Search

Reconstruction of 2-dimensional transcerebellar images into 3-dimensional transcerebellar has an important role in diagnosis and treatment planning in neurology. In this study, we propose the 3D-FHNet method to produce an accurate three-dimensional representation of transcerebellar images. The process begins with the selection of images and the application of image augmentation and enhancement techniques to improve the quality of the initial image. Furthermore, segmentation was carried out using two different architectures, namely U-Net and LinkNet, to compare the performance of the two. After training, both architectures can process object segmentation properly. The best performance was produced by U-Net with a pixel accuracy of 99.83%, Mean IU of 89.71%, FPR of 0.91%, Precision of 85.78%, Recall of 85.31%, and F1 Score of 85.31%. With this accuracy, cross-validation was carried out using a 10-Fold. The experimental results show that U-Net gives better results in terms of transcerebellar image segmentation. After the segmentation process, an initial reconstruction is carried out using the PiFUHD architecture which produces a three-dimensional object. The results of this reconstruction are then taken from four sides to be introduced to the 3D-FHNet architecture, because the main concept of 3DFHNet is to use multiview input. To measure the accuracy of the model, the IoU (Intersection over Union) metric is used for the ground truth obtained from the PiFUHD method. This metric is used to compare the similarities between the reconstruction results and the ground truth, so that information can be obtained about the extent to which the model has succeeded in reconstructing three-dimensional objects accurately. Model performance can be calculated by using the input as ground truth or the IoU (Intersection over Union) method with an average of 76.76%. By using the 3D-FHNet method, three-dimensional image reconstruction of the ultrasound image of the fetal head can be performed accurately. The experimental results show that the 3D-FHNet method produces a more accurate three-dimensional representation of the transcerebellar image compared to the previous method. These results demonstrate great potential in improving diagnosis and treatment planning in neurology, as well as making important contributions to the development of medical image processing technologies. [ABSTRACT FROM AUTHOR]

Detecting parcels accurately and efficiently has always been a challenging task when unloading from trucks onto conveyor belts because of the diverse and complex ways in which parcels are stacked. Conventional methods struggle to quickly and accurately classify the various shapes and surface patterns of unordered parcels. In this paper, we propose a parcel-picking surface detection method based on deep learning and image processing for the efficient unloading of diverse and unordered parcels. Our goal is to develop a systematic image processing algorithm that emphasises the boundaries of parcels regardless of their shape, pattern, or layout. The core of the algorithm is the utilisation of RGB-D technology for detecting the primary boundary lines regardless of obstacles such as adhesive labels, tapes, or parcel surface patterns. For cases where detecting the boundary lines is difficult owing to narrow gaps between parcels, we propose using deep learning-based boundary line detection through the You Only Look at Coefficients (YOLACT) model. Using image segmentation techniques, the algorithm efficiently predicts boundary lines, enabling the accurate detection of irregularly sized parcels with complex surface patterns. Furthermore, even for rotated parcels, we can extract their edges through complex mathematical operations using the depth values of the specified position, enabling the detection of the wider surfaces of the rotated parcels. Finally, we validate the accuracy and real-time performance of our proposed method through various case studies, achieving mAP (50) values of 93.8% and 90.8% for randomly sized and rotationally covered boxes with diverse colours and patterns, respectively. [ABSTRACT FROM AUTHOR]

Background: Breast fibroadenoma poses a significant health concern, particularly for young women. Computer-aided diagnosis has emerged as an effective and efficient method for the early and accurate detection of various solid tumors. Automatic segmentation of the breast fibroadenoma is important and potentially reduces unnecessary biopsies, but challenging due to the low image quality and presence of various artifacts in sonography. Methods: Human learning involves modularizing complete information and then integrating it through dense contextual connections in an intuitive and efficient way. Here, a human learning paradigm was introduced to guide the neural network by using two consecutive phases: the feature fragmentation stage and the information aggregation stage. To optimize this paradigm, three fragmentation attention mechanisms and information aggregation mechanisms were adapted according to the characteristics of sonography. The evaluation was conducted using a local dataset comprising 600 breast ultrasound images from 30 patients at Suining Central Hospital in China. Additionally, a public dataset consisting of 246 breast ultrasound images from Dataset_BUSI and DatasetB was used to further validate the robustness of the proposed network. Segmentation performance and inference speed were assessed by Dice similarity coefficient (DSC), Hausdorff distance (HD), and training time and then compared with those of the baseline model (TransUNet) and other state-of-the-art methods. Results: Most models guided by the human learning paradigm demonstrated improved segmentation on the local dataset with the best one (incorporating C3ECA and LogSparse Attention modules) outperforming the baseline model by 0.76% in DSC and 3.14 mm in HD and reducing the training time by 31.25%. Its robustness and efficiency on the public dataset are also confirmed, surpassing TransUNet by 0.42% in DSC and 5.13 mm in HD. Conclusions: Our proposed human learning paradigm has demonstrated the superiority and efficiency of ultrasound breast fibroadenoma segmentation across both public and local datasets. This intuitive and efficient learning paradigm as the core of neural networks holds immense potential in medical image processing. [ABSTRACT FROM AUTHOR]

Pneumonia is a common and challenging disease to treat. Diagnosis of pneumonia is performed by analysing chest X-ray images with a specialist doctor today. This situation can create an excessive workload for doctors and prolong the diagnosis time. Performing early and accurate diagnosis of pneumonia using pre-trained deep learning models, which are a subcategory of the deep learning method, can be extremely beneficial. Using computeraided diagnosis systems increases the accuracy of pneumonia diagnosis and thanks to these systems, doctors have an idea about the disease before diagnosis. In this study chest X-Ray images were classified as healthy or pneumonia using pre-trained deep learning methods. The histogram equalisation image processing method was used to improve image quality and the mask region-based convolutional neural network pre-trained method was used to segment the chest region. Alexnet, ResNet18 and VGG16 pre-trained models were used for image classification as healthy and pneumonia. ResNet18 showed outstanding performance in this study. According to the performance metrics of accuracy (0.983), recall (0.994) and F1-score (0.987), success rates were achieved by using the ResNet18 model. This study has shown that deep learning models can achieve high success rates in pneumonia diagnosis. [ABSTRACT FROM AUTHOR]

Floe size distribution (FSD) has become a parameter of great interest in observations of sea ice because of its importance in affecting climate change, marine ecosystems, and human activities in the polar ocean. A most effective way to monitor FSD in the ice-covered regions is to apply image processing techniques to airborne and satellite remote sensing data, where the segmentation of individual ice floes is a challenge in obtaining FSD from remotely sensed images. In this study, we adopt a deep learning (DL) semantic segmentation network to fast and adaptive implement the task of ice floe instance segmentation. In order to alleviate the costly and time-consuming data annotation problem of model training, classical image processing technique is applied to automatically label ice floes in local-scale marginal ice zone (MIZ). Several state-of-the-art (SoA) semantic segmentation models are then trained on the labelled MIZ dataset and further applied to additional large-scale optical Sentinel-2 images to evaluate their performance in floe instance segmentation and to determine the best model. A post-processing algorithm is also proposed in our work to refine the segmentation. Our approach has been applied to both airborne and high-resolution optical (HRO) satellite images to derive acceptable FSDs at local and global scales. [ABSTRACT FROM AUTHOR]

