Accurate image super-resolution using dense connections and dimension reduction network

Hu, Shiyu; Wang, Guodong; Wang, Yanjie; Chen, Chenglizhao; Pan, Zhenkuan

doi:10.1007/s11042-019-08241-5

Cited by 14 publications

(3 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Reconstructing real ground truth images with the proposed super-resolution approach At this stage, the performance of the proposed method was compared quantitatively and qualitatively to state-of-the-art and conventional techniques, such as bicubic interpolation, FIGURE 6 Comparing the image quality of the proposed method to that of existing algorithms for a sample image of chest X-ray datasets at an x2 magnification scale dictionary-based image enhancement methods (FL [31], A+ [32]), self-similarity-based method Self-ExSR [33], and artificial neural network-based techniques (LapSRN [34], Ms-LapSRN [35], DRRN [36], FSRCNN [33], SRCNN [6], SCN [37], DRCN [38], VDSR [38], RDN [39], LapSRN [34], EDSR [40], CARN [41], MemNet [42], RCAN+ [43], SRCLIQUENET+ [44]), for magnification factors of 2, 3, and 4. Furthermore, SET5, SET14, and BSDS100 databases, which contained images of natural scenes, as well as the URBAN100 dataset, which contained images of architectural challenges, were evaluated.…”

Section: 32mentioning

confidence: 99%

X‐Ray medical image super‐resolution via self‐organization neural networks and geometric directional gradient

Ahmadian

Reza-Alikhani

2022

IET Image Processing

View full text Add to dashboard Cite

Nowadays, due to the rapid development of the Internet and communication networks, remote disease diagnosis by physicians utilizing medical images such as X-rays have increased. However, the transmitted images lose their true quality and resolutions due to several factors, including noise and image compression techniques used to conserve memory space. This paper presents a novel clinical X-ray image enhancement method based on self-organizing neural networks, the ability of first-order derivative operators to detect edges, and improved classification methods by enhancing image features and extending the nearest neighbor algorithms selection of the best similarity feature vector among all sample feature vectors. The proposed method employs first-order image derivation operators to extract edge details and features from images. The feature vectors were preprocessed and segmented into various classes using self-organizing neural networks. The best matching and most similar vectors among the feature vectors are retrieved via the nearest neighbor algorithm. In contrast to conventional and contemporary image super-resolution techniques, the proposed method does not rely on the cost function. It is independent of error backpropagation methods because the competitive nature of the neural network is used to update the weight vectors rather than the gradient descent method. In addition, the performance and accuracy of the proposed image super-resolution method were improved by increasing the number of feature components in the feature vectors through the use of the two-dimensional image gradient. Furthermore, numerous image quality measurement criteria, such as structural similarity index (SSIM) and peak signalto-noise ratio (PSNR), were used to compare the reconstructed images of the proposed algorithm with those of other image enhancement algorithms. The results show that the proposed image enhancement algorithms' high-resolution and high-quality reconstructed image significantly outperformed many other medical image enhancement algorithms in reconstructing the edges and boundaries of objects with a smooth slope, as deemed by expert personnel and compared with image quality measurement criteria.

show abstract

Section: 32mentioning

confidence: 99%

X‐Ray medical image super‐resolution via self‐organization neural networks and geometric directional gradient

Ahmadian

Reza-Alikhani

2022

IET Image Processing

View full text Add to dashboard Cite

show abstract

“…Compared with many traditional SISR methods based on machine learning, the simple structure of the SRCNN model shows remarkable performance in image super-resolution problems. Then, a large number of CNN-based models were proposed to obtain more accurate SISR results using different techniques to improve the quality of the reconstructed image: the design of the network structure with residuals [18][19][20][21][22]; generative adversarial networks [23]; neural architecture search [24,25]; various attention mechanisms [26], and other technologies [27,28]. With the improvement of architecture, this field has indeed made rich progress.…”

Section: Introductionmentioning

confidence: 99%

GRAN: Ghost Residual Attention Network for Single Image Super Resolution

Niu¹,

Wang²,

Zhu³

et al. 2023

Preprint

View full text Add to dashboard Cite

Recently, many works have designed wider and deeper networks to achieve higher image super-resolution performance. Despite their outstanding performance, they still suffer from high computational resources, preventing them from directly applying to embedded devices. To reduce the computation resources and maintain performance, we propose a novel Ghost Residual Attention Network (GRAN) for efficient super-resolution. This paper introduces Ghost Residual Attention Block (GRAB) groups to overcome the drawbacks of the standard convolutional operation, i.e., redundancy of the intermediate feature. GRAB consists of the Ghost Module and Channel and Spatial Attention Module (CSAM) to alleviate the generation of redundant features. Specifically, Ghost Module can reveal information underlying intrinsic features by employing linear operations to replace the standard convolutions. Reducing redundant features by the Ghost Module, our model decreases memory and computing resource requirements in the network. The CSAM pays more comprehensive attention to where and what the feature extraction is, which is critical to recovering the image details. Experiments conducted on the benchmark datasets demonstrate the superior performance of our method in both qualitative and quantitative. Compared to the baseline models,

show abstract

“… Exposure: If position is unknown still data access is possible.  Network dimension: Depends on number of nodes [12].  Comparable network: Nodes present in a network has same characteristics.…”

Section: Introductionmentioning

confidence: 99%

Network Aided Positioning Techniques Based on Rssi and Signal Processing

Kevin¹

2020

ijarcs

View full text Add to dashboard Cite

The researcher's attentiveness has been diverted to create mobile positioning techniques based on RSSI and with signal processing techniques like GPS and multidimensional scaling. The localization system has been proposed in different topologies with a lot of tactical challenges in mobile positioning. Several positioning systems has been proposed for mobile based wireless sensor network and some are in a dense environment. In consequence, it is not practical to use a same localization system for different types of networks. Therefore, a system and algorithm are required which can calibrate itself and transform the global coordinates according to the environmental changes. In this article we provide an overview of different localization systems and provide some insight overview for future researchers.

show abstract

Accurate image super-resolution using dense connections and dimension reduction network

Cited by 14 publications

References 27 publications

X‐Ray medical image super‐resolution via self‐organization neural networks and geometric directional gradient

X‐Ray medical image super‐resolution via self‐organization neural networks and geometric directional gradient

GRAN: Ghost Residual Attention Network for Single Image Super Resolution

Network Aided Positioning Techniques Based on Rssi and Signal Processing

Contact Info

Product

Resources

About