Satisfactory Image Research Articles

A Novel Image Reconstruction Strategy for ECT: Combining Two Algorithms With a Graph Cut Method

Image reconstruction plays a key role in the application of electrical capacitance tomography (ECT). Although many different algorithms have been developed in the past, it is often difficult to obtain satisfactory images in all imaging regions by the use of a single algorithm due to the soft-field nature of ECT. This motivated us to develop a novel ECT image reconstruction strategy, in which a high-quality image can be obtained by combining the images reconstructed by two different algorithms via a graph cut method. By doing so, it is possible to retain the advantage of each algorithm for specified imaging regions and improve the quality of the whole image. This strategy was verified both numerically and experimentally for two widely used ECT reconstruction algorithms, i.e., linear backprojection and Tikhonov regularization. The results for stationary objects as well as gas–solid fluidized beds demonstrated that this graph-cut-based combination strategy presents a promising approach for ECT image reconstruction.

A joint guidance-enhanced perceptual encoder and atrous separable pyramid-convolutions for image inpainting

Satisfactory image inpainting requires visually-exquisite details and semantically-plausible structures, where encoder-decoder networks have shown their potentials but bear undesired local and global inconsistencies, such as blurry textures. To address this issue, we incorporate a perception operation in the encoder, which extracts features from known areas of the input image, to improve textured details in missing areas. We also propose an iterative guidance loss for the perception operation to guide perceptual encoding features approaching to ground-truth encoding features. The guidance-enhanced perceptual encoding features are transferred to the decoder through skip connections, mutually reinforcing the entire encoder–decoder performance. Since the inpainting task involves different levels of feature representations, we further apply atrous separable parallel-convolutions (i.e., atrous separable pyramid-convolutions or ASPC) with different receptive fields in the last guidance-enhanced perceptual encoding feature, which is used to learn high-level semantic features with multi-scale information. Experiments on public databases show that the proposed method achieves promising results in terms of visual details and semantic structures.

An efficient protocol and data set for automated otolith image analysis

AbstractInformation on fish age constitutes one of the most important biological variables for a fish stock, and an accurate estimation of the age structure of the fish populations is essential for the reliable management of these natural resources. The age of individual cod (Gadus morhua) is determined by manually examining the layered structure of otoliths, a calcium carbonate structure of the inner ear. Image‐based methods to age otoliths have been investigated for over 4 decades with varying results, but recent developments in automatic image analysis techniques are promising. The objective of this paper is to describe a method to efficiently image a manually broken otolith (avoiding the time‐consuming embedding and cross‐sectioning process) and to describe the organization and acquisition of imaged broken otolith images with associated metadata for a collection of north‐east Arctic cod otoliths. A single‐lens reflex camera was used for capturing photographs of the broken otoliths. A total of six images were acquired for each subject, consisting of three images in the first position with three different light exposures and three images in the second position with three different light exposures. This results in a simple and efficient procedure for capturing clear, satisfactory, and reproducible images of broken fish otoliths, and a more straightforward and less labour‐intensive alternative to the commonly used methods that involve embedding and cross‐sectioning of the otolith.

Biocompatible melanin based theranostic agent for in vivo detection and ablation of orthotopic micro-hepatocellular carcinoma.

Early diagnosis and therapy of hepatocellular carcinoma (HCC) is critical to improve the five-year survival rates of patients. Theranostic agents synergized with photothermal ablation are expected to realize the early detection and treatment of orthotopic HCC. However, conventional metallic nanoagents are limited by their potential bio-toxicity to surrounding normal organs. Recently, endogenous biological melanin pigments have been utilized to develop nanoplatforms due to their excellent biocompatibility and degradability. Whereas, the insufficient capability of PEGylated melanin nanoparticles (PEG-MNPs) in photoacoustic (PA) imaging limits their further biomedical applications. Paradoxically, it is difficult to meet these two different requirements. Herein, a multifunctional nanoagent based on melanin (MNPs) conjugating the near-infrared (NIR) dye IR820 was successfully designed and fabricated. Encapsulation by polyethylene glycol (PEG) renders the solubility in water and allows the physical absorption of IR820 for enhanced photoacoustic (PA) performance and photothermal therapy. Besides, PEG coating on the surface of IR820-PEG-MNPs resulted in a reduction in swallowing in the reticuloendothelial system of the liver and spleen, prolonging the circulation time in the blood and increasing the accumulation in the tumor. The IR820-PEG-MNPs displayed satisfactory PA and T1-weighted magnetic resonance imaging (MRI) signals in aqueous solution as well as strong photothermal efficiency. Compared with prior injection, PA/MR signals of the tumor region were enhanced by 4.13- and 1.60-fold, respectively, which could effectively detect lesions smaller than ∼1.8 mm. Furthermore, the high photothermal conversion efficiency (40.2%) endowed the IR820-PEG-MNPs with the capability of selectively ablating tumors in orthotopic HCC mouse models under the guidance of PA/MR imaging. This work broadens the biomedical applications of melanin-based agent, which are promising for the precise diagnosis of orthotopic micro HCC and imaging guided photothermal ablation.

