Search

We propose an image super-resolution method (SR) using a deeply-recursive convolutional network (DRCN). Single-image super-resolution reconstruction technology is to reconstruct fuzzy low-resolution images into clearer high-resolution images. It is a research hotspot in the field of computer vision and image processing. In recent years, the attention mechanism has been successfully applied in image super-resolution reconstruction. However, the existing methods use the channel attention mechanism and the spatial attention mechanism separately, or simply superimpose them, which cannot effectively unify the adjustment effects of both, and the performance is limited. This paper proposes a method that can merge channel attention and spatial attention into pixel attention, which achieves more precise adjustment of feature map information. The pixel attention convolutional neural network method built on this basis can improve the quality of image texture detail reconstruction. We have been tested on five widely used standard datasets, the experimental results show that the method is superior to most current representative reconstruction methods, especially in terms of high-definition picture texture restoration. [ABSTRACT FROM AUTHOR]

Precise and content-aware style transfer in oil painting remains a significant research focus. This involves preserving the semantic content of the original image while accurately emulating the desired painting style. Developing robust algorithms for accurate recognition and classification of various patterns within oil paintings remains a challenge which identify and categorize styles, textures and visual elements to contribute comprehensive understanding of the artwork. The conventional image style transfer algorithm mainly relies on mathematical modeling to characterize image texture facilitating the combination of a content image with a style image to realize style transfer effects. These algorithms neglect the distribution of image edges leading to blurred contours in the resulting images. To address these limitations, this paper proposed a novel decoration pattern style migration algorithm based on SRCNN (Super Resolution Convolutional Neural Network) model using UNet-based architecture. The algorithm leverages the Laplace operator for image sharpening by accentuating edge distributions. Downsampling techniques are used to generate low-resolution images mitigating the protracted duration of image style transfer iterations. The incorporation of Gaussian sampling and a parallelization algorithm contributes to the efficacy of this method in facilitating the transfer of oil painting styles. The proposed model achieves better results using Facades data set, i.e., variance (6.35%), standard deviation (8.67%), uncertainty (11.21%), SSIM score (94.45%), PSNR score (40.24%), MSE score (6.21%) and accuracy (95.00%). For the Monet2photo data set, i.e., variance (7.25%), standard deviation (9.78%), uncertainty (12.78%), SSIM score (91.69%), PSNR score (43.71%), MSE score (8.67%) and accuracy (92.00%). Our proposed method outperforms classical methods using both data sets. [ABSTRACT FROM AUTHOR]

Restored oyster reefs enhance commercial harvests and ecosystem services in coastal environments. Spatial and temporal changes in habitat availability can affect reef persistence and restoration benefits, and understanding how construction and location of a restored habitat influence its persistence over time is key to optimizing restoration efforts. The short-term persistence of six subtidal restored oyster reefs in Pamlico Sound, NC, USA was characterized by sidescan sonar and bathymetric mapping conducted immediately after restoration in August 2016 and again 21 months later in May 2018. A U-net convolutional neural network architecture was trained to classify reef pixels within the sonar imagery using image-based and image-texture features calculated from gray-level co-occurrence matrices. Oyster reef restoration used shell and limestone marl to construct flat substrates, with only a few 10's of centimeters of local relief, spread over areas of ~3000–12,000 m2. All six reefs provided habitat for the settlement and growth of oyster populations, but this role changed as reefs underwent varying degrees of sediment burial between surveys. Reefs constructed in relatively low-energy environments lost ~18–35% of their substrate area, primarily by deposition of sediment along their margins. Reefs having greater sediment supply and greater exposure to predominant winds and currents were most susceptible to burial and became heavily fragmented with ~50–65% of the restored habitat lost. Sediment dynamics appear to exert a controlling influence on the success of these reefs, and oyster restoration sites in high-energy environments may have limited long-term economic and ecosystem benefits. [ABSTRACT FROM AUTHOR]

Image dehazing aims to recover a clean image from a hazy image, which is a challengingly longstanding problem. In this paper, we propose an Ensemble Multi-scale Residual Attention Network (EMRA-Net) to directly generate a clean image, which include two parts: a three-scale residual attention CNN (TRA-CNN), and an ensemble attention CNN (EA-CNN). In TRA-CNN, we employ wavelet transform to obtain the downsampled images, instead of using common spatial downsampling methods, such as nearest downsampling and strided-convolution. With the help of wavelet transform, we can avoid the loss of image texture details. Moreover, in each scale-branch, Res2Net modules are connected in series to make full use of the hierarchical features from the original hazy images, and channel attention mechanism is introduced to focus channel-dimension information. Finally, an EA-CNN is proposed to fuse coarse images generated from TRA-CNN into a refined clean image. Extensive experiments on the benchmark synthetic hazy datasets and the real-world hazy dataset prove that proposed EMRA-Net is superior to previous state-of-the-art methods both in subjective visual perception and objective image quality assessment metrics. [ABSTRACT FROM AUTHOR]

