Enhanced wide-activated residual network for efficient and accurate image deblocking

To save bandwidth and storage space as well as speed up data transmission, people usually perform lossy compression on images. Although the JPEG standard is a simple and effective compression method, it usually introduces various visually unpleasing artifacts, especially the notorious blocking artifacts. In recent years, deep convolutional neural networks (CNNs) have seen remarkable development in compression artifacts reduction. Despite the excellent performance, most deep CNNs suffer from heavy computation due to very deep and wide architectures. In this paper, we propose an enhanced wide-activated residual network (EWARN) for efficient and accurate image deblocking. Specifically, we propose an enhanced wide-activated residual block (EWARB) as basic construction module. Our EWARB gives rise to larger activation width, better use of interdependencies among channels, and more informative and discriminative non-linearity activation features without more parameters than residual block (RB) and wide-activated residual block (WARB). Furthermore, we introduce an overlapping patches extraction and combination (OPEC) strategy into our network in a full convolution way, leading to large receptive field, enforced compatibility among adjacent blocks, and efficient deblocking. Extensive experiments demonstrate that our EWARN outperforms several state-of-the-art methods quantitatively and qualitatively with relatively small model size and less running time, achieving a good trade-off between performance and complexity.     

Structure of presented stimuli influences gazing behavior and choice

Well-structured stimuli presentation is essential in eye-tracking research to test predefined hypotheses reliably and to conduct relevant gazing behavior studies. Several bottom-up factors associated with stimuli presentation (such as stimuli orientation, size etc.) can influence gazing behavior. However, only a small number of scientific papers address these factors in a sensory and consumer science context and thus provide guidance to practitioners. The two presented eye-tracking studies on food images aimed at evaluating the effect of the bottom-up factors stimulus size, background of the picture, orientation of food product presentation, the evaluated products and the number of alternatives. Significant effects of product group were found in the case of all eye-movement parameters except time to first fixation and first fixation duration. In contrary, orientation significantly influenced only the time to first fixation and first fixation duration parameters. Stimulus size significantly increased fixation and dwell count, while background showed no significant effects. Furthermore, significant relationships were found between the number of presented images and eye-movement and decision time. Less time was needed in 2AFC (alternative forced choice test), 3AFC and 4AFC and significantly more time was needed to choose one alternative out of 7AFC and 8AFC. The results of the two studies show that the investigated bottom-up factors can significantly influence gazing behavior, and therefore need to be carefully considered when planning or comparing results of eye-tracking experiments.     

Overlapping tracks processed by TIG melting TiC preplaced powder on low alloy steel surfaces

An overlapping composite track coating was produced on a steel surface by preplacing a 0·5 mm thick layer of TiC powder and then melting using a tungsten inert gas torch of constant energy input. The influence of the overlapping operation on preheating of the substrate, the dissolution of TiC particulates and the subsequent depth and hardness of the composite layer was analysed. The melt microstructure consisted of both undissolved and partially dissolved TiC particulates, together with a variety of morphologies and sizes of TiC particles precipitated during solidification. Preheating, resulting from the overlapping operation, occurred, producing additional melting of the TiC particulates and deeper melt depths but with a reduced volume fraction of TiC precipitates in the subsequent tracks. A maximum hardness of over 800 HV was developed in the composite layer. The high hardness was unevenly distributed in tracks melted at the initial and final stages, while it varied across the melt depths in other tracks.     

Ultrasonic-vibration-assisted laser annealing of fluorine-doped tin oxide thin films for improving optical and electrical properties: Overlapping rate optimization

An ultrasonic-vibration-assisted laser annealing method was developed to enhance the performance of fluorine-doped tin oxide (FTO) thin films. The influences of ultrasonic vibration, laser scan line overlapping rate (L_OR) and laser spot overlapping rate (S_OR) on surface morphology, FTO layer thickness, RMS roughness, crystal structure and photoelectric properties of the FTO films were investigated. The results indicated that the presence of ultrasonic vibration during laser annealing could significantly enhance the film compactness, and using moderate L_OR and S_OR values resulted in significantly decreased FTO layer thicknesses and RMS roughnesses as well as slightly increased crystallite sizes, thus yielding significantly improved optical transmittance values and slightly enhanced electrical conductivity values. It was found that the optimal L_OR and S_OR values for ultrasonic-vibration-assisted laser annealing of the FTO films were 80% and 90%, respectively. The as-obtained film possessed the best overall photoelectric property with an average transmittance (400–800?nm) of 85.9%, a sheet resistance of 8.7?Ω/sq and a figure of merit of 2.51?×?10^–2 Ω^–1. This work may be of great significance in terms of performance optimization of transparent conducting oxide (TCO) thin films.     

Dilated and soft attention-guided convolutional neural network for breast cancer histology images classification

Breast cancer is one of the most common types of cancer in women, and histopathological imaging is considered the gold standard for its diagnosis. However, the great complexity of histopathological images and the considerable workload make this work extremely time-consuming, and the results may be affected by the subjectivity of the pathologist. Therefore, the development of an accurate, automated method for analysis of histopathological images is critical to this field. In this article, we propose a deep learning method guided by the attention mechanism for fast and effective classification of haematoxylin and eosin-stained breast biopsy images. First, this method takes advantage of DenseNet and uses the feature map's information. Second, we introduce dilated convolution to produce a larger receptive field. Finally, spatial attention and channel attention are used to guide the extraction of the most useful visual features. With the use of fivefold cross-validation, the best model obtained an accuracy of 96.47% on the BACH2018 dataset. We also evaluated our method on other datasets, and the experimental results demonstrated that our model has reliable performance. This study indicates that our histopathological image classifier with a soft attention-guided deep learning model for breast cancer shows significantly better results than the latest methods. It has great potential as an effective tool for automatic evaluation of digital histopathological microscopic images for computer-aided diagnosis.     

A tutorial on the segmentation of metallographic images: Taxonomy,new MetalDAM dataset,deep learning-based ensemble model,experimental analysis and challenges

Image segmentation is an important issue in many industrial processes, with high potential to enhance the manufacturing process derived from raw material imaging. For example, metal phases contained in microstructures yield information on the physical properties of the steel. Existing prior literature has been devoted to develop specific computer vision techniques able to tackle a single problem involving a particular type of metallographic image. However, the field lacks a comprehensive tutorial on the different types of techniques, methodologies, their generalizations and the algorithms that can be applied in each scenario. This paper aims to fill this gap. First, the typologies of computer vision techniques to perform the segmentation of metallographic images are reviewed and categorized in a taxonomy. Second, the potential utilization of pixel similarity is discussed by introducing novel deep learning-based ensemble techniques that exploit this information. Third, a thorough comparison of the reviewed techniques is carried out in two openly available real-world datasets, one of them being a newly published dataset directly provided by ArcelorMittal, which opens up the discussion on the strengths and weaknesses of each technique and the appropriate application framework for each one. Finally, the open challenges in the topic are discussed, aiming to provide guidance in future research to cover the existing gaps.