Super-resolution Image Reconstruction Techniques Research Articles

A Review of GAN-Based Super-Resolution Reconstruction for Optical Remote Sensing Images

High-resolution images have a wide range of applications in image compression, remote sensing, medical imaging, public safety, and other fields. The primary objective of super-resolution reconstruction of images is to reconstruct a given low-resolution image into a corresponding high-resolution image by a specific algorithm. With the emergence and swift advancement of generative adversarial networks (GANs), image super-resolution reconstruction is experiencing a new era of progress. Unfortunately, there has been a lack of comprehensive efforts to bring together the advancements made in the field of super-resolution reconstruction using generative adversarial networks. Hence, this paper presents a comprehensive overview of the super-resolution image reconstruction technique that utilizes generative adversarial networks. Initially, we examine the operational principles of generative adversarial networks, followed by an overview of the relevant research and background information on reconstructing remote sensing images through super-resolution techniques. Next, we discuss significant research on generative adversarial networks in high-resolution image reconstruction. We cover various aspects, such as datasets, evaluation criteria, and conventional models used for image reconstruction. Subsequently, the super-resolution reconstruction models based on generative adversarial networks are categorized based on whether the kernel blurring function is recognized and utilized during training. We provide a brief overview of the utilization of generative adversarial network models in analyzing remote sensing imagery. In conclusion, we present a prospective analysis of forthcoming research directions pertaining to super-resolution reconstruction methods that rely on generative adversarial networks.

Impact of a Deep Learning-based Super-resolution Image Reconstruction Technique on High-contrast Computed Tomography: A Phantom Study

Deep-learning-based super-resolution image reconstruction (DLSRR) is a novel image reconstruction technique that is expected to contribute to improvement in spatial resolution as well as noise reduction through learning from high-resolution computed tomography (CT). This study aims to evaluate image quality obtained with DLSRR and assess its clinical potential. CT images of a Mercury CT 4.0 phantom were obtained using a 320-row multi-detector scanner at tube currents of 100, 200, and 300 mA. Image data were reconstructed by filtered back projection (FBP), hybrid iterative reconstruction (HIR), model-based iterative reconstruction (MBIR), deep-learning-based image reconstruction (DLR), and DLSRR at image reconstruction strength levels of mild, standard, and strong. Noise power spectrum (NPS), task transfer function (TTF), and detectability index were calculated. The magnitude of the noise-reducing effect in comparison with FBP was in the order MBIR <HIR <DLR <DLSRR. The resolution property was in the order HIR <FBP <DLR <MBIR <DLSRR. The detectability index was highest for DLSRR. The maximum and mean of the NPS shifted towards lower frequencies for HIR and MBIR compared with FBP, and similar shifts were observed for DLR and DLSRR. For each image reconstruction technique, NPS decreased with increasing reconstruction strength level, but no change was observed in TTF. The present results suggest that DLSRR can achieve greater noise reduction and improved spatial resolution in the high-contrast region compared with conventional DLR and iterative reconstruction techniques.

Super Resolution Image Reconstruction for Bone Images

Objectives: Images got from image intensifier to assess joint movements during surgery are usually distorted. This paper aims to get exact high resolution image from such low resolution (distorted, blurred) images using super resolution image reconstruction. Methods/Statistical analysis: This method uses different images taken from the video of the original procedure of studying a patient with stiff hip to assess his hip movement under image intensifier. The proposed method uses the Singular Value Decomposition (SVD) transformation model for the purpose of reconstruction. In this work two data sets of images extracted as video from a c-arm –image intensifier imaging of a patient with disease of left hip are analysed. Findings: While capturing a fast moving object needs a camera with more radiation. Image intensifiers-even with methods like gating have disadvantage of smear phenomenon when capturing fast moving objects. But clear, quick analysis is needed in operation room setting where time is vital. In this method details like the inferior cortex of the neck of femur or proximal end of the trochanter which is absent in captured figures are appreciated in output high resolution image. Thus the outputs generated without omitting essential details. Application/Improvements: Distorted images captured during real-time procedures in the operation theatre while patient’s part is moving is resolved using Super Resolution Image Reconstruction technique. Thus surgeon understand the patient’s bone better. Procedures like placing a screw or passing a guide wire to reduce a fracture can be easily done with such a methodology. Keywords: Bone Images, Image Intensifier, Image Reconstruction, Moving, Super Resolution

A Novel Image Superresolution Reconstruction Algorithm Based on Sparse Representation

Superresolution image reconstruction technique uses single or a series of low-resolution images to reconstruct a high resolution image without changing the hardware devices, while improving image quality and the spatial resolution of the image. High resolution means the image with a higher pixel density, can provide more details. In this paper, a novel image superresolution algorithm based on sparse representation is studied. During over-complete dictionary of the training phase, the proposed method improves two aspects including feature extraction and dimension reduction. In the feature extraction process, combining the second derivative with the gradient direction, we construct a new descent direction to improve gradient method. The convergence speed of the new algorithm is faster than the gradient method and can get better results. Then improved two-dimensional Principal Component Analysis (2DPCA) algorithm is used to reduce the dimension, it could eliminate the correlation of the image lines and column. Experiment results show that this method of image reconstruction is better and faster for high resolution image reconstruction.

Super-resolution phase reconstruction technique in electron holography with a stage-scanning system

Super-resolution image reconstruction is a digital signal processing technique that allows creating a high-resolution image from multiple low-resolution images taken at slightly different positions. We introduce the super-resolution image reconstruction technique into electron holography for reconstructing phase images as follows: the studied specimen is shifted step-wise with a high-precision piezo holder, and a series of holograms is recorded. When the step size is not a multiple of the CCD pixel size, processing of the acquired series results in a higher pixel density and spatial resolution as compared to the phase image obtained with conventional holography. The final resolution exceeds the limit of the CCD pixel size divided by the magnification.

