•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.
The friction force for aircraft landing is mainly provided by the texture of runway surfaces. The mechanism underlying friction force generation is the energy dissipation of tire rubber materials ...during random excitation induced by asperities. However, the runway surface texture is deteriorated by cyclic loading and environmental effects during the service life of a runway, leading to loss of braking force and extension of landing distance. Additionally, when an aircraft lands on a wet runway at a high velocity, the hydrodynamic force causes the tires to detach from the runway surface, which is risky and may lead to the loss of aircraft control and runway excursion. Worn-out surfaces along with wet conditions increase the risk of poor control during aircraft landing. Accordingly, this study investigated three types of asphalt runways (SMA-13, AC-13, and OGFC-13). Surface texture deterioration was simulated using a surface texture wear algorithm. Kinematic friction models were established based on the viscoelastic property of rubber materials, power spectrum density, and statistics of surface textures. A finite element model was developed by considering a real rough runway surface and different water film depths (3, 7, and 10 mm). A comparison of hydroplaning speed was conducted between numerical simulation and former experiments. The effects of different factors, such as velocity, wear ratio, runway type, water film depth, and slip ratio, on the skid resistance of the runway were analyzed.
•Runway surface texture deterioration was considered in FEM simulation based on a surface texture wear algorithm.•The friction coefficient between tire rubber and runway was calculated based on surface texture and tread rubber property.•The effect of surface texture deterioration and wet conditions were considered simultaneously in finite element model.
Classifying texture images, especially those with significant rotation, illumination, scale, and viewpoint changes, is a fundamental and challenging problem in computer vision. This paper proposes a ...simple yet effective image descriptor, called Locally Encoded TRansform feature hISTogram (LETRIST), for texture classification. LETRIST is a histogram representation that explicitly encodes the joint information within an image across feature and scale spaces. The proposed representation is training-free, low-dimensional, yet discriminative and robust for texture description. It consists of the following major steps. First, a set of transform features is constructed to characterize local texture structures and their correlation by applying linear and non-linear operators on the extremum responses of directional Gaussian derivative filters in scale space. Established on the basis of steerable filters, the constructed transform features are exactly rotationally invariant as well as computationally efficient. Second, the scalar quantization via binary or multi-level thresholding is adopted to quantize these transform features into texture codes. Two quantization schemes are designed, both of which are robust to image rotation and illumination changes. Third, the cross-scale joint coding is explored to aggregate the discrete texture codes into a compact histogram representation, i.e., LETRIST. Experimental results on the Outex, CUReT, KTH-TIPS, and UIUC texture data sets show that LETRIST consistently produces better or comparable classification results than the state-of-the-art approaches. Impressively, recognition rates of 100.00% and 99.00% have been achieved on the Outex and KTH-TIPS data sets, respectively. In addition, the noise robustness is evaluated on the Outex and CUReT data sets. The source code is publicly available at https://github.com/stc-cqupt/letrist .
While soil erosion drives land degradation, the impact of erosion on soil microbial communities and multiple soil functions remains unclear. This hinders our ability to assess the true impact of ...erosion on soil ecosystem services and our ability to restore eroded environments. Here we examined the effect of erosion on microbial communities at two sites with contrasting soil texture and climates. Eroded plots had lower microbial network complexity, fewer microbial taxa, and fewer associations among microbial taxa, relative to non-eroded plots. Soil erosion also shifted microbial community composition, with decreased relative abundances of dominant phyla such as Proteobacteria, Bacteroidetes, and Gemmatimonadetes. In contrast, erosion led to an increase in the relative abundances of some bacterial families involved in N cycling, such as Acetobacteraceae and Beijerinckiaceae. Changes in microbiota characteristics were strongly related with erosion-induced changes in soil multifunctionality. Together, these results demonstrate that soil erosion has a significant negative impact on soil microbial diversity and functionality.
•We propose a learnable residual pooling layer comprising of a residual encoding module and an aggregation module that retains spatial information and aggregates them to a feature with a lower ...dimension.•We propose an end-to-end learning framework that integrates the residual pooling layer into any pre-trained CNN model for efficient feature transfer for texture recognition.•We compare the performance of the proposed pooling layer with other residual encoding schemes to illustrate state-of-the-art performance on benchmark texture datasets, an industry dataset and a scene recognition dataset.
Current deep learning-based texture recognition methods extract spatial orderless features from pre-trained deep learning models that are trained on large-scale image datasets. These methods either produce high dimensional features or have multiple steps like dictionary learning, feature encoding and dimension reduction. In this paper, we propose a novel end-to-end learning framework that not only overcomes these limitations, but also demonstrates faster learning. The proposed framework incorporates a residual pooling layer consisting of a residual encoding module and an aggregation module. The residual encoder preserves the spatial information for improved feature learning and the aggregation module generates orderless feature for classification through a simple averaging. The feature has the lowest dimension among previous deep texture recognition approaches, yet it achieves state-of-the-art performance on benchmark texture recognition datasets such as FMD, DTD, 4D Light and one industry dataset used for metal surface anomaly detection. Additionally, the proposed method obtains comparable results on the MIT-Indoor scene recognition dataset. Our codes are available at https://github.com/maoshangbo/DRP-Texture-Recognition.
