Texture Information Research Articles

Edible Flowers As A Garnish In Food Serving: Knowledge and Cognition of Students of STP AMPTA Yogyakarta Hotel Management Study Program as Research Approach

The objectives of this study are: first, to identify the types of edible flowers which can be used in plating; second, to recognize the knowledge and cognition of the Hotel Management students at STP AMPTA Yogyakarta on the usage of edible plant garnishes for plating. This research is conducted in a qualitative descriptive statistical method. The population and the sample of this research are 30 students of STP AMPTA Yogyakarta majoring in Hotel Management. The sample was collected using a purposive sampling method with the criteria of STP AMPTA students in Hotel Management study program who were taking food processing practice 2 course or students who were in 3rd semester in 2022/2023 academic year, with the total of the respondent of 30 students. The methods of data collecting included in-depth interview, observation, documentation, and literature review. The in-depth interview was conducted with the lecturers (chef) in food processing practice class at STP AMPTA in regard to the types of edible flower used for garnishes. The method used in analysing the data is by describing or presenting the data that had been collected without intending to draw a conclusion that is generally applicable. The data collected is the students’ knowledge and cognition of edible flowers. The result of the study found that the types of edible plant garnishes used in STP AMPTA Yogyakarta are edible leaf (red sorel, nasturtium, pea tendril) and edible flower (viola and pansy). Besides that, the knowledge and cognition indicator revealed the average of variative responses from positive to negative. The average positive responses indicated that they acknowledge the types of edible garnish plants and are confident in putting edible plant garnishes in their plating. Meanwhile, the average of negative responses implicated the students’ lack of information and understanding of flavor and texture of edible plant garnishes they used.

Calculation of the CRSS ratios of Ti80 alloy and its application in prediction of texture in Pilger cold rolling

The accurate critical resolved shear stress (CRSS) ratios of different slip systems and deformation history are vital for the texture simulation and controlling for Ti80 alloy pipe during Pilger cold rolling process. This study proposed a comprehensive framework for determining these parameters. A method to calculate the CRSS ratio based on the statistics of activated slip systems was proposed, which could effectively eliminate the error of activated slip systems proportion caused by microtexture. No twinning was observed in the deformation of Ti80 alloy, and the activated slip systems of {0002}<11 2‾ 0>, {101‾ 0}<112‾ 0>, {101‾ 1}<112‾ 0> and {112‾ 2}<112‾ 3> were observed through uniaxial in-situ tensile test combined with EBSD at room temperature. And the CRSS ratio of Ti80 alloy has been calculated approximately as τBasal<a>: τPrism<a>: τPyram<a>: τPyram<a> = 1:0.8:3.5:6. Based on visco-plastic self-consistent (VPSC) model and the calculated CRSS, the texture with shear strain and without shear strain was simulated respectively in the Pilger cold rolling process. Meanwhile, the mechanism of texture formation was analyzed. The texture component was [0001] ‖ TD, and [11-20]‖ AD when the traditional velocity gradient neglecting shear strain was adopted in simulation. However, the shear strain in ZR direction would cause the texture to rotate 30° around the [0001] axis. Compared with that only considering the velocity gradient in the normal strain direction, the rolling texture can be more accurately predicted when considering the history of velocity gradient in all directions.

Mineralogical characterization and structural control of the Tadaout-Tizi n’Rsas vein field (eastern Anti-Atlas Morocco)

The Tadaout-Tizi n’Rsas (TTR) polymetallic (Pb, Cu, Zn) vein field, located at the southeastern of the Moroccan eastern Anti-Atlas, is hosted in sedimentary sandstone formations of the Ktaoua Group of the upper Ordovician. These deposits are reported to be late Variscan to Post-variscan in age, and are related to the emplacement of late Permian doleritic magma event outcropping in the Tafilalet region. Structural and paragenetic studies of the TTR mineralization deposit were conducted in order to establish a general model of the mineralization. A two-stage model of the formation of the mineralized veins of the TTR vein field is proposed herein. The first episode is attributed to the late Variscan phase. It is a trantensive regime characterized by the presence of lenticular structures related to the normal dextral movement of the major faults. This episode is coeval with the emplacement and brecciation of the polymetallic mineralization of the TTR vein field (galena, chalcopyrite, sphalerite, and pyrite). The second episode is associated with normal faults, during the extensional phase corresponding to the tectonic relaxation of shortening (Upper Permian) and more probably during the Atlantic rifting. It is characterized by the formation of a banded texture of mineralization.

