Spectral superresolution (SSR) aims to improve the spectral resolution of images from multispectral imagery or even RGB images. However, the majority of existing SSR methods do not fully exploit the ...spatial and texture features in RGB images, which would lead to the image unreal, distorted of the high frequency details in the reconstructed SSR images. In this study, a hybrid spectral and texture attention pyramid network (STANet) is proposed to reconstruct hyperspectral images (HSI) with RGB bands of remote sensing image as input. More specifically, a learnable texture feature extraction module is proposed, aiming to make full use of the texture features in the RGB images which is important in the subsequent spectral reconstruction. Furthermore, to better reconstruct the correlations between various spectral channels, a spatial-spectral constrained cross-attention module is introduced. Finally, a novel spectral-texture fusion method is proposed, which successfully alleviates the problem of insufficient deep interaction among multiple deep features. On three remote sensing datasets, STANet demonstrates state-of-the-art performance, with its Peak Signal-to-Noise Ratio (PSNR) exceeding the sub-optimal methods by 0.7266dB, 0.6724dB, and 0.6dB respectively. The results of the land cover classification experiment using the reconstructed HSI further demonstrated the performance of the STANet algorithm.
Surface texture is one of the important cues for human beings to identify different fabrics. This paper presents a novel design of a surface texture sensor by imitating human active texture ...perception by touch. A thin polyvinylidene fluoride (PVDF) film is used as the sensitive element to fabricate a high-accuracy, high-speed-response fabric surface texture sensor, and a mechanism is designed to produce the relative motion at a certain speed between the texture sensor and the surface of the perceived fabric with constant contact force. Thus, the surface texture property can be measured as the output charge of the PVDF film of the sensor induced by the small height/depth variation of the moving fabric surface. A texture feature extraction method by compressing the zero value spectral lines in frequency domain is proposed. In addition, a radial basis function (RBF) neural networks based on unsupervised K-means clustering algorithm is used as classifier for texture recognition. The experiments show that the proposed texture sensor is effective in detecting the feature signals of fabric surface textures, which are suitable for the RBF networks to classify the different fabrics.
The tribological characteristics of sliding surfaces have been remarkably improved by surface texturing. Surface texturing can be beneficial in many ways; for example, it can reduce friction and ...wear, increase load carrying capacity, and increase fluid film stiffness. The design process for surface texturing is highly correlated to the particular functions of any application for which texturing is required. Texture quality is greatly affected by manufacturing methods, therefore, it is important to have a detailed understanding of the related parameters of any technique.
The use of surface texturing to improve the cutting performance of tools is a relatively new application. These textures improve cutting performance by enhancing lubricant availability at the contact point, reducing the tool-chip contact area, and trapping wear debris. Reductions in crater and flank wear, friction force, cutting forces, and cutting temperature are the main benefits obtained by this technique. To date, surface texturing has been successfully used in drilling, milling, and turning operations.
This article provides an overview of the techniques that have been used in industry and research platforms to manufacture micro-/nano-textures for tribological applications, and it examines the effects of surface textures on cutting tool performance.
Full text
Available for:
BFBNIB, GIS, IJS, KISLJ, NUK, PNG, UL, UM, UPUK
Display omitted
•A novel application is introduced, X-ray chest image based Covid-19 detection.•Deep learning approaches are used for Covid-19 detection.•Local texture descriptors are also used in ...Covid-19 detection.
COVID-19 is a novel virus that causes infection in both the upper respiratory tract and the lungs. The numbers of cases and deaths have increased on a daily basis on the scale of a global pandemic. Chest X-ray images have proven useful for monitoring various lung diseases and have recently been used to monitor the COVID-19 disease. In this paper, deep-learning-based approaches, namely deep feature extraction, fine-tuning of pretrained convolutional neural networks (CNN), and end-to-end training of a developed CNN model, have been used in order to classify COVID-19 and normal (healthy) chest X-ray images. For deep feature extraction, pretrained deep CNN models (ResNet18, ResNet50, ResNet101, VGG16, and VGG19) were used. For classification of the deep features, the Support Vector Machines (SVM) classifier was used with various kernel functions, namely Linear, Quadratic, Cubic, and Gaussian. The aforementioned pretrained deep CNN models were also used for the fine-tuning procedure. A new CNN model is proposed in this study with end-to-end training. A dataset containing 180 COVID-19 and 200 normal (healthy) chest X-ray images was used in the study’s experimentation. Classification accuracy was used as the performance measurement of the study. The experimental works reveal that deep learning shows potential in the detection of COVID-19 based on chest X-ray images. The deep features extracted from the ResNet50 model and SVM classifier with the Linear kernel function produced a 94.7% accuracy score, which was the highest among all the obtained results. The achievement of the fine-tuned ResNet50 model was found to be 92.6%, whilst end-to-end training of the developed CNN model produced a 91.6% result. Various local texture descriptors and SVM classifications were also used for performance comparison with alternative deep approaches; the results of which showed the deep approaches to be quite efficient when compared to the local texture descriptors in the detection of COVID-19 based on chest X-ray images.