Manual identification of tomato leaf diseases is a time-consuming and laborious process that may lead to inaccurate results without professional assistance. Therefore, an automated, early, and precise leaf disease recognition system is essential for farmers to ensure the quality and quantity of tomato production by providing timely interventions to mitigate disease spread. In this study, we have proposed seven robust Bayesian optimized deep hybrid learning models leveraging the synergy between deep learning and machine learning for the automated classification of ten types of tomato leaves (nine diseased and one healthy). We customized the popular Convolutional Neural Network (CNN) algorithm for automatic feature extraction due to its ability to capture spatial hierarchies of features directly from raw data and classical machine learning techniques [Random Forest (RF), XGBoost, GaussianNB (GNB), Support Vector Machines (SVM), Multinomial Logistic Regression (MLR), K-Nearest Neighbor (KNN)], and stacking for classifications. Additionally, the study incorported a Boruta feature filtering layer to capture the statistically significant features. The standard, research-oriented PlantVillage dataset was used for the performance testing, which facilitates benchmarking against prior research and enables meaningful comparisons of classification performance across different approaches. We utilized a variety of statistical classification metrics to demonstrate the robustness of our models. Using the CNN-Stacking model, this study achieved the highest classification performance among the seven hybrid models. On an unseen dataset, this model achieved average precision, recall, f1-score, mcc, and accuracy values of 98.527%, 98.533%, 98.527%, 98.525%, and 98.268%, respectively. Our study requires only 0.174 s of testing time to correctly identify noisy, blurry, and transformed images. This indicates our approach's time efficiency and generalizability in images captured under challenging lighting conditions and with complex backgrounds. Based on the comparative analysis, our approach is superior and computationally inexpensive compared to the existing studies. This work will aid in developing a smartphone app to offer farmers a real-time disease diagnosis tool and management strategies. [ABSTRACT FROM AUTHOR]

With the development of image feature matching technology, feature matching algorithms based on deep learning have achieved excellent results, but in scenarios with low texture or extreme perspective changes, the matching accuracy is still difficult to guarantee. In this paper, a superresolution reconstruction method based on a Residual-ESPCN (efficient subpixel convolutional neural network) approach is proposed based on LoFTR (local feature matching with transformers). The superresolution method is used to improve the interpolation method used in ASFF (adaptive spatial feature fusion) to increase the image resolution, enhance the detailed information of the image, and make the extracted features richer. Then, ASFF is introduced into the local feature extraction module of LoFTR, which can alleviate the inconsistency problem of information transmission between different scale features of the feature pyramid and lessen the amount of information lost during transmission from low- to high-resolution levels. Moreover, to improve the adaptability of the algorithm to different scenarios, OTSU is introduced to adaptively calculate the threshold of feature matching. The experimental results show that in different indoor or outdoor scenarios, our proposed algorithm for matching features can effectively improve the adaptability of feature matching and can achieve good results in terms of the area under the curve (AUC), accuracy and recall. [ABSTRACT FROM AUTHOR]

The windspeed on the sea surface is an important factor affecting the process of detecting sea surface targets, as it affects the reflection and radiation intensity, posing challenges for precise detection of optical remote sensing targets. This study collects and obtains ultra-high-resolution hyperspectral data using a push-broom hyperspectral sensor, and employs a novel data processing approach to process the raw data and extract significant features related to sea surface windspeed. Based on this foundation, further exploration is conducted into the practical requirements of the spatial dimension and spectral resolution of remote sensing sensors. Dimensionality reduction processing is applied to the hyperspectral data in both spatial and spectral dimensions. It is noteworthy that certain low-resolution spectral extractions will be derived from the central wavelengths of AVIRIS and Landsat satellites, and generate spatial-spectral joint heatmaps (SSHMs) capable of depicting sea surface windspeeds, so as to assess the potential of windspeed estimation utilizing these sensors. Moreover, four kinds of convolutional neural network (CNN) architectures, in conjunction with transfer learning techniques, are utilized to achieve precise estimation of sea surface windspeed. The final estimation results show that CNN models achieve reliable performance until the spectral dimension is reduced to 8 or below, and the spatial dimension is reduced to 25; The lightweight framework effectively employs coarse-resolution SSHMs to extract windspeed and achieve accurate recognition results. This paper introduces a feasibility study for windspeed estimation utilizing the optical sensors that meet the spatial and spectral resolution requirements. [ABSTRACT FROM AUTHOR]

The integration of convolutional neural network (CNN) and transformer enhances the network's capacity for concurrent modeling of texture details and global structures. However, training challenges with transformer limit their effectiveness to low-resolution images, leading to increased artifacts in slightly larger images. In this paper, we propose a single-stage network utilizing large kernel attention (LKA) to address high-resolution damaged images. LKA enables the capture of both global and local details, akin to transformer and CNN networks, resulting in high-quality inpainting. Our method excels in: (1) reducing parameters, improving inference speed, and enabling direct training on 1024 × 1024 resolution images; (2) utilizing LKA for enhanced extraction of global high-frequency and local details; (3) demonstrating excellent generalization on irregular mask models and common datasets such as Places2, Celeba-HQ, FFHQ, and the random irregular mask dataset Pconv from NVIDIA. [ABSTRACT FROM AUTHOR]