COVID‐19 has had a profound global impact, necessitating the development of infection detection systems based on machine learning. This paper presents a Multi‐task architecture that addresses the classification and segmentation tasks for COVID‐19 detection. The model comprises an encoder for feature representation, a decoder for segmentation, and a multi‐layer perceptron for classification. Evaluations conducted on two datasets demonstrate the model's performance in both classification and segmentation. To enhance efficiency and diagnosis accuracy, CT‐scan images undergo pre‐processing using image processing algorithms like histogram equalization, median filtering, and mathematical morphology operations. The combination of the median filter pre‐processing and the proposed model yields impressive results in the classification task, achieving high accuracy, sensitivity, and specificity, with values of 0.97, 0.97, and 0.96, respectively, for dataset 1, and 0.96 in mentioned metrics for dataset 2. For segmentation, the proposed model, particularly with the average morphology pre‐processing, exhibits excellent performance with high accuracy, low mean squared error, high peak signal‐to‐noise ratio, high structural similarity index, and a mean dice coefficient of 88.86 ± 0.05 for dataset 1, and 87.97 ± 0.02 for dataset 2. Furthermore, the pre‐trained models consistently demonstrate the superiority of the median filter and proposed model in the classification task on the same datasets. In conclusion, the proposed multi‐task model, incorporating image processing techniques, achieves remarkable results in both classification and segmentation. The utilization of pre‐processing algorithms and the multi‐task framework significantly contribute to superior performance metrics. This study encourages further exploration of combining diverse image processing algorithms to advance infection diagnosis and treatment. [ABSTRACT FROM AUTHOR]

Background: Image segmentation pipelines are commonly used in microscopy to identify cellular compartments like nucleus and cytoplasm, but there are few standards for comparing segmentation accuracy across pipelines. The process of selecting a segmentation assessment pipeline can seem daunting to researchers due to the number and variety of metrics available for evaluating segmentation quality. Results: Here we present automated pipelines to obtain a comprehensive set of 69 metrics to evaluate segmented data and propose a selection methodology for models based on quantitative analysis, dimension reduction or unsupervised classification techniques and informed selection criteria. Conclusion: We show that the metrics used here can often be reduced to a small number of metrics that give a more complete understanding of segmentation accuracy, with different groups of metrics providing sensitivity to different types of segmentation error. These tools are delivered as easy to use python libraries, command line tools, Common Workflow Language Tools, and as Web Image Processing Pipeline interactive plugins to ensure a wide range of users can access and use them. We also present how our evaluation methods can be used to observe the changes in segmentations across modern machine learning/deep learning workflows and use cases. [ABSTRACT FROM AUTHOR]

Cloud and cloud shadow segmentation is one of the most critical challenges in remote sensing image processing. Because of susceptibility to factors such as disturbance from terrain features and noise, as well as a poor capacity to generalize, conventional deep learning networks, when directly used to cloud and cloud shade detection and division, have a tendency to lose fine features and spatial data, leading to coarse segmentation of cloud and cloud shadow borders, false detections, and omissions of targets. To address the aforementioned issues, a multi-scale strip feature attention network (MSFANet) is proposed. This approach uses Resnet18 as the backbone for obtaining semantic data at multiple levels. It incorporates a particular attention module that we name the deep-layer multi-scale pooling attention module (DMPA), aimed at extracting multi-scale contextual semantic data, deep channel feature information, and deep spatial feature information. Furthermore, a skip connection module named the boundary detail feature perception module (BDFP) is introduced to promote information interaction and fusion between adjacent layers of the backbone network. This module performs feature exploration on both the height and width dimensions of the characteristic pattern to enhance the recovery of boundary detail intelligence of the detection targets. Finally, during the decoding phase, a self-attention module named the cross-layer self-attention feature fusion module (CSFF) is employed to direct the aggregation of deeplayer semantic feature and shallow detail feature. This approach facilitates the extraction of feature information to the maximum extent while conducting image restoration. The experimental outcomes unequivocally prove the efficacy of our network in effectively addressing complex cloud-covered scenes, showcasing good performance across the cloud and cloud shadow datasets, the HRC_WHU dataset, and the SPARCS dataset. Our model outperforms existing methods in terms of segmentation accuracy, underscoring its paramount importance in the field of cloud recognition research. [ABSTRACT FROM AUTHOR]

We investigated various methods for image segmentation and image processing for the segmentation of MRI of human medical data, as well as bioinformatics for the segmentation of brain cell details, in this work. The goal is to demonstrate and bring various mathematical analyses for medical and biological image analysis. We proposed new software and methods for improving the segmentation of biological and medical data. This way, we can fi nd new ways to improve the diagnostic process in medical data and improve results in cell and iron diagnostics. We present the GrabCut algorithm as well as new, improved software for this part, a fuzzy approach and fuzzy processing of tissues, and fi nally machine-learning techniques with neural networks. We implemented the new software in the C++ programming language for the Grab cut algorithm. Consequently, we present a fuzzy approach to the diagnosis of image data in Matlab. Finally, a deep learning-based approach is used, with a U-Net-based segmentation architecture proposed to measure the various brain cell parameters. We will be able to proceed with data that we were unable to proceed when using other methods. As a result, we improved biological and medical data segmentation to obtain better boundaries and sharper edges on the objects. There is still space to extend these methods to other medical and biological applications (Tab. 1, Fig. 34, Ref. 46). Text in PDF www.elis.sk. [ABSTRACT FROM AUTHOR]

Punching is a process that is sensitive to a multitude of parameters. The estimation of part and punch quality is often based on expert knowledge and trial-and-error methods, mostly carried out as a separate offline process analysis. In a previous study, we developed an optical inline monitoring system with subsequent image processing which showed promising results in terms of capturing every manufactured part, but was limited by slow image processing. Here, we present a more efficient image processing technique based on neural networks. For our approach, we manually identify the burnish parts in images based on criteria established via an expert survey in order to generate a training dataset. We then employ a combination of region-based and boundary-based losses to optimize the neural network towards a segmentation of the burnish surface which allows for an accurate measurement of the burnish height. The hyperparameter optimization is based on custom evaluation metrics that reflect the requirements of the burnish surface identification problem as well. After comparing different neural network architectures, we focus on optimizing the backbone of the UNet++ structure for our task. The promising results demonstrate that neural networks are indeed capable of an inline segmentation that can be used for measuring the burnish surface of punching parts. [ABSTRACT FROM AUTHOR]

Background: Grain count is crucial to wheat yield composition and estimating yield parameters. However, traditional manual counting methods are time-consuming and labor-intensive. This study developed an advanced deep learning technique for the segmentation counting model of wheat grains. This model has been rigorously tested on three distinct wheat varieties: 'Bainong 307', 'Xinmai 26', and 'Jimai 336', and it has achieved unprecedented predictive counting accuracy. Method: The images of wheat ears were taken with a smartphone at the late stage of wheat grain filling. We used image processing technology to preprocess and normalize the images to 480*480 pixels. A CBAM-HRNet wheat grain segmentation counting deep learning model based on the Convolutional Block Attention Module (CBAM) was constructed by combining deep learning, migration learning, and attention mechanism. Image processing algorithms and wheat grain texture features were used to build a grain counting and predictive counting model for wheat grains. Results: The CBAM-HRNet model using the CBAM was the best for wheat grain segmentation. Its segmentation accuracy of 92.04%, the mean Intersection over Union (mIoU) of 85.21%, the category mean pixel accuracy (mPA) of 91.16%, and the recall rate of 91.16% demonstrate superior robustness compared to other models such as HRNet, PSPNet, DeeplabV3+ , and U-Net. Method I for spike count, which calculates twice the number of grains on one side of the spike to determine the total number of grains, demonstrates a coefficient of determination R2 of 0.85, a mean absolute error (MAE) of 1.53, and a mean relative error (MRE) of 2.91. In contrast, Method II for spike count involves summing the number of grains on both sides to determine the total number of grains, demonstrating a coefficient of determination R2 of 0.92, an MAE) of 1.15, and an MRE) of 2.09%. Conclusions: Image segmentation algorithm of the CBAM-HRNet wheat spike grain is a powerful solution that uses the CBAM to segment wheat spike grains and obtain richer semantic information. This model can effectively address the challenges of small target image segmentation and under-fitting problems in training. Additionally, the spike grain counting model can quickly and accurately predict the grain count of wheat, providing algorithmic support for efficient and intelligent wheat yield estimation. [ABSTRACT FROM AUTHOR]