Identification of Spinal Disorders Based on Spine X-ray Dataset Processing Using the LBP and CNN Algorithms

This research will use deep learning in conducting spinal x-ray image analysis but computational time problems are a problem of this study. Computations on deep learning across multiple nodes can increase training time and longer computation time compared to machine learning models. Based on experimental results, the best spine x-ray image classification results when using the CNN model with accuracy at the training stage, evaluation stage and test stage were 69.00%, 83.33% and 81.16% respectively. CNN models optimized with LBP get the lowest accuracy, with results at the training stage of 62.64%, validation stage of 75.00% and testing stage of 65.22%. LBP feature extraction turns out to have several drawbacks when combined with the CNN model, one major drawback is its inability to process global spatial information while retaining local texture information which causes LBP to be unable to capture the entire structure or context of the image, focusing only on local patterns so that many features of the image are lost. Another issue is the sensitivity of CNNs to image data, which can affect classification accuracy.

Yield locus and texture evolution of AA7475-T761 aluminum alloy under planar biaxial loading: An experimental and analytical study

AA7475 aluminum alloy is used as a structural material in aerospace and automobile applications where complex loading conditions are applicable. The material properties under multi-axial loading are recommended for efficient component design. Hence, the mechanical behaviour of AA7475-T761 aluminium alloy was investigated through planar biaxial tensile tests. The yield locus evolution and plastic strain direction were measured at higher plastic strain values (up to 7 %) at various load ratios. The yield loci were constructed and compared with existing yield criteria. Yld2000–2d yield criterion demonstrated accurate predictions with a deviation of approximately 1 %, highlighting its effectiveness in capturing the yield behavior of AA7475. Microstructure analysis using Electron Backscatter Diffraction (EBSD) was conducted to understand the misorientation evolution under the multi-axial loading. Bulk-texture analysis was performed using X-ray diffraction method. Texture analysis revealed that uniaxial deformation favoured the development of Cube and Inverse-Copper textures, while biaxial deformation yielded split Inverse-Goss texture formation. Fractography study shows very different fracture surfaces of biaxial samples compared to uniaxial samples. Overall, this study contributes to a comprehensive understanding of the yield behavior, microstructure, and texture evolution of AA7475-T761 aluminium alloy under different loading conditions at very large strains.

Measuring dynamic deformation of a rotating blade by point cloud matching algorithm

In this paper, a point cloud matching algorithm is proposed for the scenario of measuring the dynamic deformation field of a rotating blade. Unlike conventional scheme based on Digital Image Correlation (DIC), the essence of this scheme is to reconstruct individual 3D feature points, instead of a group of feature points in a finite-size subset, on the measurement surface and then track their relative offset from reference baseline. The principles of 3D feature-point reconstruction and straddle-frame tracking are similar to those being used in the algorithm of Particle Tracking Velocimetry (PTV); therefore, no additional tags on feature points to facilitate the perspective matching and tracking is needed. Experiment test shows that this scheme works well in the scenario of high feature-point density (0.026 points per pixel), which cannot be achieved by existing feature-point-tagging methods. Both the rigid motion of the rotating blade and its dynamic deformation field can be reliably obtained. Comparing to DIC-based scheme, the benefit of the present proposed scheme includes the improvement of spatial resolution, the insensitivity to feature-point density, as well as the avoidance of outliers due to insufficient texture information.