As malicious code attacks continue to evolve, attackers leverage techniques like packing and code obfuscation to generate numerous variants, challenging traditional detection methods. Addressing the limitations of current deep learning-based malicious code classification approaches in feature extraction and accuracy, this paper introduces an innovative RGB visualization detection method based on a hybrid multi-head attention mechanism. Initially, a feature representation method utilizing RGB images is introduced. This approach focuses on semantic relationships between a malware's binary information, assembly details, and API data, generating images with richer textural information. This technique effectively uncovers the deep dependencies between the original and variant versions of malicious code, providing stronger support for subsequent classification tasks. Furthermore, to tackle the issues of malware encryption and obfuscation, a deep neural network framework is adopted, incorporating a modular design philosophy and integrating a multi-head attention mechanism. This design not only enhances the expressiveness of critical features but also helps the model better focus on key aspects of the malicious code, thereby improving classification accuracy. Through comparative experiments and in-depth analysis, the effectiveness and superiority of the proposed RGB visualization method and MSA-ResNet model in the field of malicious code variant classification are validated. The accuracy rates achieved on the Kaggle and DataCon datasets are 99.49% and 97.70%, respectively, representing significant improvements over other methods. This approach demonstrates strong generalization capabilities and resistance to obfuscation, offering a new and effective tool for malicious code detection. [ABSTRACT FROM AUTHOR]

Image segmentation is a critical and challenging endeavor in the field of medicine. A magnetic resonance imaging (MRI) scan is a helpful method for locating any abnormal brain tissue these days. It is a difficult undertaking for radiologists to diagnose and classify the tumor from several pictures. This work develops an intelligent method for accurately identifying brain tumors. This research investigates the identification of brain tumor types from MRI data using convolutional neural networks and optimization strategies. Two novel approaches are presented: the first is a novel segmentation technique based on firefly optimization (FFO) that assesses segmentation quality based on many parameters, and the other is a combination of two types of convolutional neural networks to categorize tumor traits and identify the kind of tumor. These upgrades are intended to raise the general efficacy of the MRI scan technique and increase identification accuracy. Using MRI scans from BBRATS2018, the testing is carried out, and the suggested approach has shown improved performance with an average accuracy of 98.6%. [ABSTRACT FROM AUTHOR]

Recently, convolutional neural networks (CNNs) have facilitated the rapid development of image super-resolution. Most deep networks are challenging to apply to the real world due to their high cost of memory storage and computational complexity. This paper addresses this issue by proposing a lightweight subpixel sampling network (SSN). Specifically, we use a traditional encoder-decoder structure and replace the deconvolution and pooling layers by subpixel up-sampling and down-sampling without parameters. Subpixel sampling retains more image information than other sampling methods. In addition, we propose parsimonious spatial and channel attention blocks through which multi-scale features are fused and more image textures can be recovered. Through extensive experiments, we validate the effectiveness of subpixel sampling, spatial attention block, and channel attention block. In terms of quantitative metrics and visual quality, our models achieve performance comparable to state-of-the-art methods. [ABSTRACT FROM AUTHOR]

Texture filtering attempts to retain salient structures and remove insignificant textures. In this paper, we propose a highly effective iterative unsupervised deep bilateral texture filtering neural network for texture smoothing. The bilateral texture loss function is introduced to train the model without the ground truth smoothing images for guidance. The proposed model inherits well-known advantages of the bilateral texture filter to capture the texture information effectively. The model is trained solely using the training data, then the predicted outputs are generated iteratively through multiple forward passes. Extensive experiments demonstrate that our proposed iterative unsupervised deep bilateral texture filtering neural network outperforms existing methods in effectively removing textures while preserving the main structures of the image. The results showcase the superior performance of our approach and its ability to achieve high-quality texture smoothing without sacrificing important image features. [ABSTRACT FROM AUTHOR]

Deep learning (DL)-based categorization and detection methods for breast cancer diagnosis through medical images are utilized by computer-aided diagnosis (CAD) techniques. In this study, two DL-based ensemble models were proposed to improve the diagnostic efficiency of the system. The proposed models were evaluated on two mammography datasets: DDSM and CBIS-DDSM. To enhance the performance of breast lesion classification from mammographic scans, three pretrained convolutional neural network (CNN) models, namely VGG16, InceptionV3, and VGG19, were used as base classifiers, and two ensemble models were trained. Ensemble Model 1, using a linear meta-learner in the form of logistic regression for classification, and Ensemble Model 2, using a neural net as the meta-learner for classification. The DDSM dataset achieved accuracy, sensitivity, and specificity of 98.02%, 97.17%, and 98.87%, respectively, for Ensemble Model 1, and 98.10%, 97.01%, and 99.12%, respectively, for Ensemble Model 2. Furthermore, the performance of the proposed models was compared with existing state-of-the-art systems, and the results showed an increase in breast cancer classification performance with the proposed models. Hence, the proposed models have the potential to aid medical professionals in accurately classifying breast lesions. [ABSTRACT FROM AUTHOR]

Cracks are the primary indicator informing the structural health of concrete structures. Frequent inspection is essential for maintenance, and automatic crack inspection offers a significant advantage, given its efficiency and accuracy. Previously, image-based crack detection systems have been utilized for individual images, yet these systems are not effective for large inspection areas. This paper thereby proposes an image-based crack detection system using a Deep Convolution Neural Network (DCNN) to identify cracks in mosaic images composed from UAV photos of concrete footings. UAV images are transformed into 3D footing models, from which the composite images are created. The CNN model is trained on 224 × 224 pixel patches, and training samples are augmented by various image transformation techniques. The proposed method is applied to localize cracks on composite images through the sliding window technique. The proposed VGG16 CNN detection system, with 95% detection accuracy, indicates superior performance to feature-based detection systems. [ABSTRACT FROM AUTHOR]