In the latest research progress, deep neural networks have been revolutionized by frameworks to extract image features more accurately. In this study, we focus on an attention model that can be useful in deep neural networks and propose a simple but strong feature extraction deep network architecture, W-Net. The architecture of our W-Net network has two mutually independent path structures, and it is designed with the following advantages. (1) There are two independent effective paths in our proposed network structure, and the two paths capture more contextual information from different scales in different ways. (2) The two paths acquire different feature images, and in the upsampling approach, we use bilinear interpolation thus reducing the feature map distortion phenomenon and integrating the different images processed. (3) The feature image processing is at a bottleneck, and a hierarchical attention module is constructed at the bottleneck by reclassifying after the channel attention module and the spatial attention module, resulting in more efficient and accurate processing of feature images. During the experiment, we also tested iSAID, a massively high spatial resolution remote sensing image dataset, with further experimental data comparison to demonstrate the generality of our method for remote sensor image segmentation. [ABSTRACT FROM AUTHOR]

Food quality control is an important task in the agricultural domain at the postharvest stage for avoiding food losses. The latest achievements in image processing with deep learning (DL) and computer vision (CV) approaches provide a number of effective tools based on the image colorization and image-to-image translation for plant quality control at the postharvest stage. In this article, we propose the approach based on Generative Adversarial Network (GAN) and Convolutional Neural Network (CNN) techniques to use synthesized and segmented VNIR imaging data for early postharvest decay and fungal zone predictions as well as the quality assessment of stored apples. The Pix2PixHD model achieved higher results in terms of VNIR images translation from RGB (SSIM = 0.972). Mask R-CNN model was selected as a CNN technique for VNIR images segmentation and achieved 58.861 for postharvest decay zones, 40.968 for fungal zones and 94.800 for both the decayed and fungal zones detection and prediction in stored apples in terms of F1-score metric. In order to verify the effectiveness of this approach, a unique paired dataset containing 1305 RGB and VNIR images of apples of four varieties was obtained. It is further utilized for a GAN model selection. Additionally, we acquired 1029 VNIR images of apples for training and testing a CNN model. We conducted validation on an embedded system equipped with a graphical processing unit. Using Pix2PixHD, 100 VNIR images from RGB images were generated at a rate of 17 frames per second (FPS). Subsequently, these images were segmented using Mask R-CNN at a rate of 0.42 FPS. The achieved results are promising for enhancing the food study and control during the postharvest stage. [ABSTRACT FROM AUTHOR]

The advancement of 6G networks is driven by the need for customer-centric communication and network control, particularly in applications such as intelligent transport systems. These applications rely on outdoor communication in extremely high-frequency (EHF) bands, including millimeter wave (mmWave) frequencies exceeding 30 GHz. However, EHF signals face challenges such as higher attenuation, diffraction, and reflective losses caused by obstacles in outdoor environments. To overcome these challenges, 6G networks must focus on system designs that enhance propagation characteristics by predicting and mitigating diffraction, reflection, and scattering losses. Strategies such as proper handovers, antenna orientation, and link adaptation techniques based on losses can optimize the propagation environment. Among the network components, aerial networks, including unmanned aerial vehicles (UAVs) and electric vertical take-off and landing aircraft (eVTOL), are particularly susceptible to diffraction losses due to surrounding buildings in urban and suburban areas. Traditional statistical models for estimating the height of tall objects like buildings or trees are insufficient for accurately calculating diffraction losses due to the dynamic nature of user mobility, resulting in increased latency unsuitable for ultra-low latency applications. To address these challenges, this paper proposes a deep learning framework that utilizes easily accessible Google Street View imagery to estimate building heights and predict diffraction losses across various locations. The framework enables real-time decision-making to improve the propagation environment based on users' locations. The proposed approach achieves high accuracy rates, with an accuracy of 39% for relative error below 2%, 83% for relative error below 4%, and 96% for both relative errors below 7% and 10%. Compared to traditional statistical methods, the proposed deep learning approach offers significant advantages in height prediction accuracy, demonstrating its efficacy in supporting the development of 6G networks. The ability to accurately estimate heights and map diffraction losses before network deployment enables proactive optimization and ensures real-time decision-making, enhancing the overall performance of 6G systems. [ABSTRACT FROM AUTHOR]

Automatic weed identification and detection are crucial for precision weeding operations. In recent years, deep learning (DL) has gained widespread attention for its potential in crop weed identification. This paper provides a review of the current research status and development trends of weed identification in crop fields based on DL. Through an analysis of relevant literature from both within and outside of China, the author summarizes the development history, research progress, and identification and detection methods of DL-based weed identification technology. Emphasis is placed on data sources and DL models applied to different technical tasks. Additionally, the paper discusses the challenges of time-consuming and laborious dataset preparation, poor generality, unbalanced data categories, and low accuracy of field identification in DL for weed identification. Corresponding solutions are proposed to provide a reference for future research directions in weed identification. [ABSTRACT FROM AUTHOR]

In remote-sensing image processing tasks, images with higher resolution always result in better performance on downstream tasks, such as scene classification and object segmentation. However, objects in remote-sensing images often have low resolution and complex textures due to the imaging environment. Therefore, effectively reconstructing high-resolution remote-sensing images remains challenging. To address this concern, we investigate embedding context information and object priors from remote-sensing images into current deep learning super-resolution models. Hence, this paper proposes a novel remote-sensing image super-resolution method called Context-Guided Constrained Network (CGC-Net). In CGC-Net, we first design a simple but effective method to generate inverse distance maps from the remote-sensing image segmentation maps as prior information. Combined with prior information, we propose a Global Context-Constrained Layer (GCCL) to extract high-quality features with global context constraints. Furthermore, we introduce a Guided Local Feature Enhancement Block (GLFE) to enhance the local texture context via a learnable guided filter. Additionally, we design a High-Frequency Consistency Loss (HFC Loss) to ensure gradient consistency between the reconstructed image (HR) and the original high-quality image (HQ). Unlike existing remote-sensing image super-resolution methods, the proposed CGC-Net achieves superior visual results and reports new state-of-the-art (SOTA) performance on three popular remote-sensing image datasets, demonstrating its effectiveness in remote-sensing image super-resolution (RSI-SR) tasks. [ABSTRACT FROM AUTHOR]

Wearing medical masks of various materials and types will lead to different prevention and control the effect of virus spread. Segmentation to masks in image data sets will benefit analyzing the differences in prevention and control effects of different types of masks. Currently, there are many facial mask detection algorithms, but there is a lack of further segmentation. Therefore, this study proposes a facial mask segmentation method based on image processing and deep learning. An improved contrast-limited adaptive histogram equalization preprocessing method is proposed to reduce the poor effect of traditional preprocessing caused by dark part of the image through brightness adaptive adjustment. SSD network is used for mask pre-detection, and CA- Net is used for mask segmentation. With U-Net as the backbone network, CA-Net adds spatial attention module, channel attention module and scale attention module to realize the comprehensive attention guidance of space, channel and scale of feature map at the same time. The segmentation result is processed by binary image closing operation to get the final segmentation results. The Dice evaluation of preliminarily segmentation index can reach to 79.18%±3.44%, and the Dice coefficient is increased to 84.03%±2.81% by adding preprocessing and post-processing operations, indicating that the proposed method could significantly improve the visual segmentation results. [ABSTRACT FROM AUTHOR]