Unbiased Image Style Transfer

Image style transferring process generates an output image in the target style with a specific strength for a given pair of content and target image. Recently, feed-forward neural networks have been employed in this process to fastly decode a linearly interpolated feature in encoded feature space. However, to date, no studies have been conducted to analyze the effectiveness of this style interpolation method. In this article, we tackle the missing work of the in-depth analysis of style interpolation and propose a new method that is more effective in controlling the strength of the desired style. The existing methods are biased because the training of a network is performed with one-sided data of full style strength. Therefore, such methods do not guarantee the generation of a satisfactory output image in an intermediate style strength. To resolve this problem of a biased network, we propose an unbiased learning technique, which uses unbiased training data and loss to allow a feed-forward network to learn the desired regression of style consistent with a specific interpolation function in encoded feature space. The experimental results verified that our unbiased method achieved a better regression learning between style control parameter and output image style, and more stable style transfer that is insensitive to the weight of style loss without adding complexity in image generating process.

Very Early-Onset Inflammatory Bowel Disease: A Challenging Field for Pediatric Gastroenterologists.

With the increasing number of children with inflammatory bowel disease (IBD), very early-onset IBD (VEO-IBD), defined as IBD that is diagnosed or that develops before 6 years of age, has become a field of innovation among pediatric gastroenterologists. Advances in genetic testing have enabled the diagnosis of IBD caused by gene mutations, also known as monogenic or Mendelian disorder-associated IBD (MD-IBD), with approximately 60 causative genes reported to date. The diagnosis of VEO-IBD requires endoscopic and histological evaluations. However, satisfactory small bowel imaging studies may not be feasible in this small population. Both genetic and immunological approaches are necessary for the diagnosis of MD-IBD, which can differ among countries according to the available resources. As a result of the use of targeted gene panels covered by the national health insurance and the nationwide research project investigating inborn errors of immunity, an efficient approach for the diagnosis of MD-IBD has been developed in Japan. Proper management of VEO-IBD by pediatric gastroenterologists constitutes a challenge. Some MD-IBDs can be curable by allogenic hematopoietic stem cell transplantation. With an understanding of the affected gene functions, targeted therapies are being developed. Social and psychological support systems for both children and their families should also be provided to improve their quality of life. Multidisciplinary team care would contribute to early diagnosis, proper therapeutic interventions, and improved quality of life in patients and their families.

Image Edge Recognition of Virtual Reality Scene Based on Multi-Operator Dynamic Weight Detection

Image edge detection in virtual reality scenes is one of the most important technologies in the field of image processing and computer vision. It occupies an important position in the image processing system and is a key factor that affects the performance of the entire system. The quality of the algorithm directly affects the performance of the computer's visual system. This paper briefly describes the basic theoretical methods of image edge detection. The basic theory and processing flow of image edge detection are analyzed, and several commonly used edge detection preprocessing methods and their basic principles are elaborated in detail. The existing traditional edge detection methods are briefly introduced, and the traditional edge detection methods are compared. This paper studies the adaptive multi-scale edge detection method based on Canny algorithm, and through theoretical analysis, compares the advantages and disadvantages of various algorithms in image edge detection. In the process of acquiring image edges, the local maximum value of the modulus is calculated along the gradient direction and the threshold is adaptively selected based on the image blocking principle. Comparing with the traditional modulus maximum edge detection method, this algorithm overcomes the contradiction that can suppress the interference of noise and obtain better edge detection effect to a certain extent. Experiments show that the method in this paper not only suppresses the interference of impulsive noise to the image edge detection, but also greatly reduces the possibility of false edges, and obtains a satisfactory accurate binary edge image.