The aim of this research is to characterize the unique microstructural features of Al-matrix nanocomposites reinforced by graphene nano-platelets (GNPs), fabricated by multi-pass friction-stir ...processing (FSP). During this process, secondary phase GNPs were dispersed within the stir zone (SZ) of an AA5052 alloy matrix, with a homogenous distribution achieved after five cumulative passes. The microstructural characteristics and crystallographic textures of different regions in the FSPed nanocomposite, i.e., base metal (BM), heat affected zone (HAZ), thermo-mechanical affected zone (TMAZ), and SZ, were evaluated using electron back scattering diffraction (EBSD) and transmission electron microscopy (TEM) analyses. The annealed BM consisted of a nearly random crystal orientation distribution with an average grain size of 10.7μm. The SZ exhibited equiaxed recrystallized grains with a mean size of 2μm and a high fraction of high-angle grain boundaries (HAGBs) caused by a discontinuous dynamic recrystallization (DDRX) enhanced by pinning of grain boundaries by GNPs. The sub-grains and grain structure modification within the HAZ and TMAZ regions are governed by dislocation annihilation and reorganization in the grain interiors/within grains which convert low-angle to high-angle grain boundaries via dynamic recovery (DRV). The FSP process and incorporation of GNPs produced a pre-dominantly {100} cube texture component in the SZ induced by the stirring action of the rotating tool and hindering effect of nano-platelets. Although, a very strong {112} simple shear texture was found in the HAZ and TMAZ regions governed by additional heating and deformation imposed by the tool shoulder. These grain structure and texture features lead to a hardness and tensile strength increases of about 55% and 220%, respectively.
Display omitted
•A new Al-matrix nanocomposite was prepared by friction stir processing.•Improved hardness and strength were attained by incorporation of graphene nano-platelets.•Microstructural changes, restoration mechanisms and textural developments were studied.•The correlation between the microstructural features and textural components was established.
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.
•We proposed a fruit-classification system that can recognize 18 types of fruits.•We used a hybrid feature set with color, texture, and shape information.•We used FNN as the classifier that is ...trained by FSCABC algorithm.•FSCABC–FNN obtained better classification accuracy than existing algorithms.
Fruit classification is a difficult challenge due to the numerous types of fruits. In order to recognize fruits more accurately, we proposed a hybrid classification method based on fitness-scaled chaotic artificial bee colony (FSCABC) algorithm and feedforward neural network (FNN). First, fruits images were acquired by a digital camera, and then the background of each image were removed by split-and-merge algorithm. We used a square window to capture the fruits, and download the square images to 256×256. Second, the color histogram, texture and shape features of each fruit image were extracted to compose a feature space. Third, principal component analysis was used to reduce the dimensions of the feature space. Finally, the reduced features were sent to the FNN, the weights/biases of which were trained by the FSCABC algorithm. We also used a stratified K-fold cross validation technique to enhance the generation ability of FNN. The experimental results of the 1653 color fruit images from the 18 categories demonstrated that the FSCABC–FNN achieved a classification accuracy of 89.1%. The classification accuracy was higher than Genetic Algorithm–FNN (GA–FNN) with 84.8%, Particle Swarm Optimization–FNN (PSO–FNN) with 87.9%, ABC–FNN with 85.4%, and kernel support vector machine with 88.2%. Therefore, the FSCABC–FNN was seen to be effective in classifying fruits.
This paper presents a novel haptic texture authoring algorithm. The main goal of this algorithm is to synthesize new virtual textures by manipulating the affective properties of already existing ...real-life textures. To this end, two different spaces are established: two-dimensional (2-D) "affective space" built from a series of psychophysical experiments where real textures are arranged according to affective properties (hard-soft, rough-smooth) and 2-D "haptic model space" where real textures are placed based on features from tool-surface contact acceleration patterns (movement-velocity, normal-force). Another space, called "authoring space" is formed to merge the two spaces; correlating changes in affective properties of real-life textures to changes in actual haptic signals in haptic space. The authoring space is constructed such that features of the haptic model space that were highly correlated with affective space become axes of the space. As a result, new texture signals corresponding to any point in authoring space can be synthesized based on weighted interpolation of three nearest real surfaces in perceptually correct manner. The whole procedure including the selection of nearest surfaces, finding weights, and weighted interpolation of multiple texture signals are evaluated through a psychophysical experiment, demonstrating the competence of the approach. The results of evaluation experiment show an average normalized realism score of 94<inline-formula><tex-math notation="LaTeX">\%</tex-math></inline-formula> for all authored textures.
Understanding the influence of surface properties (roughness, grooves, discrete textures/dimples) on the performance of hydrodynamically lubricated contacts has been the aim of numerous studies. A ...variety of different numerical models have been employed by many researchers in order to find optimal texturing parameters (shape, size, distribution) for best performance enhancement in terms of load carrying capacity, film thickness, friction and wear. However, the large number of different modeling techniques and complexity in the patterns make finding the optimum texture a challenging task and have led to contrary conclusions. This article outlines the research effort on surface texturing worldwide, reviews the key findings and, in particular, provides a comparative summary of different modeling techniques for fluid flow, cavitation and micro-hydrodynamic effects.
•This article facilitates the application of textures for hydrodynamic contacts.•Functions of surface textures, texture design and modeling techniques are discussed.•Textures must be designed for a given application and range of operating conditions.•Robust models allow the evaluation of texture designs prior to being manufactured.•The three major challenges in numerical modeling are discussed.