Cracks are fractures or breaks that occur in materials such as concrete, metals, rocks, and other solids. Various methods are used to detect and monitor cracks; among many of them, image-based methodologies allow fast identification of the distress and easy quantification of the percentage of cracks in the scene. Two main categories can be identified: classical and deep learning approaches. In the last decade, the tendency has moved towards the use of the latter. Even though they have proven their outstanding predicting performance, they suffer some drawbacks: a "black-box" nature leaves the user blind and without the possibility of modifying any parameters, a huge amount of labeled data is generally needed, a process that requires expert judgment is always required, and, finally, they tend to be time-consuming. Accordingly, the present study details the methodology for a new algorithm for crack segmentation based on the theory of minimal path selection combined with a region-based approach obtained through the segmentation of texture features extracted using Gabor filters. A pre-processing step is described, enabling the equalization of brightness and shadows, which results in better detection of local minima. These local minimal are constrained by a minimum distance between adjacent points, enabling a better coverage of the cracks. Afterward, a region-based segmentation technique is introduced to determine two areas that are used to determine threshold values used for rejection. This step is critical to generalize the algorithm to images presenting close-up scenes or wide cracks. Finally, a geometrical thresholding step is presented, allowing the exclusion of rounded areas and small isolated cracks. The results showed a very competitive F1-score (0.839), close to state-of-the-art values achieved with deep learning techniques. The main advantage of this approach is the transparency of the workflow, contrary to what happens with deep learning frameworks. In the proposed approach, no prior information is required; however, the statistical parameters may have to be adjusted to the particular case and requirements of the situation. The proposed algorithm results in a useful tool for researchers and practitioners needing to validate their results against some reference or needing labeled data for their models. Moreover, the current study could establish the grounds to standardize the procedure for crack segmentation with a lower human bias and faster results. The direct application of the methodology to images obtained with any low-cost sensor makes the proposed algorithm an operational support tool for authorities needing crack detection systems in order to monitor and evaluate the current state of the infrastructures, such as roads, tunnels, or bridges. [ABSTRACT FROM AUTHOR]

As a severe thermal damage, grinding burns reduce the surface quality and service life of high-performance gears. In this study, to realize accurate localization, classification, and grading of burn defects on gear grinding surfaces, a machine vision–based intelligent detection method was proposed. Different from image processing methods based on hand-designed features, the proposed method can minimize inspection conditions. To recognize individual gear functional surfaces and burn regions from random backgrounds, an image segmentation model was developed by using deep convolutional neural networks. For the scarcity of defect samples in industrial surface testing, a data-augmentation method combining deep learning methods with geometric and color-space transformations was proposed. The experimental results of the gear surface image dataset demonstrated that the proposed burn segmentation model has a precision and recall rate of 84.44% and 82.79%, respectively. This work provides fresh insights for realizing efficient and accurate detection of gear grinding burn defects. [ABSTRACT FROM AUTHOR]

Metallographic images or often called the microstructures contain important information about metals, such as strength, toughness, ductility, corrosion resistance, which are used to choose the proper materials for various engineering applications. Thus by understanding the microstructures, one can determine the behaviour of a component made of a particular metal, and can predict the failure of that component in certain conditions. Image segmentation is a powerful technique for determination of morphological features of the microstructure like volume fraction, inclusion morphology, void, and crystal orientations. These are some key factors for determining the physical properties of metal. Therefore, automatic micro-structure characterization using image processing is useful for industrial applications which currently adopts deep learning-based segmentation models. In this paper, we propose a metallographic image segmentation method using an ensemble of modified U-Nets. Three U-Net models having the same architecture are separately fed with color transformed imaged (RGB, HSV and YUV). We improvise the U-Net with dilated convolutions and attention mechanisms to get finer grained features. Then we apply the sum-rule-based ensemble method on the outcomes of U-Net models to get the final prediction mask. We achieve the mean intersection over union (IoU) score of 0.677 on a publicly available standard dataset, namely MetalDAM. We also show that the proposed method obtains results comparable to state-of-the-art methods with fewer number of model parameters. The source code of the proposed work can be found at https://github.com/mb16biswas/attention-unet. [ABSTRACT FROM AUTHOR]

Image segmentation is an essential step in vision sensing and image processing. It enables the understanding of the object's classes, spatial locations, and extents in the scene, which can be used to support a wide range of construction applications such as progress monitoring, safety management, and productivity analysis. The recent ground-breaking achievements of deep learning-based approaches for semantic segmentation are at the cost of expensive large-scale training datasets annotated at the pixel level. Although building information modeling (BIM) has been leveraged to alleviate labeling costs using automatically generated, color-coded images as semantic labels, the differences between the BIM models and the real-world scenes make it difficult to apply networks trained on BIM-generated labels to real images. Furthermore, it takes nontrivial efforts to reduce such differences. To address these problems, this paper proposes a weakly supervised segmentation approach that uses inexpensive image-level labels. The missing boundary information in image-level labels is compensated by BIM-extracted object information. The proposed method consists of three modules: (1) detect initial object locations from image-level labels; (2) extract object information from BIM as prior knowledge; and (3) incorporate the prior knowledge into the network to enhance the detected object locations. Three extensive experiments are designed to evaluate the effectiveness of the proposed method. Results show that the proposed method substantially improves the detected object areas by using prior knowledge of target objects from BIM and outperforms the state-of-the-art weakly supervised methods. [ABSTRACT FROM AUTHOR]

In the food and beverage industry, the existing recognition of code characters on the surface of complex packaging usually suffers from low accuracy and low speed. This work presents an efficient and accurate inkjet code recognition system based on the combination of the deep learning and traditional image processing methods. The proposed system mainly consists of three sequential modules, i.e., the character’s region extraction by modified YOLOv3-tiny network, the character processing by the traditional image processing methods such as binarization and the modified character projection segmentation, and the character recognition by a Convolutional recurrent neural network (CRNN) model based on a modified version of MobileNetV3. In this system, only a small amount of tag data has been made and an effective character data generator is designed to randomly generate different experimental data for the CRNN model training. To the best of our knowledge, this report for the first time describes that deep learning has been applied to the recognition of codes on complex background for the real-life industrial application. Experimental results have been provided to verify the accuracy and effectiveness of the proposed model, demonstrating a recognition accuracy of 0.986 and a processing speed of 100 ms per bottle in the end-to-end character recognition system. [ABSTRACT FROM AUTHOR]

Deep learning methods have achieved outstanding results in many image processing and computer vision tasks, such as image segmentation. However, they usually do not consider spatial dependencies among pixels/voxels in the image. To obtain better results, some methods have been proposed to apply classic spatial regularization, such as total variation, into deep learning models. However, for some challenging images, especially those with fine structures and low contrast, classical regularizations are not suitable. We derived a new regularization to improve the connectivity of segmentation results and make it applicable to deep learning. Our experimental results show that for both deep learning methods and unsupervised methods, the proposed method can improve performance by increasing connectivity and dealing with low contrast and, therefore, enhance segmentation results. [ABSTRACT FROM AUTHOR]