360 Panorama Synthesis from a Sparse Set of Images on a Low-Power Device

A full 360 $^\circ$ × 180 $^\circ$ image provides an unlimited field of view (FOV) and an immersive experience for the users without any loss of information of the surrounding. In this study, a deep learning based approach is proposed to synthesize a 360 $^\circ$ image from a sparse set of images captured with a limited FOV. The proposed network consists of a cascade of the FOV estimation network and the panorama synthesis network. We propose a hierarchical generative network to synthesize high quality 360 $^\circ$ panorama images. The design of progressive multi-scale generator and multiple discriminator reduces the high frequency artifact which is commonly observed in image synthesis using generative networks. The network is further compressed to run on a low-power device such as a smartphone using our proposed size and latency optimization. Experimental result demonstrates that the proposed method produces 360 $^\circ$ panorama with satisfactory image quality of up to 512 × 1024 resolution. It is also shown that the proposed method outperforms the alternative method and can be generalized for non-panoramic scenes and real images captured by a smartphone camera.

A Panhellenic Social Survey (2018-9) regarding the Quality of Life, Energy Needs and People’s Attitudes towards R.E.S.

This Pan-Hellenic Social Survey (2018-2019) covers the attitudes of the people regarding Climate Change, Energy Needs, the Quality of Life of the people, and also their recent attitudes towards the Renewable Energy Sources.It is a well known fact that Hellas is suffering from an economic crisis during the last ten years. As expected, this crisis, has not only immediately affected the economics of each household, but also the quality of life, the comfort conditions and, in consequence, the everyday life of the citizens. It is also very interesting to see how people’s attitudes towards the application of small and large-scale devices of Renewable Energy Sources, i.e. Photovoltaic and Wind generators, change over time.It is at least an intriguing subject to see how people cope with the above mentioned circumstances. Among other research projects our Laboratory, every two years, conducts a similar social research with printed questionnaires regarding the attitudes of Hellenic people towards R.E.S..This specific research presented here is of special interest. It aims at the investigation of how peoples’ attitudes and views towards the Environmental subjects and the use of RES. are affected by the Economic Crisis, and a rather dystopian general future. How serious and important are the environmental issues considered to be when people feel that their everyday life is threatened? This subject is approached through this Pan-Hellenic survey analyzing the data gathered by questionnaires.After an extremely heavy winter, (January 2019), It is very interesting to see how environmental matters are faced in general, regarding energy sources, fuels and related costs during this critical period.But parallel to the above, Hellenic people have to face their household economics, their traditional attitudes towards their environment (both built and natural) and their dependence from imported fuels (oil and gas).The conclusions of this research are important, describing the hellenic people’s attitudes towards quality of life, energy needs, energy poverty, and their attitudes towards R.E.S. and the environment. A large number of areas and cities have been covered, offering a satisfactory image of the subject.

An Underwater Image Enhancement Benchmark Dataset and Beyond.

Underwater image enhancement has been attracting much attention due to its significance in marine engineering and aquatic robotics. Numerous underwater image enhancement algorithms have been proposed in the last few years. However, these algorithms are mainly evaluated using either synthetic datasets or few selected real-world images. It is thus unclear how these algorithms would perform on images acquired in the wild and how we could gauge the progress in the field. To bridge this gap, we present the first comprehensive perceptual study and analysis of underwater image enhancement using large-scale real-world images. In this paper, we construct an Underwater Image Enhancement Benchmark (UIEB) including 950 real-world underwater images, 890 of which have the corresponding reference images. We treat the rest 60 underwater images which cannot obtain satisfactory reference images as challenging data. Using this dataset, we conduct a comprehensive study of the state-of-the-art underwater image enhancement algorithms qualitatively and quantitatively. In addition, we propose an underwater image enhancement network (called Water-Net) trained on this benchmark as a baseline, which indicates the generalization of the proposed UIEB for training Convolutional Neural Networks (CNNs). The benchmark evaluations and the proposed Water-Net demonstrate the performance and limitations of state-of-the-art algorithms, which shed light on future research in underwater image enhancement. The dataset and code are available at.