In recent years, automatic image classification methods have significantly progressed, notably black box algorithms such as machine learning and deep learning. Unfortunately, such efforts only focused on improving performance, rather than attempting to explain and interpret how classification models actually operate. This article compares three state-of-the-art algorithms incorporating random forests, gradient boosting and convolutional neural networks for geomorphological mapping. It also attempts to explain how the most effective classifier makes decisions by evaluating which of the geomorphometric variables are most important for automatic mapping and how they affect the classification results using one of the explainable artificial intelligence techniques, namely accumulated local effects (ALE). This method allows us to understand the relationship between predictors and the model's outcome. For these purposes, eight sheets of the digital geomorphological map of Poland on the scale of 1:100,000 were used as the reference material. The classification results were validated using the holdout method and cross-validation for individual sheets representing different morphogenetic zones. The terrain elevation entropy, absolute elevation, aggregated median elevation and standard deviation of elevation had the greatest impact on the classification results among the 15 geomorphometric variables considered. The ALE analysis was conducted for the XGBoost classifier, which achieved the highest accuracy of 92.8%, ahead of Random Forests at 84% and LightGBM at 73.7% and U-Net at 59.8%. We conclude that automatic classification can support geomorphological mapping only if the geomorphological characteristics in the predicted area are similar to those in the training dataset. The ALE plots allow us to analyze the relationship between geomorphometric variables and landform membership, which helps clarify their role in the classification process. [ABSTRACT FROM AUTHOR]

Display technologies have evolved over the years. It is critical to develop practical HDR capturing, processing, and display solutions to bring 3D technologies to the next level. Depth estimation of multi-exposure stereo image sequences is an essential task in the development of cost-effective 3D HDR video content. In this paper, we develop a deep architecture for multi-exposure stereo depth estimation. The proposed architecture has two novel components. First, the stereo matching technique used in traditional stereo depth estimation is revamped. For the stereo depth estimation component of our architecture, a mono-to-stereo transfer learning approach is deployed. The proposed formulation circumvents the cost volume construction requirement, which is replaced by a dual-encoder single-decoder CNN with different weights for feature fusion. EfficientNet-based blocks are used to learn the disparity. Secondly, we combine disparity maps obtained from the stereo images at different exposure levels using a robust disparity feature fusion approach. The disparity maps obtained at different exposures are merged using weight maps calculated for different quality measures. The final predicted disparity map obtained is more robust and retains best features that preserve the depth discontinuities. The proposed CNN offers flexibility to train using standard dynamic range stereo data or with multi-exposure low dynamic range stereo sequences. In terms of performance, the proposed model surpasses state-of-the-art monocular and stereo depth estimation methods, both quantitatively and qualitatively, on challenging Scene flow and differently exposed Middlebury stereo datasets. The architecture performs exceedingly well on complex natural scenes, demonstrating its usefulness for diverse 3D HDR applications. [ABSTRACT FROM AUTHOR]

Any kidney dimension and volume variation can be a remarkable indicator of kidney disorders. Precise kidney segmentation in standard planes plays an undeniable role in predicting kidney size and volume. On the other hand, ultrasound is the modality of choice in diagnostic procedures. This paper proposes a convolutional neural network with nested layers, namely Fast-Unet++, promoting the Fast and accurate Unet model. First, the model was trained and evaluated for segmenting sagittal and axial images of the kidney. Then, the predicted masks were used to estimate the kidney image biomarkers, including its volume and dimensions (length, width, thickness, and parenchymal thickness). Finally, the proposed model was tested on a publicly available dataset with various shapes and compared with the related networks. Moreover, the network was evaluated using a set of patients who had undergone ultrasound and computed tomography. The dice metric, Jaccard coefficient, and mean absolute distance were used to evaluate the segmentation step. 0.97, 0.94, and 3.23 mm for the sagittal frame, and 0.95, 0.9, and 3.87 mm for the axial frame were achieved. The kidney dimensions and volume were evaluated using accuracy, the area under the curve, sensitivity, specificity, precision, and F1. [ABSTRACT FROM AUTHOR]

Deep convolutional neural networks can effectively improve the performance of single-image super-resolution reconstruction. Deep networks tend to achieve better performance than others. However, the deep CNNs will lead to a dramatic increase in the size of parameters, limiting its application on embedding and resource-constrained devices, such as smart phone. To address the common problems of blurred image edges, inflexible convolution kernel size selection and slow convergence during training procedure due to redundant network structure in image super-resolution algorithms, this paper proposes a lightweight single-image super-resolution network that fuses multi-level features. The components are mainly two-level nested residual blocks. To better extract features and reduce the number of parameters, each residual block adopts an asymmetric structure. Firstly, it expands twice and then compresses the number of channels twice. Secondly, in the residual block, the feature information of different channels is weighted and fused by adding an autocorrelation weight unit. The quality of the reconstructed image of the proposed method is superior to the existing image super-resolution reconstruction methods in both subjective perception and objective evaluation indicators, and the reconstruction performance is better when the factor is large. [ABSTRACT FROM AUTHOR]

Designing reasonable architectures of convolutional neural network (CNN) for specific image segmentation remains a challenging task, as the determination of the structure and hyperparameters of CNN depends heavily on expertise and requires a great deal of time. Evolutionary algorithm (EA) has been successfully applied to the automatic design of CNNs; however, the inherent stochastic search of EA tends to cause "experience loss" and requires very large computational resources. To deal with this problem, a maximal sparse convex surrogate model with updated empirical information is proposed in this paper to guide the evolutionary process of CNN design. This sparse convex function is transformed from a non-convex function to a maximized sparse convex function, which can better utilize the prior empirical knowledge to assist the evolutionary search. In addition, a balance strategy between computational resources and accuracy is proposed in the selection of reasonable network architectures. The proposed fully automatic design method of CNN is applied to the segmentation of steel microstructure images, and experimental results demonstrate that the proposed method is competitive with the existing state-of-the-art methods. [ABSTRACT FROM AUTHOR]