• Semantic-based segmentation (Semseg) methods are presented in deep learning architecture. • A comparative study is presented for reviewed paper based on performance. • Existing challenges, problems in DL-based semantic segmentation approaches are discussed. • The challenges of Semseg applications are mentioned for other researchers. • Prospect for future work in this area for stable medical image segmentation. Semantic-based segmentation (Semseg) methods play an essential part in medical imaging analysis to improve the diagnostic process. In Semseg technique, every pixel of an image is classified into an instance, where each class is corresponded by an instance. In particular, the semantic segmentation can be used by many medical experts in the domain of radiology, ophthalmologists, dermatologist, and image-guided radiotherapy. The authors present perspectives on the development of an architectural, and operational mechanism of each machine learning-based semantic segmentation approach with merits and demerits. In this regard, researchers have proposed different Semseg methods and examined their performance in a variety of applications such as medical image analysis (e.g., medical image classification and segmentation). A review of recent advances in Semseg techniques are presented in this paper by applying computational image processing and machine learning methods. This article is further presented a comprehensive investigation on how different architectures are helpful for medical image segmentation. Finally, advantages, open challenges, and possible future directions are elaborated in the discussion part, beneficial to the research community to understand the significance of the available medical imaging segmentation technology based on Semseg and thus deliver robust segmentation solutions. Fig. 3: An overview of a latest trend to show the methodological evolution in the development of semantic-based segmentation models for medical images [Display omitted] [ABSTRACT FROM AUTHOR]

Medical image segmentation is a crucial stage in computer vision and image processing to help the later-stage diagnosis process become more accurate. Because medical image segmentation, such as X-ray, can extract tissue, organs, and pathological structures. However, medical image processing, primarily in the segmentation process, has significant challenges regarding feature representation. Because medical images have different characteristics than other images related to contrast, blur, and noise. This study proposes the use of lung segmentation on chest X-ray images based on deep learning with the FCA-Net (Fully Convolutional Attention Network) architecture. In addition, attention modules, namely spatial attention and channel attention, are added to the Res2Net encoder so that it is expected to be able to represent features better. This research was conducted on chest X-ray images from Qatar University contained in the Kaggle repository. A chest x-ray image measuring 256 × 256 pixels and as many as 1500 images were then divided into 10% testing data and 90% training data. The training data will then be processed in K-Fold Cross validation from K = 2 until K = 10. The experiment was conducted with scenarios that used spatial attention, channel attention, and a combination of spatial and channel attention. The best test results in this study were using a variety of spatial attention and channel attention in the division of K-Fold with a value of K = 5 with a DSC (Dice Similarity Coefficient) value in the testing data of 97.24% and IoU (Intersection over Union) in the testing data of 94.66%. This accuracy result is better than the UNet++, DeepLabV3+, and SegNet architectures. [ABSTRACT FROM AUTHOR]

Upcoming technologies enable routine collection of highly multiplexed (20–60 channel), subcellular resolution images of mammalian tissues for research and diagnosis. Extracting single cell data from such images requires accurate image segmentation, a challenging problem commonly tackled with deep learning. In this paper, we report two findings that substantially improve image segmentation of tissues using a range of machine learning architectures. First, we unexpectedly find that the inclusion of intentionally defocused and saturated images in training data substantially improves subsequent image segmentation. Such real augmentation outperforms computational augmentation (Gaussian blurring). In addition, we find that it is practical to image the nuclear envelope in multiple tissues using an antibody cocktail thereby better identifying nuclear outlines and improving segmentation. The two approaches cumulatively and substantially improve segmentation on a wide range of tissue types. We speculate that the use of real augmentations will have applications in image processing outside of microscopy. Presenting UnMICST, strategies for robust single-cell segmentation in challenging human tissues. [ABSTRACT FROM AUTHOR]

The robust delineation of the cochlea and its inner structures combined with the detection of the electrode of a cochlear implant within these structures is essential for envisaging a safer, more individualized, routine image-guided cochlear implant therapy. We present Nautilus—a web-based research platform for automated pre- and post-implantation cochlear analysis. Nautilus delineates cochlear structures from pre-operative clinical CT images by combining deep learning and Bayesian inference approaches. It enables the extraction of electrode locations from a post-operative CT image using convolutional neural networks and geometrical inference. By fusing pre- and post-operative images, Nautilus is able to provide a set of personalized pre- and post-operative metrics that can serve the exploration of clinically relevant questions in cochlear implantation therapy. In addition, Nautilus embeds a self-assessment module providing a confidence rating on the outputs of its pipeline. We present a detailed accuracy and robustness analyses of the tool on a carefully designed dataset. The results of these analyses provide legitimate grounds for envisaging the implementation of image-guided cochlear implant practices into routine clinical workflows. [ABSTRACT FROM AUTHOR]

As we know, image colorization is widely used in computer graphics and has become a research hotspot in the field of image processing. Current image colorization technology has the phenomenon of single coloring effect and unreal color, which is too complicated to be implemented and struggled to gain popularity. In this paper, a new method based on a convolution neural network is proposed to study the reasonable coloring of human images and ensures the realism of the coloring effect and the diversity of coloring at the same time. First, this paper selects about 5000 pictures of people and plants from the Imagenet dataset and makes a small dataset containing only people and backgrounds. Secondly, in order to obtain the image segmentation results, this paper improves the U-net network and carries out three times of down sampling and three times of up-sampling. Finally, we add the expanded convolution, and use the sigmoid activation function to replace the ReLU (The Rectified Linear Unit) activation function and put the BN (Batch Normalization) before the activation function. Experimental results show that our proposed image colorization algorithm based on the deep learning scheme can reduce the training time of the network and achieve higher quality segmentation results. [ABSTRACT FROM AUTHOR]

The detection and counting of lunar impact craters are crucial for the selection of detector landing sites and the estimation of the age of the Moon. However, traditional crater detection methods are based on machine learning and image processing technologies. These are inefficient for situations with different distributions, overlaps, and crater sizes, and most of them mainly focus on the accuracy of detection and ignore the efficiency. In this paper, we propose an efficient lunar crater detection (ELCD) algorithm based on a novel crater edge segmentation network (AFNet) to detect lunar craters from digital elevation model (DEM) data. First, in AFNet, a lightweight attention mechanism module is introduced to enhance the feature extract capabilities of networks, and a new multiscale feature fusion module is designed by fusing different multi-level feature maps to reduce the information loss of the output map. Then, considering the imbalance in the classification and the distributions of the crater data, an efficient crater edge segmentation loss function (CESL) is designed to improve the network optimization performance. Lastly, the crater positions are obtained from the network output map by the crater edge extraction (CEA) algorithm. The experiment was conducted on the PyTorch platform using two lunar crater catalogs to evaluate the ELCD. The experimental results show that ELCD has a superior detection accuracy and inference speed compared with other state-of-the-art crater detection algorithms. As with most crater detection models that use DEM data, some small craters may be considered to be noise that cannot be detected. The proposed algorithm can be used to improve the accuracy and speed of deep space probes in detecting candidate landing sites, and the discovery of new craters can increase the size of the original data set. [ABSTRACT FROM AUTHOR]

Among the congenital coronary heart diseases, atrial septal defect constitutes the 1/3 most common type. In many cases, the affected person stays asymptomatic for the duration of the youth even having big shunts. Methodologies that may be hired for figuring out the defects are: echocardiogram, chest X-ray, electrocardiogram, cardiac catheterization, MRI, CT scan, phonocardiogram. Deep learning may be correctly utilised for the automatic estimation of the illness from the test result. The purpose of this review paper is to offer an perception into ASD, the strategies for figuring out it and the application of deep learning models for distinguishing the illness. The paper opinions diverse algorithms used for identity of defects also points out the restrictions of every algorithm. [ABSTRACT FROM AUTHOR]