Single image super resolution using dictionary learning and sparse coding with multi-scale and multi-directional Gabor feature representation

Recently, sparse representation theory has shown the state-of-art performance in image super resolution (SR) field. The sparse representation based single image SR methods learn dictionaries to discover the co-occurence relationship between low-resolution (LR) and high-resolution (HR) image feature spaces to generate satisfactory SR images. However, most existing learning based methods focus on Gradient and Laplacian filters to achieve accurate feature representation in SR task. In this paper, a novel multi-scale and multi-directional feature descriptor approach is proposed to improve SR quality. In the proposed approach, Gabor filter is first used as feature representation in learning based super resolution to extract image features at different scales and orientations. Therefore, the difficulty of capturing the complex local structures in all scale and directions using traditional 1-D filters is resolved by the proposed Gabor filter approach. Then the efficient mapping between LR and HR images is achieved by searching the sparse representation coefficients over the LR and HR dictionaries in dictionary learning phase. Finally, the learned relationship is applied to validation LR input in order to achieve accurate SR image in reconstruction phase. The experimental results show that the proposed method outperforms other state-of-art methods in terms of both quantity and quality.

Design of Low-Complexity 3-D Underwater Imaging System With Sparse Planar Arrays

The development of a real-time 3-D underwater imaging system with a planar array is restricted by the huge hardware cost and computational burden associated with the large number of elements required. In this paper, a new design of low-complexity 3-D underwater imaging system is proposed, involving two key parts: a special sparse array with low hardware cost and an efficient beamforming with low computational burden. Especially, the simulated annealing algorithm is optimized based on distributed and parallel subarray (DPS) beamforming and results in fewer active elements than existing methods. To improve the computational efficiency especially for sparse arrays, an optimized DPS beamforming is presented with the pruning fast Fourier transform technology. To test the validity of the design, a real system based on the proposed methods was devised and employed in the lake and sea trials. The experiment results demonstrate that the low-complexity 3-D underwater imaging system can provide a satisfactory imaging quality.

Carbide-bonded graphene-based Joule heating for embossing fine microstructures on optical glass

This paper reports the fabrication of high-quality microstructures on optical glass via hot embossing using carbide-bonded graphene (CBG) based Joule heating for the first time. In this study, a tailor-made micro hot embossing tool equipped with a modified CBG-based Joule heating system was designed and developed for transferring microstructures (e.g., microlens arrays, MLAs for short) from the CBG-coated silicon mold insert into the optical glass (P-SK57). Initially, the surface topographies of a typical 3 × 3 MLA from a bare silicon mold to an embossed glass replica were compared for evaluating form errors brought in during different preparation stages. The feasibility of the CBG-based Joule heating technique for the non-equilibrium thermal imprinting of optical glass was evaluated by the surface integrity and replication fidelity of the embossed MLA features. Thermally induced residual stress and imaging performance of the embossed glass lens were assessed as well. Experimental results indicate that the proposed CBG-assisted hot embossing technique, in combination with single point diamond turning technology, has the capability of producing high-quality glass MLAs. Moreover, this technique allows notably fine replication of surface shapes at the microscale, as well as roughness information at the nanoscale. Consequently, the embossed MLA replica shows satisfactory imaging performance.

Total-Body PET and Highly Stable Chelators Together Enable Meaningful 89Zr-Antibody PET Studies up to 30 Days After Injection.

