Piecewise linear regression-based single image super-resolution via Hadamard transform

Abstract

Image super-resolution (SR) has extensive applications in surveillance systems, satellite imaging, medical imaging, and ultra-high definition display devices. The state-ofthe-art methods for SR still incur considerable running time. In this paper, we propose a novel approach based on Hadamard pattern and tree search structure in order to reduce the running time significantly. In this approach, LR (low-resolution)-HR (high-resolution) training patch pairs are classified into different classes based on the Hadamard patterns generated from the LR training patches. The mapping relationship between the LR space and the HR space for each class is then learned and used for SR. Experimental results show that the proposed method can achieve comparable accuracy as state-of-the-art methods with much faster running speed. The dataset, pretrained models and source code can be accessed at this URL † .

A weighted least squares optimisation strategy for medical image super resolution via multiscale convolutional neural networks for healthcare applications

“…The dataset consists of ultrasound (US) image (Dataset1), four sets of magnetic resonance imaging (MRI) images (Data-set2,4, 6 and 7) and three sets of computed tomography (CT) images (Dataset3, 5 and 8). We compare our proposed weighted least squares optimisation strategy via wavelet multiscale CNNs based SR algorithm with bicubic interpolation and seven state-of-the-art SR methods: CCR_SISR [64], Dual_Dic_SR [63], HT_SR [65], SR_ALS [62], SRCNN [5], WMCNN [33], QSIM [50]. For verifying the reliability of our method, we performed an experiment through adding different Gaussian noise to the input image to produce LR-HR image pairs.…”

An efficient medical image super resolution based on piecewise linear regression strategy using domain transform filtering

“…This section discusses our method for fast regression‐based SR 52 . The concept of piecewise linear regression, as discussed in References 53 and 54 is the root of our proposed method.…”

“…This section discusses our method for fast regression-based SR. 52 The concept of piecewise linear regression, as discussed in References 53 and 54 is the root of our proposed method. It uses a ternary search algorithm to find the suitable mapping model from an ensemble of piecewise linear mapping models (i.e., piecewise linear regressors) stationed to certain leaf nodes.…”

“…A Hadamard matrix having order of power of 2 (i.e., Q 16 ) could be generated using a recursive approach. 52 It can be achieved using an inbuilt MATLAB function (i.e., Hadamard []). We extract square patches and vectorize them.…”

“…To evaluate the performance of proposed method with other comparative methods, we use an objective metrics such as peak signal to noise ratio (PSNR) and structural similarity index measure (SSIM). 61 With the view to display an effectiveness of our proposed algorithm based on a piecewise linear regression system via domain transform filtering, we compare with other existing techniques such as bicubic, CCR_SISR, 62 ANR, 22 GESR, 63 HT_SR, 52 FSRCNN, 64 MMSR, 65 QSIM, 37 SR_ALS, 66 and Dual_Dic. 67 We extract LR training data from the standard image dataset without Gaussian blurring on these the training images.…”