Learning graph-constrained cascade regressors for single image super-resolution

Yan, Jianqiang; Zhang, Kaibing; Luo, Shuang; Xu, Jian; Lü, Jian; Xiong, Zenggang

doi:10.1007/s10489-021-02904-3

Cited by 1 publication

(3 citation statements)

References 45 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To this end, we converted high-quality images from high-resolution datasets into low-quality, low-resolution images using blur noise, rotation, and subsampling techniques to produce low-resolution medical X-ray images. We then compared the proposed image super-resolution algorithm with other image super-resolution algorithms using real ground truth FIGURE 5 The proposed image reconstruction method image datasets Set 5 [22], BSDS100 [23], Set 14 [24], and URBAN100 [25], as well as X-ray medical imaging datasets such as Chest X-ray 8 and Chest X-ray 14 image datasets from NIH.…”

Section: Database Preparation and Configurationmentioning

confidence: 99%

“…By learning the statistical relationships between low-and high-resolution image patches across a large training dataset [4], learning-based methods can restore high-resolution images with sharp edges at a low computational cost. Image super-resolution techniques based on dictionary learning algorithms are referred to as shallow learning and deep learning [5]. Dong (2014) proposed a convolution neural network-based high-image super-resolution technique consisting of three layers of convolution neural networks for learning the nonlinear mapping relationship between low-resolution and high-resolution image patches.…”

Section: Introductionmentioning

confidence: 99%

“…By learning the statistical relationships between low‐ and high‐resolution image patches across a large training dataset [4], learning‐based methods can restore high‐resolution images with sharp edges at a low computational cost. Image super‐resolution techniques based on dictionary learning algorithms are referred to as shallow learning and deep learning [5].…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

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