Synthetic Data-Driven Real-Time Detection Transformer Object Detection in Raining Weather Conditions

Images captured in rainy weather conditions often suffer from contamination, resulting in blurred or obscured objects, which can significantly impact detection performance due to the loss of identifiable texture and color information. Moreover, the quality of the detection model plays a pivotal role in determining detection outcomes. This study adopts a dual perspective, considering both pre-trained models and training data. It employs 15 image augmentation techniques, combined with neural style transfer (NST), CycleGAN, and an analytical method, to synthesize images under rainy conditions. The Real-Time Detection Transformer (RTDETR) and YOLOv8 pre-trained models are utilized to establish object detection frameworks tailored for rainy weather conditions. Testing is carried out using the DAWN (Detection in Adverse Weather Nature) dataset. The findings suggest compatibility between the pre-trained detection models and various data synthesis methods. Notably, YOLOv8 exhibits better compatibility with CycleGAN data synthesis, while RTDETR demonstrates a stronger alignment with the NST and analytical approaches. Upon the integration of synthesized rainy images into model training, RTDETR demonstrates significantly enhanced detection accuracy compared to YOLOv8, indicating a more pronounced improvement in performance. The proposed approach of combining RTDETR with NST in this study shows a significant improvement in Recall (R) and mAP50-95 by 16.35% and 15.50%, respectively, demonstrating the robust rainy weather resilience of this method. Additionally, RTDETR outperforms YOLOv8 in terms of inference speed and hardware requirements, making it easier to use and deploy in real-time applications.

Interferometric phase diagram generation method based on dot trace texture information and semantic segmentation of correlation coefficients

This paper proposes a method for generating interferometric phase diagrams, which includes interferometric image registration based on Dot Trace Texture Information (DTTI) and interferometric phase filtering based on semantic segmentation. First, the InSAR images are sharpened according to the different backscattering characteristics of various pixel values, and DTTI is extracted to generate the Dot Trace Texture Map (DTTM). Second, SIFT feature points are extracted from two InSAR coherent complex images. They are then screened by comparison with DTTI. These selected points are used to calculate the registration relationship, ensuring precise registration of the two images. Third, the interferometric phase diagram is segmented by semantics based on correlation coefficients. For high-quality interferometric phase regions, we use two-dimensional frequency domain rotational symmetric Gaussian Laplace and wavelet domain filters successively. For low-quality regions, we use an average filter to smooth out noise. The superiority of the proposed algorithm was verified through comparative experiments.

A GPU-Based Integration Method from Raster Data to a Hexagonal Discrete Global Grid

This paper proposes an algorithm for the conversion of raster data to hexagonal DGGSs in the GPU by redevising the encoding and decoding mechanisms. The researchers first designed a data structure based on rhombic tiles to convert the hexagonal DGGS to a texture format acceptable for GPUs, thus avoiding the irregularity of the hexagonal DGGS. Then, the encoding and decoding methods of the tile data based on space-filling curves were designed, respectively, so as to reduce the amount of data transmission from the CPU to the GPU. Finally, the researchers improved the algorithmic efficiency through thread design. To validate the above design, raster integration experiments were conducted based on the global Aster 30 m digital elevation dataDEM, and the experimental results showed that the raster integration accuracy of this algorithms was around 1 m, while its efficiency could be improved to more than 600 times that of the algorithm for integrating the raster data to the hexagonal DGGS data, executed in the CPU. Therefore, the researchers believe that this study will provide a feasible method for the efficient and stable integration of massive raster data based on a hexagonal grid, which may well support the organization of massive raster data in the field of GIS.

A video object detector with Spatio-Temporal Attention Module for micro UAV detection

Many deep neural network-based methods have recently been proposed for object detection due to the significant success of deep learning in computer vision. However, existing object detection methods typically extract the appearance features of objects from single image so that they usually suffer from poor performance in detecting micro Unmanned Aerial Vehicle (UAV), because micro UAV lacks of rich color, shape and texture information. To address this issue, we introduce the temporal information of objects from videos and develop a Spatio-Temporal Attention Module (STAM) to efficiently enhance feature map extraction for detecting micro UAV, and then integrate STAM into YOLOX to develop a video object detector for micro UAV. Meanwhile, we propose a lightweight Spatial Pyramid Pooling (SPP) module termed Group Simplified Spatial Pyramid Pooling-Fast with Cross Stage Partial (Group SimSPPFCSP) for the backbone’s final stage layer to efficiently and lightly extract more semantic information, and we propose a neck with rich propagation pathways (NRPP) to facilitate the effective propagation of spatial and temporal information across different levels. Furthermore, we propose two data augmentation operations including SeqMosaic and SeqMixUp, to augment video data for video object detection. Experimental results show that our model can achieve competitive precision (with 5.0 mAP and 8.1 mAPSmall improvement) while maintaining real-time inference speed (35.3 fps).