Rapid advancement in the sophistication of malware has posed a serious impact on the device connected over the Internet. Malware writing is driven by economic benefits; thus, an alarming increase in malware variants is witnessed. Recently, a large volume of malware attacks are reported on Internet of Things (IoT) networks; as these devices are exposed to insecure segments, further IoT devices reported have hardcoded credentials. To combat malware attacks on mobile devices and desktops, deep learning-based detection approaches have been attempted to detect malware variants. The existing solutions require large computational overhead and also have limited accuracy. In this paper, we visualize malware as Markov images to preserve semantic information of consecutive pixels. We further extract textures from Markov images using Gabor filter (named as Gabor images), and subsequently develop models using VGG-3 and Densely Connected Network (DenseNet). To encourage real-time malware detection and classification, we fine-tune Densely Connected Network. These models are trained and evaluated on two datasets namely Malimg and BIG2015. In our experimental evaluations, we found that DenseNet identifies Malimg and BIG2015 samples with accuracies of 99.94% and 98.98%, respectively. Additionally, the performance of our proposed method in classifying malware files to their respective families is superior compared to the state-of-the approach calibrated using prediction time, F1-score, and accuracy. [ABSTRACT FROM AUTHOR]

Purpose: 2-[18F]FDG PET/CT plays an important role in the management of pulmonary nodules. Convolutional neural networks (CNNs) automatically learn features from images and have the potential to improve the discrimination between malignant and benign pulmonary nodules. The purpose of this study was to develop and validate a CNN model for classification of pulmonary nodules from 2-[18F]FDG PET images. Methods: One hundred thirteen participants were retrospectively selected. One nodule per participant. The 2-[18F]FDG PET images were preprocessed and annotated with the reference standard. The deep learning experiment entailed random data splitting in five sets. A test set was held out for evaluation of the final model. Four-fold cross-validation was performed from the remaining sets for training and evaluating a set of candidate models and for selecting the final model. Models of three types of 3D CNNs architectures were trained from random weight initialization (Stacked 3D CNN, VGG-like and Inception-v2-like models) both in original and augmented datasets. Transfer learning, from ImageNet with ResNet-50, was also used. Results: The final model (Stacked 3D CNN model) obtained an area under the ROC curve of 0.8385 (95% CI: 0.6455–1.0000) in the test set. The model had a sensibility of 80.00%, a specificity of 69.23% and an accuracy of 73.91%, in the test set, for an optimised decision threshold that assigns a higher cost to false negatives. Conclusion: A 3D CNN model was effective at distinguishing benign from malignant pulmonary nodules in 2-[18F]FDG PET images. [ABSTRACT FROM AUTHOR]

In ophthalmology, early fundus screening is an economical and effective way to prevent blindness from eye diseases. Because clinical evidence does not exist, manual detection is time-consuming and may cause the situation to be delayed clinically. With the development of deep learning, a wide variety of eye diseases have shown promising results; however, most of these studies focus on only one disease. Therefore, focusing on multi-disease classification based on fundus images is an effective approach. Consequently, this paper presents a method based on the multilevel glowworm swarm optimization convolutional neural network (MGSCNN) for the classification of multiple diseases. It is proposed that the proposed system has two stages, namely preprocessing and classification. In the beginning, the images are normalized, smoothed, and resized to prepare them for preprocessing. After pre-processing, the images are fed to the MGSCNN classifier to classify an image as normal or abnormal (covering 39 different types of diseases). In the CNN classifier, with the help of Glowworm Swarm Optimizer (GSO), we optimally detect the structure and hyperparameters of CNN simultaneously. This approach achieves an excellent accuracy of 95.09% based on various metrics. [ABSTRACT FROM AUTHOR]

The mango crop production and quality are affected by several factors. Plant disease is one of the prime factors that impact crop yield. The disease impacts all parts of plants such as leaves, roots, and stems. Farmers waste most of their energy, time, and effort dealing with it manually and lead to heavy loss in the yield of the crops. Mango production is affected by several types of diseases. Prior recognition of disease would ease and reduce the diagnostic process that enhances the production of quality crops. A huge investigation has been carried out in the field of identifying and classifying leaf disease. Hence, an appropriate artificial intelligence (AI) based solution is needed to support farmers. The objective of the work is to provide an effective and efficient AI-based solution to detect and classify leaf disease earlier. Earlier disease detection in crops is the most prominent way to prevent loss of money and time. The plant leaf image is mainly used as a source to detect disease in the plant. This paper employs an ensemble stacked deep learning model to resolve the problem of automatic identification of mango-leaf diseases. In the proposed approach, initially, the images are segmented for the region of interest and input to a stack of various deep neural networks. The outcome of the deep neural network is aggregated with a machine learning model to identify leaf disease. This model is used to identify various mango leaf diseases such as Powdery mildew, Anthracnose, etc. In the experiment, the deep learning models are stacked and aggregated with machine learning to identify mango leaf diseases. The proposed model is compared with state-of-the-art models and outperforms with 98.57% accuracy. [ABSTRACT FROM AUTHOR]