The use of 89Zr-antibody PET imaging to measure antibody biodistribution and tissue pharmacokinetics is well established, but current PET systems lack the sensitivity needed to study 89Zr-labeled antibodies beyond 2-3 isotope half-lives (7-10 d), after which a poor signal-to-noise ratio is problematic. However, studies across many weeks are desirable to better match antibody circulation half-life in human and nonhuman primates. These studies investigated the technical feasibility of using the primate mini-EXPLORER PET scanner, making use of its high sensitivity and 45-cm axial field of view, for total-body imaging of 89Zr-labeled antibodies in rhesus monkeys up to 30 d after injection. Methods: A humanized monoclonal IgG antibody against the herpes simplex viral protein glycoprotein D (gD) was radiolabeled with 89Zr via 1 of 4 chelator-linker combinations (benzyl isothiocyanate-DFO [DFO-Bz-NCS], where DFO is desferrioxamine B; DFO-squaramide; DFO*-Bz-NCS, where DFO* is desferrioxamine*; and DFO*-squaramide). The pharmacokinetics associated with these 4 chelator-linker combinations were compared in 12 healthy young male rhesus monkeys (∼1-2 y old, ∼3 ± 1 kg). Each animal was initially injected intravenously with unlabeled antibody in a peripheral vessel in the right arm (10 mg/kg, providing therapeutic-level antibody concentrations), immediately followed by approximately 40 MBq of one of the 89Zr-labeled antibodies injected intravenously in a peripheral vessel in the left arm. All animals were imaged 6 times over a period of 30 d, with an initial 60-min dynamic scan on day 0 (day of injection) followed by static scans of 30-45 min on approximately days 3, 7, 14, 21, and 30, with all acquired using a single bed position and images reconstructed using time-of-flight list-mode ordered-subsets expectation maximization. Activity concentrations in various organs were extracted from the PET images using manually defined regions of interest. Results: Excellent image quality was obtained, capturing the initial distribution phase in the whole-body scan; later time points showed residual 89Zr mainly in the liver. Even at 30 d after injection, representing approximately 9 half-lives of 89Zr and with a total residual activity of only 20-40 kBq in the animal, the image quality was sufficient to readily identify activity in the liver, kidneys, and upper and lower limb joints. Significant differences were noted in late time point liver uptake, bone uptake, and whole-body clearance between chelator-linker types, whereas little variation (±10%) was observed within each type. Conclusion: These studies demonstrate the ability to image 89Zr-radiolabeled antibodies up to 30 d after injection while maintaining satisfactory image quality, as provided by the primate mini-EXPLORER with high sensitivity and long axial field of view. Quantification demonstrated potentially important differences in the behavior of the 4 chelators. This finding supports further investigation.

Viscoacoustic least-squares reverse time migration using a time-domain complex-valued wave equation

With limited recording apertures, finite-frequency source functions, and irregular subsurface illuminations, traditional imaging methods have been insufficient to produce satisfactory reflectivity images with high resolution and amplitude fidelity. This is because most traditional imaging approaches are commonly formulated as the adjoint instead of the inverse operator with respect to the forward-modeling operator. In addition, intrinsic attenuation introduces amplitude loss and phase dispersion during wave propagation. Without considering these effects, migrated images might be kinematically and dynamically incorrect. We have developed a viscoacoustic least-squares reverse time migration (LSRTM) method based on a time-domain complex-valued wave equation. According to the Born approximation, we first linearized the viscoacoustic wave equation and derived a demigration operator. Then, using the complex-valued Lagrange multiplier method, we derived the adjoint viscoacoustic wave equation and corresponding sensitivity kernel. With the forward and adjoint operators, a linear inverse problem is formulated to estimate the subsurface reflectivity model. A total-variation regularization scheme is introduced to enhance the robustness of our viscoacoustic LSRTM, and a diagonal Hessian is used as the preconditioner to accelerate the convergence. Three synthetic examples are used to demonstrate that our approach enables us to compensate attenuation effects, improve imaging resolution, and enhance amplitude fidelity in comparison with the adjoint imaging method.

Measurement of Dynamic Responses from Large Structural Tests by Analyzing Non-Synchronized Videos.

Image analysis techniques have been employed to measure displacements, deformation, crack propagation, and structural health monitoring. With the rapid development and wide application of digital imaging technology, consumer digital cameras are commonly used for making such measurements because of their satisfactory imaging resolution, video recording capability, and relatively low cost. However, three-dimensional dynamic response monitoring and measurement on large-scale structures pose challenges of camera calibration and synchronization to image analysis. Without satisfactory camera position and orientation obtained from calibration and well-synchronized imaging, significant errors would occur in the dynamic responses during image analysis and stereo triangulation. This paper introduces two camera calibration approaches that are suitable for large-scale structural experiments, as well as a synchronization method to estimate the time difference between two cameras and further minimize the error of stereo triangulation. Two structural experiments are used to verify the calibration approaches and the synchronization method to acquire dynamic responses. The results demonstrate the performance and accuracy improvement by using the proposed methods.