Full text
Available for:
GEOZS, IJS, IMTLJ, KILJ, KISLJ, NLZOH, NUK, OILJ, PNG, SAZU, SBCE, SBJE, UILJ, UL, UM, UPCLJ, UPUK, ZAGLJ, ZRSKP
A combined nickel-cobalt-based eutectic high entropy alloy (Ni-Co-based HEA) has been designed based on the valence electron concentration (VEC) value. The microstructure of the developed alloy ...consists of a face-centered cubic (FCC) and ordered cubic (B2) structure, which was validated using CALPHAD. The microstructure is hierarchical with length scales in micrometers (lamellar eutectic morphology) and nanometers (B2 length scale). B2 phase precipitation was observed in the supersaturated FCC primary phase. The orientation relationship (OR) between the phases exhibited a strong Kurdjimov-Sachs (KS) type OR, typical of FCC/BCC interface structures. This EHEA displayed good yield strength at room temperature and strain rate insensitivity in the 10
−3
-10
−1
strain rate range.
Full text
Available for:
BFBNIB, GIS, IJS, KISLJ, NUK, PNG, UL, UM, UPUK
We present a simple and effective architecture for fine-grained recognition called Bilinear Convolutional Neural Networks (B-CNNs). These networks represent an image as a pooled outer product of ...features derived from two CNNs and capture localized feature interactions in a translationally invariant manner. B-CNNs are related to orderless texture representations built on deep features but can be trained in an end-to-end manner. Our most accurate model obtains 84.1, 79.4, 84.5 and 91.3 percent per-image accuracy on the Caltech-UCSD birds 1, NABirds 2, FGVC aircraft 3, and Stanford cars 4 dataset respectively and runs at 30 frames-persecond on a NVIDIA Titan X GPU. We then present a systematic analysis of these networks and show that (1) the bilinear features are highly redundant and can be reduced by an order of magnitude in size without significant loss in accuracy, (2) are also effective for other image classification tasks such as texture and scene recognition, and (3) can be trained from scratch on the ImageNet dataset offering consistent improvements over the baseline architecture. Finally, we present visualizations of these models on various datasets using top activations of neural units and gradient-based inversion techniques. The source code for the complete system is available at http://vis-www.cs.umass.edu/bcnn.
Textured grinding wheels: A review Li, Hao Nan; Axinte, Dragos
International journal of machine tools & manufacture,
October 2016, 2016-10-00, Volume:
109
Journal Article
Peer reviewed
Textured grinding wheels (TGWs) are wheels that have both specially-designed active and passive grinding areas on their geometrically active surfaces. The active area allows TGWs to perform the ...intermittent grinding process such that total wheel-workpiece contact time, average grinding forces and temperature in the cutting zone can be reduced. The passive area (or textures) refers to the non-grinding area where no grain is located at and the main functions of it include serving as reservoirs to transport more coolants/lubricants into the grinding zone and providing larger chip disposal space. With the increasingly demanding requirements from industries, the continuous evolution of TGWs has been enforced. However, to the best of the authors' knowledge, no comprehensive review on TGWs has been reported yet. To address this gap in the literature, this paper aims to present an informative literature survey of research and engineering developments in relation to TGWs, define and categorise TGW concepts, explain basic principles, briefly review the concept developments, discuss key challenges, and further provide new insights into understanding of TGWs for their advanced future engineering applications.
•The studies related with textured grinding wheels (TGWs) have been reviewed.•The definition, classification, and basic principle of TGWs have been given.•Texture geometry, dimension and texturing methods have been analyzed.•Promising future directions related with TGWs have been given.