Stereo-matching is a hot topic in the field of visual image research, to address the low image-matching accuracy of traditional algorithms. In this paper, an optimization for image stereo-matching algorithm using deep reinforcement learning (DRL) is proposed in rule constraints and parallax estimation. First, the image edge pixel constraint rules are established, and the image sample blocks are adjusted. Second, the image parallax estimation is performed by computing geometric constraint and pixel parallax probability in rule constraints, and a DRL structure is designed. Finally, the DRL analysis is performed iteratively by the convolutional neural networks feature extraction, agent training decision, and reward value accumulation, and stereo-matching images are output. Experiments show that the image structural similarity of the proposed algorithm is high, and the correct matching rate is more than 95%. The images have good interpretability, and the stereo-matching effect is good. [ABSTRACT FROM AUTHOR]

In recent years, deep learning has been widely employed in the field of image compression, the most significant of which is the lossy image compression method on the basis of convolutional neural networks. And we study the application of convolutional neural networks to remote sensing image compression. Consequently, we implement an enhanced residual attention module (ERAM) on the primary and hyper coders. ERAM can apply a spatial attention mechanism to generate importance masks for potential features of the original image. And the importance mask can adaptively adjust the bit distribution and allocate more bits to substantial target regions and fewer bits to unimportant background regions. Additionally, ERAM has the capacity to lessen the channel redundancy of potential features. Furthermore, an accurate probability estimate of a potential feature can affect to a great degree the effectiveness of entropy coding and hence image compression. We propose to utilise the discrete mixed Laplace entropy model to parameterize the probability distribution of latent features, which can improve the compression efficiency of latent features in the entropy encoding process. In the field of remote sensing image compression, the experiments demonstrate that the algorithm described in this paper has good subjective effects as well as good objective effects. [ABSTRACT FROM AUTHOR]

Image capture systems fail to capture high-resolution images when used at great depth underwater, and the equipment is also expensive. With the use of image processing algorithms, it is possible to reconstruct and improve image quality without any costly and reliable image acquisition programs. Developing and rebuilding an underwater image is a daunting task and has gained momentum in recent years. The aim is to improve underwater images by removing graininess, fine-tuning, and sharpening the images using deep learning models.In this work, the authors train four Convolution Neural Network (CNN) based models (two 3-layered and two 5-layered) over GAN-augmented datasets viz. EUVP (Enhancing Underwater Visual Perception)and UIEB (Underwater Image Enhancement Benchmark). Comparisons of these four models are done with the state-of-the-art methods with the aim of identifying the best model. The results showed that the 5-layered model with SGD optimizer performs the best. [ABSTRACT FROM AUTHOR]

The combination of feature extraction and classification methods is an often used approach for wafer map failure pattern recognition. Recently, the convolutional neural network (CNN) method is used to raw wafer map data without feature extraction. CNN can improve the accuracy, but the drawback is the expensive computation cost. In our study, we have extracted local property analysis based features and used them with the traditional classification methods, ensemble methods, and CNN for wafer map failure pattern recognition. The decision tree showed better performance than the other methods when evaluating single traditional classification methods. Therefore, we used the decision tree as the base classifier of the proposed ensemble learning. We built a constituent model on a single type of feature set first and then made an ensemble of models to produce the final decision. We found that it is better than directly building a model on total features. Also, we have tested and compared CNN on extracted feature sets and raw wafer map image data. The results showed that raw image based CNN outperforms extracted features under the same number of epochs. However, the training cost of the raw image is much expensive. Furthermore, the performance of extracted features becomes closer to the raw image when increasing the number of epochs with a much lower training cost. [ABSTRACT FROM AUTHOR]

With the high demand and sub-nanometer design for integrated circuits, surface defect complexity and frequency for semiconductor wafers have increased; subsequently emphasizing the need for highly accurate fault detection and root-cause analysis systems as manual defect diagnosis is more time-intensive, and expensive. As such, machine learning and deep learning methods have been integrated to automated inspection systems for wafer map defect recognition and classification to enhance performance, overall yield, and cost-efficiency. Concurrent with algorithm and hardware advances, in particular the onset of neural networks like the convolutional neural network, the literature for wafer map defect detection exploded with new developments to address the limitations of data preprocessing, feature representation and extraction, and model learning strategies. This article aims to provide a comprehensive review on the advancement of machine learning and deep learning applications for wafer map defect recognition and classification. The defect recognition and classification methods are introduced and analyzed for discussion on their respective advantages, limitations, and scalability. The future challenges and trends of wafer map detection research are also presented. [ABSTRACT FROM AUTHOR]

General methods of image processing, analysis and enhancement and their biomedical applications developed by the scientific school of the Laboratory of Mathematical Methods of Image Processing of the Faculty of Computational Mathematics and Cybernetics of Lomonosov Moscow State University are reviewed. The suggested general methods and algorithms of image quality enhancement for image resampling and super-resolution, ringing artifact reduction, image sharpening, image denoising, and image registration are described. Image analysis methods based on Hermite projection method, Gauss-Laguerre functions and the use of phase information are presented. We describe and review the developed methods for medical imaging tasks solution, including problems in histology, color Doppler flow mapping, ultrasound liver fibrosis diagnostics, CT brain perfusion, Alzheimer's disease diagnostics, dermatology, chest X-ray image analysis, live cell image registration, tracking, segmentation and synthesis. The paper illustrates the basic research idea of the effectiveness of the hybrid approach when we jointly use classical mathematical methods and deep learning approaches. [ABSTRACT FROM AUTHOR]