Cloud-Based Data Offloading for Multi-focus and Multi-views Image Fusion in Mobile Applications

The mobile phone is currently the most wid- ely used and most convenient photographic device. Like many optical imaging devices the camera of mobile ph- one are far from flawless, such as limited field of view and depth of focus in photos. Due to its limited computing power, it is not possible to use a mobile phone to fuse images. In addition, the multimedia communication need a good network connection and bandwidth. In this paper, we solve this problem by proposing an image fusion strategy and mobile data offloading method based on cloud computing platform. We design a cloud computing environment to fuse the images captured by the mobile phone where mobile terminal uploads and downloads images to the cloud through 5G signal. And a continuous time Markov model is applied to offload the mobile network data. We fuse the original images to all-in-focus image and 3D stereo image based on Non Subsampled Contourlet Transform and Detail-preserving & Content-aware Variational multiple images fusion method, respectively. The experimental results show that the proposed image fusion and data offloading method achieves satisfactory image quality and execution performance.

MRI of the liver: choosing the right contrast agent.

Contrast enhanced MRI of the liver provides valuable information in the evaluation of both chronic liver disease and focal liver lesions. Currently, two classes of MRI contrast agents are available for clinical use, namely the extracellular contrast agent (ECA) and the hepatobiliary agent (HBA). The use of appropriate contrast agents for liver MRI requires knowledge of the clinical situation and question to be answered. ECAs have been used for decades since their introduction into clinical practice and provide excellent dynamic phase information that is useful in characterizing focal liver lesions. In the last decade, HBAs, particularly Gadoxetate, have been found useful for characterizing lesions with functioning hepatocytes and more importantly in evaluating the biliary tree. Gadoxetate, however, provides less satisfactory dynamic phase images compared to ECAs, particularly during the arterial phase. In this perspective article, we will discuss the various intravenous contrast agents used for liver MRI and their ideal utilization.

Development of radiation imaging system for nutrient distribution in sapling

Radioactive tracer in plant commonly uses X-ray films or imaging plate for study nutrient distribution, which cause radioactive waste. We developed a real-time imaging system for radiotracer in sapling to reduce a large number of samples and radioactive waste. The main components of the developed system consist of the radiation imaging detector, the mechanical part, and the operating software. We used 4 × 4 channel array of Silicon Photomultiplier (SiPM) model ArrayC-30035-16P from SensL coupling with plastic scintillator array of 3 × 3 × 5 mm3 pixels as a radiation imaging detector. The signals from the detector were amplified and noises discriminated then transfer to the operating software on a personal computer (PC). The area scanning unit and mechanical parts were modified from MicromakeCl 3D printer with customised control board and controlled by operating software on PC interfacing via USB to RS232. Furthermore, the LabVIEW base system control software was developed to control the movement of motors in X, Y and Z directions of the mechanical control board in associated with the counting signals transferring from the developed detector board. Each counted data from the scanning process was transformed into rainbow scale image. The developed system could measure a sample with a maximum size of 300 × 300 mm2, and the precision of motors was ± 0.1 mm. The control software is able to change parameters of the time for counting, a pitch of motors and scanning area of a sample. Finally, the developed system was tested by run through the process of radiotracer in the maize sapling growth for 30 hours. The result showed satisfactory rainbow color scale image of accumulation and distribution of radioactive tracer in sapling.

Unsupervised Single-Image Super-Resolution with Multi-Gram Loss

Recently, supervised deep super-resolution (SR) networks have achieved great success in both accuracy and texture generation. However, most methods train in the dataset with a fixed kernel (such as bicubic) between high-resolution images and their low-resolution counterparts. In real-life applications, pictures are always disturbed with additional artifacts, e.g., non-ideal point-spread function in old film photos, and compression loss in cellphone photos. How to generate a satisfactory SR image from the specific prior single low-resolution (LR) image is still a challenging issue. In this paper, we propose a novel unsupervised method named unsupervised single-image SR with multi-gram loss (UMGSR) to overcome the dilemma. There are two significant contributions in this paper: (a) we design a new architecture for extracting more information from limited inputs by combining the local residual block and two-step global residual learning; (b) we introduce the multi-gram loss for SR task to effectively generate better image details. Experimental comparison shows that our unsupervised method in normal conditions can attain better visual results than other supervised SR methods.