Super-resolution image reconstruction for ultrasonic nondestructive evaluation

Ultrasonic testing is one of the most successful nondestructive evaluation (NDE) techniques for the inspection of carbon-fiber-reinforced polymer (CFRP) materials. This paper discusses the application of the iterative backprojection (IBP) super-resolution image reconstruction technique to carbon epoxy laminates with simulated defects to obtain high-resolution images for NDE. Super-resolution image reconstruction is an approach used to overcome the inherent resolution limitations of an existing ultrasonic system. It can greatly improve the image quality and allow more detailed inspection of the region of interest (ROI) with high resolution, improving defect evaluation and accuracy. First, three artificially simulated delamination defects in a CFRP panel were considered to evaluate and validate the application of the IBP method. The results of the validation indicate that both the contrast-tonoise ratio (CNR) and the peak signal-to-noise ratio (PSNR) value of the super-resolution result are better than the bicubic interpolation method. Then, the IBP method was applied to the low-resolution ultrasonic C-scan image sequence with subpixel displacement of two types of defects (delamination and porosity) which were obtained by the micro-scanning imaging technique. The result demonstrated that super-resolution images achieved better visual quality with an improved image resolution compared with raw C-scan images.

Overview of techniques applicable to self-interference incoherent digital holography.

Self-interference incoherent digital holography (SIDH) retrieves the complex hologram from the object illuminated by the incoherent light. Supported by the adaptive optic feature, SIDH is readily applicable to the ocular imaging to investigate the human retinal cells. Considering the practical issues, issues related to resolution, phase-shifting, and contrast should be addressed to implement the viable SIDH system which is capable of recording the holographic information of human retinal cells under the incoherent illumination. Super resolution image reconstruction technique can be directly applied to SIDH to enhance the resolution of the system without any change of configuration. We present the improved way to incorporate the phase-shifting itself into the lateral shift required by the super resolution technique. To deal with the phase-shifting issue, we present an arbitrary phase shift retrieval algorithm which can reduce the number of phase-shift and accept the blind phase-shift. The single-shot imaging is also possible by adopting the off-axis configuration of SIDH. We will provide the detailed procedures to retrieve the complex hologram using the proposed arbitrary phase shifting algorithm and the off-axis configuration.

Spatio-Temporal Resolution Enhancement of Vocal Tract MRI Sequences—A Comparison Among Wiener Filter Based Methods

Articulatory Synthesis consists in reproducing speech by means of models of the vocal tract and of articulatory processes. Recent advances in Magnetic Resonance Imaging (MRI) allowed for important improvements with respect to the speech comprehension and the forms taken by the vocal tract. However, one of the main challenges in the field is the fast and at the same time high-quality acquisition of image sequences. Since adopting more powerful acquisition devices might be financially inviable, we propose a method for the spatio-temporal resolution enhancement of the obtained sequences using only digital image processing techniques. The approach involves two stages: (1) the temporal resolution enhancement by means of a motion compensated interpolation technique; and (2) the spatial resolution enhancement by means of a super resolution image reconstruction technique. Considering the spatial resolution enhancement, inspired by two methods available in the literature, three adaptations of the Wiener filter were proposed: the statistical interpolation, the multi-temporal approach, and the adaptive Wiener filter. In all cases, a separable Markovian model and an isotropic model were compared for the characterization of the spatial correlation structures. Considering all Wiener filter-based approaches, the adaptive Wiener filter outperformed all other approaches.

Super-resolution image reconstruction techniques: Trade-offs between the data-fidelity and regularization terms

Stochastic regularized methods are quite advantageous in super-resolution (SR) image reconstruction problems. In the particular techniques, the SR problem is formulated by means of two terms, the data-fidelity term and the regularization term. The present work examines the effect of each one of these terms on the SR reconstruction result with respect to the presence or absence of noise in the low-resolution (LR) frames. Experimentation is carried out with the widely employed L2, L1, Huber and Lorentzian estimators for the data-fidelity term. The Tikhonov and Bilateral (B) Total Variation (TV) techniques are employed for the regularization term. The extracted conclusions can, in practice, help to select an effective SR method for a given sequence of LR frames. Thus, in case that the potential methods present common data-fidelity or regularization term, and frames are noiseless, the method which employs the most robust regularization or data-fidelity term should be used. Otherwise, experimental conclusions regarding performance ranking vary with the presence of noise in frames, the noise model as well as the difference in robustness of efficiency between the rival terms. Estimators employed for the data-fidelity term or regularizations stand for the rival terms.

Evaluation and benchmarking of a pixel-shifting camera for superresolution lensless digital holography

In lensless digital holography, the comparatively low resolution of the CCD devices that are used to record the digital holograms has to date limited both the maximum linear dimensions of the measurement object and also the minimum possible stand-off distance between the object and the CCD detector. A signal-processing-based technique known as superresolution (SR) image reconstruction can provide an alternative approach that reduces these restrictions. We report on an SR image reconstruction technique that has been introduced by employing a camera with a "microscanning" function to capture SR digital holograms via multiple subpixel movements of the CCD sensor. A detailed description of the approach is given, along with experimental results, which are discussed and evaluated, showing the advantages of using this method. An approach using three-dimensional holographic contouring is also described that may be adopted as a strategy for benchmarking newly developed algorithms at any stage of the lensless digital holographic process.