Motivation Over the last decades, image processing and analysis have become one of the key technologies in systems biology and medicine. The quantification of anatomical structures and dynamic processes in living systems is essential for understanding the complex underlying mechanisms and allows, i.e. the construction of spatio-temporal models that illuminate the interplay between architecture and function. Recently, deep learning significantly improved the performance of traditional image analysis in cases where imaging techniques provide large amounts of data. However, if only a few images are available or qualified annotations are expensive to produce, the applicability of deep learning is still limited. Results We present a novel approach that combines machine learning-based interactive image segmentation using supervoxels with a clustering method for the automated identification of similarly colored images in large image sets which enables a guided reuse of interactively trained classifiers. Our approach solves the problem of deteriorated segmentation and quantification accuracy when reusing trained classifiers which is due to significant color variability prevalent and often unavoidable in biological and medical images. This increase in efficiency improves the suitability of interactive segmentation for larger image sets, enabling efficient quantification or the rapid generation of training data for deep learning with minimal effort. The presented methods are applicable for almost any image type and represent a useful tool for image analysis tasks in general. Availability and implementation The presented methods are implemented in our image processing software TiQuant which is freely available at tiquant.hoehme.com. Supplementary information Supplementary data are available at Bioinformatics online. [ABSTRACT FROM AUTHOR]

Magnetoencephalography (MEG) is a useful tool for clinically evaluating the localization of interictal spikes. Neurophysiologists visually identify spikes from the MEG waveforms and estimate the equivalent current dipoles (ECD). However, presently, these analyses are manually performed by neurophysiologists and are time-consuming. Another problem is that spike identification from MEG waveforms largely depends on neurophysiologists’ skills and experiences. These problems cause poor cost-effectiveness in clinical MEG examination. To overcome these problems, we fully automated spike identification and ECD estimation using a deep learning approach fully automated AI-based MEG interictal epileptiform discharge identification and ECD estimation (FAMED). We applied a semantic segmentation method, which is an image processing technique, to identify the appropriate times between spike onset and peak and to select appropriate sensors for ECD estimation. FAMED was trained and evaluated using clinical MEG data acquired from 375 patients. FAMED training was performed in two stages: in the first stage, a classification network was learned, and in the second stage, a segmentation network that extended the classification network was learned. The classification network had a mean AUC of 0.9868 (10-fold patient-wise cross-validation); the sensitivity and specificity were 0.7952 and 0.9971, respectively. The median distance between the ECDs estimated by the neurophysiologists and those using FAMED was 0.63 cm. Thus, the performance of FAMED is comparable to that of neurophysiologists, and it can contribute to the efficiency and consistency of MEG ECD analysis. [ABSTRACT FROM AUTHOR]

Deep learning (DL) methods usually need to collect a large amount of labeled data to extract deep features. However, due to the difficulty of obtaining numerous labeled data from synthetic aperture radar (SAR) images, unsupervised feature learning has been focused on SAR image processing. In this article, we propose a 3-D sparse model (3-DSM) to extract deep sparse features from SAR images in an unsupervised way. Concretely, 3-DSM learns the convolution kernels by minimizing the error between the features and the constructed sparse maps, without labeled samples. Thus, the discriminative features can be extracted in an unsupervised way by the learned convolution kernels and are able to capture the main structural information of SAR images. Furthermore, to the best of our knowledge, 3-DSM first specifies the sparsity of convolution kernels, with each convolution kernel exhibiting its independence from the others and the redundancy of convolution kernels being diminishing. It means that each convolution kernel extracts its unique structural features of SAR images. Consequently, in the feature extraction, 3-D sparsities have been specified, including width, height, and depth, with the acquisition of discriminative less-redundant features. The effectiveness of 3-DSM is demonstrated by the feature extraction and segmentation of the simulated and real SAR images. [ABSTRACT FROM AUTHOR]

A method for overlapping cell image segmentation is presented with a focus on multi‐layer image processing in a three‐phase scheme. In the first phase, a convolutional neural network is developed to provide a coarse cell segmentation with multiple output layers to identify cell cytoplasm, locations of cell nuclei, and the background, all as probabilistic image maps for the layer outputs. In the second phase, the probabilistic image maps from the convolutional neural network are used to identify locations of cell nuclei and cell cytoplasm. Then, multi‐layer random walker image segmentation is used with cell nuclei as hard initial seeds and the cytoplasm estimates as soft seeds in a diffusion graph‐based segmentation of the cells. With rough cell segmentation from both the trained convolutional neural network and the multi‐layer random walker graph‐based technique, a third phase combines and refines the cell segmentation using the Hungarian algorithm to optimise the assignment of individual pixel locations for the final cell segmentation. We evaluate the proposed method on cervical cell images generated from the International Symposium on Biomedical Imaging 2014 dataset with results that give a Dice similarity coefficient of 97.2% (compared to 93.2% for competitors) when trained on the generated dataset. [ABSTRACT FROM AUTHOR]

Grain size is one of the most important parameters for metallographic microstructure analysis, which can partly determine the material performance. The measurement of grain size is based on accurate image segmentation methods, which include traditional image processing methods and emerging machine-learning-based methods. Unfortunately, traditional image processing methods can hardly segment grains correctly from metallographic images with low contrast and blurry boundaries. Moreover, the proposed machine-learning-based methods need a large dataset to train the model and can hardly deal with the segmentation challenge of complex images with fuzzy boundaries and complex structure. In this paper, an improved U-Net model is proposed to automatically accomplish image segmentation of complex metallographic images with only a small training set. The experiments on metallographic images show the significant advantage of the method, especially for the metallographic images with low contrast, a fuzzy boundary and complex structure. Compared with other deep learning methods, the improved U-Net scored higher in ACC, MIoU, Precision, and F1 indexes, among which ACC was 0.97, MIoU was 0.752, Precision was 0.98, and F1 was 0.96. The grain size was calculated based on the segmentation according to the American Society for Testing Material (ASTM) standards, producing a satisfactory result. [ABSTRACT FROM AUTHOR]

Image segmentation is a key task in computer vision and image processing with important applications such as scene understanding, medical image analysis, robotic perception, video surveillance, augmented reality, and image compression, among others, and numerous segmentation algorithms are found in the literature. Against this backdrop, the broad success of deep learning (DL) has prompted the development of new image segmentation approaches leveraging DL models. We provide a comprehensive review of this recent literature, covering the spectrum of pioneering efforts in semantic and instance segmentation, including convolutional pixel-labeling networks, encoder-decoder architectures, multiscale and pyramid-based approaches, recurrent networks, visual attention models, and generative models in adversarial settings. We investigate the relationships, strengths, and challenges of these DL-based segmentation models, examine the widely used datasets, compare performances, and discuss promising research directions. [ABSTRACT FROM AUTHOR]

Serving as an essential step for many applications of image processing, superpixel generation has attracted a lot of attentions. Most existing superpixel generation algorithms focus on the boundary adherence and compactness of the superpixels, but ignore the topological consistency between the superpixels, which severely limites their applications in the subsequent tasks, especially in the CNN based image processing tasks. In this paper, we present a fast lattice superpixel generation algorithm, which can generate superpixels with lattice topology like the original pixels. We also propose a local similarity loss function to improve the segmentation accuracy of the generated lattice superpixels. The whole algorithm is parallelly implemented on GPU. We perform extensive experiments on three datasets (i.e., BSDS500, NYUv2 and VOC) to verify the efficacy of our algorithm. The experimental results show that our method achieves competitive results compared to the state-of-the-art methods. [ABSTRACT FROM AUTHOR]