Image processing is currently developing as a unique and the inventive field in computer research and applications in the modern area. Most image processing algorithms produce a large quantity of data as an outcome, which is termed as Big-data. These algorithms process and store bulky information either as structured or unstructured data. The use of big data analytics to mine the data produced by image processing technology has huge potential in areas like education, governments, medical establishments, production units, finance and banking, and retail business centers. This paper well defined the innovations made in Big Data analytics and image processing. In this study, a novel data classification approach especially for image analytics is proposed. To improve image quality, pre-processing is applied to huge data that has been gathered. Then, most relevant features like spatial information, texture GLCM, and color and shape features are extracted from the pre-processed image. Since the dimensions of the features are huge in size, an adaptive map-reduce framework with Improved Shannon Entropy has been introduced to lessen the dimensionality of the extracted features. Then, in the big data classification phase, an optimized deep learning classifier deep convolutional neural network (DCNN) is introduced to classify the images accurately. The weight function of the DCNN is fine-tuned using the newly proposed dragonfly updated mothsearch (DAUMS) Algorithm to enhance the classification accuracy and to solve the optimization problems of the research work. The moth search algorithm and dragonfly algorithm are both concepts in this hybrid algorithm DAUMS. [ABSTRACT FROM AUTHOR]

Background: CT image reconstruction has evolved from filtered back projection to hybrid- and model-based iterative reconstruction. Deep learning-based image reconstruction is a relatively new technique that uses deep convolutional neural networks to improve image quality. Objective: To evaluate and compare 1.25 mm thin-section abdominal CT images reconstructed with deep learning image reconstruction (DLIR) with 5 mm thick images reconstructed with adaptive statistical iterative reconstruction (ASIR-V). Methods: This retrospective study included 52 patients (31 F; 56.9±16.9 years) who underwent abdominal CT scans between August-October 2019. Image reconstruction was performed to generate 5 mm images at 40% ASIR-V and 1.25 mm DLIR images at three strengths (low [DLIR-L], medium [DLIR-M], and high [DLIR-H]). Qualitative assessment was performed to determine image noise, contrast, visibility of small structures, sharpness, and artifact based on a 5-point-scale. Image preference determination was based on a 3-point-scale. Quantitative assessment included measurement of attenuation, image noise, and contrast-to-noise ratios (CNR). Results: Thin-section images reconstructed with DLIR-M and DLIR-H yielded better image quality scores than 5 mm ASIR-V reconstructed images. Mean qualitative scores of DLIR-H for noise (1.77 ± 0.71), contrast (1.6 ± 0.68), small structure visibility (1.42 ± 0.66), sharpness (1.34 ± 0.55), and image preference (1.11 ± 0.34) were the best (p<0.05). DLIR-M yielded intermediate scores. All DLIR reconstructions showed superior ratings for artifacts compared to ASIR-V (p<0.05), whereas each DLIR group performed comparably (p>0.05, 0.405-0.763). In the quantitative assessment, there were no significant differences in attenuation values between all reconstructions (p>0.05). However, DLIR-H demonstrated the lowest noise (9.17 ± 3.11) and the highest CNR (CNRliver = 26.88 ± 6.54 and CNRportal vein = 7.92 ± 3.85) (all p<0.001). Conclusion: DLIR allows generation of thin-section (1.25 mm) abdominal CT images, which provide improved image quality with higher inter-reader agreement compared to 5 mm thick images reconstructed with ASIR-V. Clinical Impact: Improved image quality of thin-section CT images reconstructed with DLIR has several benefits in clinical practice, such as improved diagnostic performance without radiation dose penalties. [ABSTRACT FROM AUTHOR]

The diagnostic phase of the treatment process is essential for patient guidance and follow-up. The accuracy and effectiveness of this phase can determine the life or death of a patient. For the same symptoms, different doctors may come up with different diagnoses whose treatments may, instead of curing a patient, be fatal. Machine learning (ML) brings new solutions to healthcare professionals to save time and optimize the appropriate diagnosis. ML is a data analysis method that automates the creation of analytical models and promotes predictive data. There are several ML models and algorithms that rely on features extracted from, for example, a patient's medical images to indicate whether a tumor is benign or malignant. The models differ in the way they operate and the method used to extract the discriminative features of the tumor. In this article, we review different ML models for tumor classification and COVID-19 infection to evaluate the different works. The computer-aided diagnosis (CAD) systems, which we referred to as classical, are based on accurate feature identification, usually performed manually or with other ML techniques that are not involved in classification. The deep learning-based CAD systems automatically perform the identification and extraction of discriminative features. The results show that the two types of DAC have quite close performances but the use of one or the other type depends on the datasets. Indeed, manual feature extraction is necessary when the size of the dataset is small; otherwise, deep learning is used. [ABSTRACT FROM AUTHOR]

Lung cancer creates pulmonary nodules in the patient's lung, which may be diagnosed early on using computer-aided diagnostics. A novel automated pulmonary nodule diagnosis technique using three-dimensional deep convolutional neural networks and multi-layered filter has been presented in this paper. For the suggested automated diagnosis of lung nodule, volumetric computed tomographic images are employed. The proposed approach generates three-dimensional feature layers, which retain the temporal links between adjacent slices of computed tomographic images. The use of several activation functions at different levels of the proposed network results in increased feature extraction and efficient classification. The suggested approach divides lung volumetric computed tomography pictures into malignant and benign categories. The suggested technique's performance is evaluated using three commonly used datasets in the domain: LUNA 16, LIDC-IDRI, and TCIA. The proposed method outperforms the state-of-the-art in terms of accuracy, sensitivity, specificity, F-1 score, false-positive rate, false-negative rate, and error rate. [ABSTRACT FROM AUTHOR]