Effect of Inoculation with Autochthonous Lactic Acid Bacteria on Flavor, Texture, and Color Formation of Dry Sausages with NaCl Partly Substituted by KCl.

The effects of inoculating lactic acid bacteria (LAB), specifically Lactiplantibacillus plantarum, Latilactobacillus sakei, Latilactobacillus curvatus, and Weissella hellenica on the flavor, texture, and color formation of dry sausages in which NaCl was partially substituted by 40% KCl, were explored in this study. It was found that LAB inoculation increased the presence of ketones, alcohols, acids, esters, and terpenes. It also reduced the pH, moisture, protein, and fat content, improving the b*-value, flavor, and texture of the sausages. Notably, L. sakei inoculation showed the most significant improvement in dry sausages with NaCl substitutes, especially on the reduction of bitterness. Meanwhile, there was a close positive correlation between the LAB count with the alcohols and esters formation of dry sausage with NaCl substitution (p < 0.05). These findings offer insight into improving the product characteristics of dry sausages using NaCl substitutes.

Dual-branch network based on transformer for texture recognition

Texture recognition is the task of identifying and understanding the patterns and structures present in textures within digital images, constituting a highly challenging research topic. With the rapid advancement of deep learning, CNN-based methods have progressively supplanted traditional approaches, emerging as the predominant techniques for texture recognition. Nevertheless, these methods face limitations in capturing the structural information of textures from global features, attributed to the constraints of CNNs. Structural information stands out as a crucial factor in describing and recognizing real-world texture images. To address this challenge, we propose DBTrans, a dual-branch network based on Transformer architecture for texture recognition. DBTrans leverages the transformer's extraction capability for global features (low-frequency information) to capture the structural nuances of texture images. Additionally, recognizing the distinctive nature of texture recognition tasks, we propose a Transformer variant module tailored for this purpose, named Residual Pooling Transformer (RPT). Finally, we investigate the impact of different branches and modules on network performance and showcase the performance of DBTrans on five public datasets, achieving state-of-the-art accuracy.

A simple and robust method for laboratory-scale preparation of butter

The aim of this study was to develop a small-scale model system resembling the micro- and meso-structure of butter, namely having a water-droplet size distribution and water content close to that of commercially produced butter. Although it is possible to churn cream on a small scale, matching the microstructure of butter is a challenge. A 2-step churning process was introduced with the application of a kitchen mixer. The resulting microstructure was evaluated using confocal laser scanning microscopy. In addition, low-field nuclear magnetic resonance was used to determine the water-droplet size distribution. Results demonstrated that a water content of 16–19% could be obtained with the proposed procedure, close to the standard water content of 16%. Average water droplet size ranged between 2.5 to 4.3 µm and did not depend on batch-to-batch variations, nor storage-induced differences in the cream. In conclusion, the proposed method could be employed to prepare water-in-oil emulsions with a microstructure similar to that of butter and opens new opportunities for studying microbial growth, flavor release, and texture formation.

Neural Radiance Selector: Find the best 2D representations of 3D data for CLIP based 3D tasks

Representing the world in 3D space provides vivid texture and depth information. However, 3D datasets currently do not match the scale of 2D datasets. There is a growing trend in representing 3D data as multi-view 2D images and using large-scale 2D models, to solve 3D tasks. In this work, we present the Neural Radiance Selector, a method that automatically selects the optimal 2D representations of 3D data. Instead of indiscriminately sampling multi-view 2D images, we define the optimal 2D views as those capable of reconstructing the entire 3D scene with a conditional neural radiance field. We propose two distinct methods for 3D point cloud data and 3D implicit models to achieve faster inference. We demonstrate the efficacy of our methods in various 3D tasks, including zero-shot 3D point cloud classification, 3D implicit model classification, and language-guided NeRF editing.