Yield is the most often used metric of crop performance, and it can be defined as the ratio between production, expressed as a function of mass or volume, and the cultivated area. Estimating fruit's volume often relies on manual measurements, and the procedure precision can change from one person to another. Measuring fruits' mass will also destroy the samples; consequently, the variation will be measured with different samples. Monitoring fruit's growth is either based on destructive tests, limited by human labour, or too expensive to be scaled. In this work, we showed that the cluster visible area could be used to describe the growth of mini tomatoes in a greenhouse using image processing in a natural environment with a complex background. The proposed method is based on deep learning algorithms and allows continuous monitoring with no contact with the cluster. The images are collected and delivered from the greenhouse using low-cost equipment with minimal parameterisation. Our results demonstrate that the cluster visible area accumulation is highly correlated (R²=0.97) with growth described by a parameterised Gompertz curve, which is a well-known growth function. This work may also be a starting point for alternative growth monitoring methods based on image segmentation. The proposed U-Net architecture, the discussion about its architecture, and the challenges of the natural environment may be used for other tasks in the agricultural context. [ABSTRACT FROM AUTHOR]

Arial images are very high resolution. The automation for map generation and semantic segmentation of aerial images are challenging problems in semantic segmentation. The semantic segmentation process does not give us precise details of the remote sensing images due to the low resolution of the aerial images. Hence, we propose an algorithm U-Net Architecture to solve this problem. It is classified into two paths. The compression path (also called: the encoder) is the first path and is used to capture the image's context. The encoder is just a convolutional and maximal pooling layer stack. The symmetric expanding path (also called: the decoder) is the second path, which is used to enable exact localization by transposed convolutions. This task is commonly referred to as dense prediction, which is completely connected to each other and also with the former neurons which gives rise to dense layers. Thus it is an end-to-end fully convolutional network (FCN), i.e. it only contains convolutional layers and does not contain any dense layer because of which it can accept images of any size. The performance of the model will be evaluated by improving the image using the proposed method U-NET and obtaining an improved image by measuring the accuracy compared with the value of accuracy with previous methods. [ABSTRACT FROM AUTHOR]

Cloud and cloud shadow segmentation is one of the most important issues in remote sensing image processing. Most of the remote sensing images are very complicated. In this work, a dual-branch model composed of transformer and convolution network is proposed to extract semantic and spatial detail information of the image, respectively, to solve the problems of false detection and missed detection. To improve the model’s feature extraction, a mutual guidance module (MGM) is introduced, so that the transformer branch and the convolution branch can guide each other for feature mining. Finally, in view of the problem of rough segmentation boundary, this work uses different features extracted by the transformer branch and the convolution branch for decoding and repairs the rough segmentation boundary in the decoding part to make the segmentation boundary clearer. Experimental results on the Landsat-8, Sentinel-2 data, the public dataset high-resolution cloud cover validation dataset created by researchers at Wuhan University (HRC_WHU), and the public dataset Spatial Procedures for Automated Removal of Cloud and Shadow (SPARCS) demonstrate the effectiveness of our method and its superiority to the existing state-of-the-art cloud and cloud shadow segmentation approaches. [ABSTRACT FROM AUTHOR]

Automated surface defect detection is a challenging problem that has attracted major attention for decades. Traditional methods were designed using a pipeline of carefully designed operations. The resulting methods were complex systems, which were difficult to tune and adapt to different problems or data. A new approach to solving this problem has emerged recently: deep learning. This trend is motivated by two main factors: the increasing digitization of society, which makes it possible to record large datasets of labeled samples; and the availability of a large pool of computational resources. This work evaluates state-of-the-art deep-learning methods in object detection and semantic segmentation in the field of automated surface inspection in metals. Images acquired in the industry are affected by the conditions of the environment, including noise, dust, and vibrations, which is an additional challenge. Moreover, industrial inspection requires accuracy, but also robustness and speed. The selected methods are applied to different datasets of images that include the most common defects in metals and the performance is compared in terms of accuracy and speed. Results show exceptional accuracy at a fraction of the required processing time. [ABSTRACT FROM AUTHOR]

Wildfire early detection and prevention had become a priority. Detection using Internet of Things (IoT) sensors, however, is expensive in practical situations. The majority of present wildfire detection research focuses on segmentation and detection. The developed machine learning models deploy appropriate image processing techniques to enhance the detection outputs. As a result, the time necessary for data processing is drastically reduced, as the time required rises exponentially with the size of the captured pictures. In a real-time fire emergency, it is critical to notice the fire pixels and warn the firemen as soon as possible to handle the problem more quickly. The present study addresses the challenge mentioned above by implementing an on-site detection system that detects fire pixels in real-time in the given scenario. The proposed approach is accomplished using Deeplabv3+, a deep learning architecture that is an enhanced version of an existing model. However, present work fine-tuned the Deeplabv3 model through various experimental trials that have resulted in improved performance. Two public aerial datasets, the Corsican dataset and FLAME, and one private dataset, Firefront Gestosa, were used for experimental trials in this work with different backbones. To conclude, the selected model trained with ResNet-50 and Dice loss attains a global accuracy of 98.70%, a mean accuracy of 89.54%, a mean IoU 86.38%, a weighted IoU of 97.51%, and a mean BF score of 93.86%. [ABSTRACT FROM AUTHOR]

• An efficient dataset synthesis method for occluded rockfill particle image segmentation. • An occlusion-aware gradation detection method based on amodal instance segmentation. • A comparison between occlusion-aware and ordinary image-based gradation detection. Image-based gradation detection methods of rockfill materials mostly ignore occluded regions of particles, and for the mainstream methods with deep learning, dataset annotation is time-consuming and labour-intensive. This study proposes an efficient virtual-to-real dataset synthesis method for rapid dataset synthesis and occlusion-aware gradation detection. Instead of photographing or scanning real particles with large time cost and labour input, Diffusion-GAN, which is trained with 600 virtual images generated by 3D modeling, efficiently generates 50,000 various individual particle images to synthesize initial stacked particle images and amodal annotations. Post-processing CycleGAN is subsequently proposed to preserve the background with image processing based on CycleGAN, which superiorly converts the style of synthetic images from virtual to real. The proposed dataset synthesis method is 50 times faster than manual labelling. Occlusion-aware gradation detection employs Bilayer Convolutional Network (BCNet) to predict both visible and occluded areas of particles, whose maximum absolute error is 4.72%, less than the error of 7.73% produced by ignoring occluded regions. The AP 50 of BCNet trained with the synthetic dataset is 0.941, extraordinarily close to the result trained with the real dataset. [ABSTRACT FROM AUTHOR]