Full text
Available for:
GEOZS, IJS, IMTLJ, KILJ, KISLJ, NUK, OILJ, PNG, SAZU, SBCE, SBJE, UL, UM, UPCLJ, UPUK, ZRSKP
Structure-texture image decomposition is a fundamental but challenging topic in computational graphics and image processing. In this paper, we introduce a structure-aware and a texture-aware measures ...to facilitate the structure-texture decomposition (STD) of images. Edge strengths and spatial scales that have been widely-used in previous STD researches cannot describe the structures and textures of images well. The proposed two measures differentiate image textures from image structures based on their distinctive characteristics. Specifically, the first one aims to measure the anisotropy of local gradients, and the second one is designed to measure the repeatability degree of signal patterns in a neighboring region. Since these two measures describe different properties of image structures and textures, they are complementary to each other. The STD is achieved by optimizing an objective function based on the two new measures. As using traditional optimization methods to solve the optimization problem will require designing different optimizers for different functional spaces, we employ an architecture of deep neural network to optimize the STD cost function in a unified manner. The experimental results demonstrate that, as compared with some state-of-the-art methods, our method can better separate image structure and texture and result in shaper edges in the structural component. Furthermore, to demonstrate the usefulness of the proposed STD method, we have successfully applied it to several applications including detail enhancement, edge detection, and visual quality assessment of super-resolved images.
•Deep layers of Convolutional Neural Networks are used for feature extraction.•Handcrafted and learned features are used together to extract information.•Different architectures for combining ...handcrafted and learned features are proposed.•Combination of different features is used to solve image classification problems.
This work presents a generic computer vision system designed for exploiting trained deep Convolutional Neural Networks (CNN) as a generic feature extractor and mixing these features with more traditional hand-crafted features. Such a system is a single structure that can be used for synthesizing a large number of different image classification tasks. Three substructures are proposed for creating the generic computer vision system starting from handcrafted and non-handcrafter features: i)one that remaps the output layer of a trained CNN to classify a different problem using an SVM; ii) a second for exploiting the output of the penultimate layer of a trained CNN as a feature vector to feed an SVM; and iii) a third for merging the output of some deep layers, applying a dimensionality reduction method, and using these features as the input to an SVM. The application of feature transform techniques to reduce the dimensionality of feature sets coming from the deep layers represents one of the main contributions of this paper. Three approaches are used for the non-handcrafted features: deep transfer learning features based on convolutional neural networks (CNN), principal component analysis network (PCAN), and the compact binary descriptor (CBD). For the handcrafted features, a wide variety of state-of-the-art algorithms are considered: Local Ternary Patterns, Local Phase Quantization, Rotation Invariant Co-occurrence Local Binary Patterns, Completed Local Binary Patterns, Rotated local binary pattern image, Globally Rotation Invariant Multi-scale Co-occurrence Local Binary Pattern, and several others. The computer vision system based on the proposed approach was tested on many different datasets, demonstrating the generalizability of the proposed approach thanks to the strong performance recorded. The Wilcoxon signed rank test is used to compare the different methods; moreover, the independence of the different methods is studied using the Q-statistic. To facilitate replication of our experiments, the MATLAB source code will be available at (https://www.dropbox.com/s/bguw035yrqz0pwp/ElencoCode.docx?dl=0).
Full text
Available for:
GEOZS, IJS, IMTLJ, KILJ, KISLJ, NUK, OILJ, PNG, SAZU, SBCE, SBJE, UL, UM, UPCLJ, UPUK, ZRSKP
•Tree species identification using bark texture information.•Improving the discrimination performance of local ternary patterns.•Optimizing a multi layer neural network to classify bark textures.
...Tree identification is one of the areas that are regarded by researchers. It is done by human expert with high cost. Experts believe that tree bark has a high relation with species in comparison with other phenotype properties. Repeated textures in the bark is usually various with slight differences. So, lbp-like descriptors used in most recent works. But, most of them do not provide discriminative features. Also some texture descriptors are sensitive to noise and rotation. Local ternary pattern is one of the operators that are resistant to the noise with high discrimination. In most of descriptors, histogram of patterns is used to extract features. But, it is rotation sensitive with high computational complexity. In this paper, the main contribution is to propose a method for bark texture classification with high accuracy based on the improved local ternary patterns (ILTP). In the proposed ILTP, the ternary patterns are coded into two binary patterns, and then each one is classified into two uniform/non-uniform groups. The extracted patterns are labeled according to the degree of uniformity. Finally the occurrence probability of the labels is extracted as features. Also, a multilayer perceptron is designed with four theories in the number of hidden nodes. Experimental results on two benchmark datasets showed that our proposed approach provides higher classification accuracy than most well known methods. Noise-resistant and rotation invariant are other advantages of the presented method. The proposed bark texture classification, because of its high classification accuracy, can be applied in real applications and reduce the financial costs and human risks in the diagnosis of plant species.
Full text
Available for:
GEOZS, IJS, IMTLJ, KILJ, KISLJ, NLZOH, NUK, OILJ, PNG, SAZU, SBCE, SBJE, UILJ, UL, UM, UPCLJ, UPUK, ZAGLJ, ZRSKP
PDF
