide-and-Conquer for Real-World Image Super-Resolution

2020 ◽  
pp. 101-117
Author(s):  
Pengxu Wei ◽  
Ziwei Xie ◽  
Hannan Lu ◽  
Zongyuan Zhan ◽  
Qixiang Ye ◽  
...  
Keyword(s):  
Real World ◽  
Super Resolution ◽  
Divide And Conquer ◽  
Image Super Resolution ◽  
World Image

scholarly journals Residual Triplet Attention Network for Single-Image Super-Resolution

Electronics ◽  
2021 ◽  
Vol 10 (17) ◽  
pp. 2072
Author(s):  
Feng Huang ◽  
Zhifeng Wang ◽  
Jing Wu ◽  
Ying Shen ◽  
Liqiong Chen
Keyword(s):  
Spatial Information ◽  
Super Resolution ◽  
Learning Ability ◽  
Single Image ◽  
Attention Network ◽  
Dimensional Interaction ◽  
Powerful Learning ◽  
Image Super Resolution ◽  
The Cross ◽  
Single Image Super Resolution

Single-image super-resolution (SISR) techniques have been developed rapidly with the remarkable progress of convolutional neural networks (CNNs). The previous CNNs-based SISR techniques mainly focus on the network design while ignoring the interactions and interdependencies between different dimensions of the features in the middle layers, consequently hindering the powerful learning ability of CNNs. In order to address this problem effectively, a residual triplet attention network (RTAN) for efficient interactions of the feature information is proposed. Specifically, we develop an innovative multiple-nested residual group (MNRG) structure to improve the learning ability for extracting the high-frequency information and train a deeper and more stable network. Furthermore, we present a novel lightweight residual triplet attention module (RTAM) to obtain the cross-dimensional attention weights of the features. The RTAM combines two cross-dimensional interaction blocks (CDIBs) and one spatial attention block (SAB) base on the residual module. Therefore, the RTAM is not only capable of capturing the cross-dimensional interactions and interdependencies of the features, but also utilizing the spatial information of the features. The simulation results and analysis show the superiority of the proposed RTAN over the state-of-the-art SISR networks in terms of both evaluation metrics and visual results.

A Short Survey of Image Super Resolution Algorithms

2015 ◽  
Vol 2 (2) ◽  
pp. 19-29 ◽  
Author(s):  
Heng Liu ◽  
◽  
Dongdong Huang
Keyword(s):  
Super Resolution ◽  
Short Survey ◽  
Image Super Resolution
Sign in / Sign up

Export Citation Format

Share Document