Deep convolutional neural networks (CNNs) have emerged as a new paradigm for Mammogram diagnosis. Contemporary CNN-based computer-aided-diagnosis systems (CADs) for breast cancer directly extract latent features from input mammogram image and ignore the importance of morphological features. In this paper, we introduce a novel end-to-end deep learning framework for mammogram image processing, which computes mass segmentation and simultaneously predicts diagnosis results. Specifically, our method is constructed in a dual-path architecture that solves the mapping in a dual-problem manner, with an additional consideration of important shape and boundary knowledge. One path, called the Locality Preserving Learner (LPL), is devoted to hierarchically extracting and exploiting intrinsic features of the input. Whereas the other path, called the Conditional Graph Learner (CGL), focuses on generating geometrical features via modeling pixel-wise image to mask correlations. By integrating the two learners, both the cancer semantics and cancer representations are well learned, and the component learning paths in return complement each other, contributing an improvement to the mass segmentation and cancer classification problem at the same time. In addition, by integrating an automatic detection set-up, the DualCoreNet achieves fully automatic breast cancer diagnosis practically. Experimental results show that in benchmark DDSM dataset, DualCoreNet has outperformed other related works in both segmentation and classification tasks, achieving 92.27% DI coefficient and 0.85 AUC score. In another benchmark INbreast dataset, DualCoreNet achieves the best mammography segmentation (93.69% DI coefficient) and competitive classification performance (0.93 AUC score). [ABSTRACT FROM AUTHOR]

Obtaining an accurate segmentation of images obtained by computed microtomography (micro-CT) techniques is a non-trivial process due to the wide range of noise types and artifacts present in these images. Current methodologies are often time-consuming, sensitive to noise and artifacts, and require skilled people to give accurate results. Motivated by the rapid advancement of deep learning-based segmentation techniques in recent years, we have developed a tool that aims to fully automate the segmentation process in one step, without the need for any extra image processing steps such as noise filtering or artifact removal. To get a general model, we train our network using a dataset made of high-quality three-dimensional micro-CT images from different scanners, rock types, and resolutions. In addition, we use a domain-specific augmented training pipeline with various types of noise, synthetic artifacts, and image transformation/distortion. For validation, we use a synthetic dataset to measure accuracy and analyze noise/artifact sensitivity. The results show a robust and accurate segmentation performance for the most common types of noises present in real micro-CT images. We also compared the segmentation of our method and five expert users, using commercial and open software packages on real rock images. We found that most of the current tools fail to reduce the impact of local and global noises and artifacts. We quantified the variation on human-assisted segmentation results in terms of physical properties and observed a large variation. In comparison, the new method is more robust to local noises and artifacts, outperforming the human segmentation and giving consistent results. Finally, we compared the porosity of our model segmented images with experimental porosity measured in the laboratory for ten different untrained samples, finding very encouraging results. [ABSTRACT FROM AUTHOR]

The upcoming Square Kilometre Array (SKA-Low) will map the distribution of neutral hydrogen during reionization and produce a tremendous amount of three-dimensional tomographic data. These image cubes will be subject to instrumental limitations, such as noise and limited resolution. Here, we present SegU-Net , a stable and reliable method for identifying neutral and ionized regions in these images. SegU-Net is a U-Net architecture-based convolutional neural network for image segmentation. It is capable of segmenting our image data into meaningful features (ionized and neutral regions) with greater accuracy compared to previous methods. We can estimate the ionization history from our mock observation of SKA with an observation time of 1000 h with more than 87 per cent accuracy. We also show that SegU-Net can be used to recover the size distributions and Betti numbers, with a relative difference of only a few per cent from the values derived from the original smoothed and then binarized neutral fraction field. These summary statistics characterize the non-Gaussian nature of the reionization process. [ABSTRACT FROM AUTHOR]

Face hallucination or super-resolution is a practical application of general image super-resolution which has been recently studied by many researchers. The challenge of good face hallucination comes from a variety of poses, illuminations, facial expressions, and other degradations. In many proposed methods, researchers resolve it by using a generative neural network to reduce the perceptual loss so we can generate a photo-realistic image. The problem is that researchers usually overlook the fidelity of the super-resolved image which could affect further facial image processing. Meanwhile, many CNN based approaches cascade multiple networks to extract facial prior information to improve super-resolution quality. Because of the end-to-end design, the details are missing for investigation. In this paper, we combine new techniques in convolutional neural network and random forests to a Hierarchical CNN based Random Forests (HCRF) approach for face super-resolution in a coarse-to-fine manner. In the proposed approach, we focus on a general approach that can handle facial images with various conditions without pre-processing. To the best of our knowledge, this is the first paper that combines the advantages of deep learning with random forests for face super-resolution. To achieve superior performance, we propose two novel CNN models for coarse facial image super-resolution and segmentation and then apply new random forests to target on local facial features refinement making use of the segmentation results. Extensive benchmark experiments on subjective and objective evaluation show that HCRF can achieve comparable speed and competitive performance compared with state-of-the-art super-resolution approaches for very low-resolution images. [ABSTRACT FROM AUTHOR]

Welding defect detection based on radiographic images plays a vital role in industrial nondestructive testing. It provides an effective guarantee with respect to welding quality in shipbuilding, chemical industry, and aerospace applications. A variety of related computer-based image processing technologies have been designed for the detection of weld defects. However, this is a challenging task because weld defects can exhibit different shapes, sizes, positions, and contrasts in radiographic images. This article proposes an end-to-end weld defect recognition method that mainly includes three steps. In the first step, we propose an improved algorithm based on deep belief network (DBN), which classifies weld feature curves extracted by applying infinite norm for detecting defective weld base on radiographic images. In the second step, a new cylindrical projection method is proposed to increase the proportion of defect parts in the images and solve the problem of loss of defects with small size. And in the third step, we propose an improved deep learning network that is based on SegNet to identify weld defects. Experimental verification shows that this method can realize end-to-end weld defect recognition and strong robustness. Compared with existing methods, this method exhibits obvious advantages and can effectively assist inspectors in welding defect detection and significantly improve the detection efficiency of industrial nondestructive testing. [ABSTRACT FROM AUTHOR]

The enhancement of light‐defect images such as extremely low‐light, low‐light and dim‐light has always been a research hotspot. Most of the existing methods are excellent in specific illuminations, and there is much room for improvement in processing light‐defect images with different illuminations. Therefore, this study proposes an efficient framework based on deep learning to enhance various light‐defect images. The proposed framework estimates the reflectance component and illumination component. Next, we propose a generator guided by an attention mechanism in the reflectance part to repair the light‐defect in the dark. In addition, we design a colour loss function for the problem of colour distortion in the enhanced images. Finally, the illumination map of the light‐defect images is adjusted adaptively. Extensive experiments are conducted to demonstrate that our method can not only deal with the images with different illuminations but also enhance the images with clearer details and richer colours. At the same time, we prove its superiority by comparing it with state‐of‐the‐art methods under both visual quality comparison and quantitative comparison of various datasets and real‐world images. [ABSTRACT FROM AUTHOR]

Deep learning artificial intelligence (AI) is a booming area in the research field. It allows the development of end-to-end models to predict outcomes based on input data without the need for manual extraction of features. This paper aims for evaluating the automatic crack detection process that is used in identifying the cracks in building structures such as bridges, foundations or other large structures using images. A hybrid approach involving image processing and deep learning algorithms is proposed to detect automatic cracks in structures. As cracks are detected in the images they are segmented using a segmentation process. The proposed deep learning models include a hybrid architecture combining Mask R-CNN with single layer CNN, 3-layer CNN, and8-layer CNN. These models utilizes depth wise convolution with varying dilation rates for efficiently extracting diversified features from the crack images. Further, performance evaluation shows that Mask R-CNN with a single layer CNN achieves an accuracy of 97.5% on a normal dataset and 97.8% on a segmented dataset. The Mask R-CNN with 2-layer convolution resulted in an accuracy of 98.32% on a normal dataset and 98.39% on a segmented dataset. The Mask R-CNN with 8-layers convolution achieves an accuracy of 98.4% on a normal dataset and 98.75% on a segmented dataset. The proposed Mask R-CNN have proved its feasibility in detecting cracks in huge building and structures. [ABSTRACT FROM AUTHOR]