CAA: Class-Aware Affinity calculation add-on for semantic segmentation

Leveraging contextual dependencies is a commonly used technique to enhance the performance of image segmentation. However, existing solutions do not effectively catch the class-level association between the pixels along the boundary across the objects of the different classes but focus more on the local pixel-to-pixel relation. This work proposes a Class-Aware Affinity module (CAA) that considers both pixel-to-pixel relation and pixel-to-class association. We try to argue that the pixel-to-pixel relations still catch the relation (e.g. similarity, attention, or affiliation) on the local texture level. At the same time, it should also consider the association between the pixel and the class context produced by the given image. Pixel-to-class association can best reveal the co-occurrent dependency on the semantic level between the given pixels and their nearby context. Such pixel-to-class association combined with the pixel-to-pixel relations aggregating the local texture information will best mitigate the confusion caused in the boundary regions across the objects of the different classes. Moreover, the proposed framework can serve as a generic add-on to be integrated with the existing image segmentation solution to boost the current performance. Equipped with CAA, we achieve promising performance against the existing work with 54.59% mIoU on ADE20K, 49.96% mIoU on COCO-Stuff10k, and 64.38% mIoU on Pascal-Context.

Lipidomics analysis reveals new insights into crisp grass carp associated with meat texture

Feeding faba beans to grass carp could crisp its muscle texture to avoid softening, the relationship between texture formation throughout the crisping process and the critical lipids regulating the fish quality has not yet been clarified. Herein, an 60-day nutritional trial and untargeted lipidomic analysis was used to study the changes of lipids in crisp grass carp dorsal muscle. A total of 1036 lipids were remarkably different between ordinary and crisp grass carp. The concentrations of the LPC, LPE, PG, Cer, Hex2Cer, SM, MG and MGMG were positively correlated with hardness and springiness, and the CL, TG, PMe, WE, dMePE and AcCa were negative correlation. High content of lipids involved in storage in ordinary grass carp, such as glycerophospholipids, polyunsaturated and saturated fatty acid content. In contrast, high content of membrane components in crisp grass carp, such as monounsaturated fatty acid, sphingolipid and glycerolipids content, and the distribution of PUFA in lipid molecules was related to lipid biosynthesis. This study might provide some insights into improved knowledge of the association between meat texture and lipid molecules in fish fed with faba bean.

DCP-Net: An Efficient Image Segmentation Model for Forest Wildfires

Wildfires usually lead to a large amount of property damage and threaten life safety. Image recognition for fire detection is now an important tool for intelligent fire protection, and the advancement of deep learning technologies has enabled an increasing number of cameras to possess functionalities for fire detection and automatic alarm triggering. To address the inaccuracies in extracting texture and positional information during intelligent fire recognition, we have developed a novel network called DCP-Net based on UNet, which excels at capturing flame features across multiple scales. We conducted experiments using the Corsican Fire Dataset produced by the “Environmental Science UMR CNRS 6134 SPE” laboratory at the University of Corsica and the BoWFire Dataset by Chino et al. Our algorithm was compared with networks such as SegNet, UNet, UNet++, and PSPNet, demonstrating superior performance across three metrics: mIoU, F1-score, and OA. Our proposed deep learning model achieves the best mIoU (78.9%), F1-score (76.1%), and OA (96.7%). These results underscore the robustness of our algorithm, which accurately identifies complex flames, thereby making a significant contribution to intelligent fire recognition. Therefore, the proposed DCP-Net model offers a viable solution to the challenges of wildfire monitoring using cameras, with hardware and software requirements typical of deep learning setups.

Multi-channel and multi-featured extended orb with gabor filter and non-maximum suppression

This research paper presents an enhanced approach to feature extraction using the Oriented FAST and Rotated BRIEF (ORB) algorithm (Rublee et al., 2014). The proposed method leverages the power of Gabor filters (Mehrotra et al., 1992) in combination with Non-Maximum Suppression (Neuback and Van Gool, 2006) to improve the robustness and efficiency of feature detection in computer vision applications. The process begins with the acquisition of an RGB image, which is then transformed into seven single-channel images representing different color and intensity aspects: red, green, blue, hue, saturation, value, and grayscale. Each single-channel image is independently subjected to Gabor filtering, resulting in seven Gabor-filtered images. These images capture distinct texture and frequency information, enhancing the discriminative power of subsequent feature extraction. Subsequently, the Oriented FAST and Rotated BRIEF (ORB) algorithm is applied to each of the seven Gabor-filtered images to extract key points and descriptors. This step yields a comprehensive set of keypoints (Mallick et al., 2015) and descriptors, capturing rich local feature information across multiple image channels. To further refine the extracted features and eliminate redundant keypoints, Non-Maximum Suppression is employed independently on each single-channel image. This process effectively filters out overlapped and false keypoints, ensuring the selection of only the most salient features for downstream tasks. Experimental results demonstrate the efficacy of the proposed approach in improving feature detection performance compared to traditional methods. The combination of Gabor filtering and Non-Maximum Suppression enhances feature discriminability, robustness to noise, and resistance to image transformations, making it well-suited for various computer vision applications, including object recognition, image matching, and scene understanding.

Remote sensing image dehazing using generative adversarial network with texture and color space enhancement

Remote sensing is gradually playing an important role in the detection of ground information. However, the quality of remote-sensing images has always suffered from unexpected natural conditions, such as intense haze phenomenon. Recently, convolutional neural networks (CNNs) have been applied to deal with dehazing problems, and some important findings have been obtained. Unfortunately, the performance of these classical CNN-based methods still needs further enhancement owing to their limited feature extraction capability. As a critical branch of CNNs, the generative adversarial network (GAN), composed of a generator and discriminator, has become a hot research topic and is considered a feasible approach to solving the dehazing problems. In this study, a novel dehazed generative adversarial network (GAN) is proposed to reconstruct the clean images from the hazy ones. For the generator network of the proposed GAN, the color and luminance feature extraction module and the high-frequency feature extraction module aim to extract multi-scale features and color space characteristics, which help the network to acquire texture, color, and luminance information. Meanwhile, a color loss function based on hue saturation value (HSV) is also proposed to enhance the performance in color recovery. For the discriminator network, a parallel structure is designed to enhance the extraction of texture and background information. Synthetic and real hazy images are used to check the performance of the proposed method. The experimental results demonstrate that the performance can significantly improve the image quality with a significant increment in peak-signal-to-noise ratio (PSNR). Compared with other popular methods, the dehazing results of the proposed method closely resemble haze-free images.

Densely integrated multi-branch attentive net for image dehazing

Single image dehazing is a fundamental but challenging task in image processing. Various deep learning-based methods have achieved great dehazing performance. However, there are still hazy residues, even color distortion and texture loss when removing haze from complex outdoor images in dense hazy scenes. A densely integrated multi-branch attentive net for image dehazing is proposed in the paper to address the above problems. The network includes a multi-scale feature extraction module and a dense-feature fusion module. The multi-scale feature extraction module adopts a multi-branch structure composed of residual channel attention blocks, which can expand the receptive field and filter the extracted features of diverse scales by weighting for fusion. It raises network learning accuracy. The dense-feature fusion module contains a multi-level feature fusion module for front and back layers, a color information renovation module, and a feature enhancement module. It achieves dynamically adjusting the channel weights of features at diverse scales, learning rich context information and suppressing redundant information, and compensating for the lack of color and texture information. The dense-feature fusion module bolsters the generalization capability of the network. The proposed method achieves superior objective and subjective evaluation results via quantitative and qualitative experiments on synthetic hazy images and natural hazy images, with better generalization ability and dehazing effect than the current SOTA dehazing algorithms, and effectively ameliorates the color distortion and incomplete dehazing.