Convolutional neural networks can solve single-image super-resolution (SR) problems owing to their powerful learning capabilities. At present, most lightweight networks are realized by stacking lightweight modules to deepen the network, which leads to the loss of flow characteristics during transmission. This paper proposes a lightweight SR network (EGARNet) based on extended group-enhanced convolution. Residual learning is introduced outside the network of cascaded lightweight modules, and adjacent residual convolution is proposed. Consequently, the shallow network features are fused by residual blocks and deep high-frequency features, which is conducive to the reconstruction of image edge structure. Our model not only reconstructs a clear edge structure but also balances the relationship between the model complexity and reconstructed image quality. The model was confirmed to be effective and lightweight using Set5, Set14, Urban100, and BSD100 test sets. [ABSTRACT FROM AUTHOR]

Objectives : Machine learning (ML) for medical imaging is emerging for several organs and image modalities. Our objectives were to provide clinicians with an overview of this field by answering the following questions: (1) How is ML applied in liver computed tomography (CT) imaging? (2) How well do ML systems perform in liver CT imaging? (3) What are the clinical applications of ML in liver CT imaging? Methods: A systematic review was carried out according to the guidelines from the PRISMA-P statement. The search string focused on studies containing content relating to artificial intelligence, liver, and computed tomography. Results: One hundred ninety-one studies were included in the study. ML was applied to CT liver imaging by image analysis without clinicians' intervention in majority of studies while in newer studies the fusion of ML method with clinical intervention have been identified. Several were documented to perform very accurately on reliable but small data. Most models identified were deep learning-based, mainly using convolutional neural networks. Potentially many clinical applications of ML to CT liver imaging have been identified through our review including liver and its lesion segmentation and classification, segmentation of vascular structure inside the liver, fibrosis and cirrhosis staging, metastasis prediction, and evaluation of chemotherapy. Conclusion: Several studies attempted to provide transparent result of the model. To make the model convenient for a clinical application, prospective clinical validation studies are in urgent call. Computer scientists and engineers should seek to cooperate with health professionals to ensure this. Key Points: • ML shows great potential for CT liver image tasks such as pixel-wise segmentation and classification of liver and liver lesions, fibrosis staging, metastasis prediction, and retrieval of relevant liver lesions from similar cases of other patients. • Despite presenting the result is not standardized, many studies have attempted to provide transparent results to interpret the machine learning method performance in the literature. • Prospective studies are in urgent call for clinical validation of ML method, preferably carried out by cooperation between clinicians and computer scientists. [ABSTRACT FROM AUTHOR]

Alzheimer's disease (AD) as an incurable disease that affects the mental functions of the patients. The early diagnosis of AD requires automatic Computer-Aided Diagnosis, which needs advanced technical practices like Deep Learning algorithms. This paper proposes a hybrid optimization tuned Deep convolutional neural network (Deep CNN) based automatic AD detection strategy. The significance of the proposed strategy lies in the optimal segmentation of Magnetic resonance imaging (MRI) and the classification of AD using the Deep CNN, which is trained using the proposed teaching learning-based brainstorm (TLBS) optimization algorithm that inherits the characteristic features of learning search agents and the associative search agents to obtain the global optimal solution for tuning the weights of the classifier. The performance evaluation using the accuracy, sensitivity, specificity, and F-Measure are obtained 97.03%, 97.18%, 97.03%, and 97.39% respectively, which shows the effectiveness of the proposed method in detecting the AD of patients. [ABSTRACT FROM AUTHOR]

Breast tumor segmentation and recognition from mammograms play a key role in healthcare and treatment services. As different tumors in mammography have dissimilar densities, shapes, sizes, and edges, the interpretation of mammograms can be time-consuming and prone to interpretation variability even for a highly trained radiologist or expert. In this study, several encoding approaches are first proposed to achieve an effective breast cancer recognition system as well as create new images from the input image. Each encoded image represents some unique features that are crucial for detecting the target texture properly. Subsequently, pectoral muscle is eliminated using obtained features from these encoded images. Moreover, 11 distinct images are then applied to a shallow and efficient cascade Convolutional Neural Network (CNN) for classifying each pixel inside the image. This network accepts 11 local patches as the input from 11 obtained encoded images. Next, all extracted features are concatenated to a vertical vector to apply to the fully connected layers. Using different representations of the input mammogram images, the suggested model is able to analyze the input texture more effectively without using a deep CNN model. Finally, comprehensive experiments are then conducted on two public datasets which then demonstrate that the proposed framework successfully is able to gain competitive outcomes compared to a number of baselines. [ABSTRACT FROM AUTHOR]

Super-resolution has achieved remarkable results in recent years, which is attributed to the rapid development of convolutional neural networks (CNN). However, most CNN-based algorithms have complex network structures and are not very adaptive in reconstructing detailed information. In this paper, we propose an adaptive global cross-scale prior attention network (GCPAN) to address this problem. GCPAN consists of nonlocal similarity prior module(NLS), adaptive cross-scale prior fusion module (CSF), and adaptive wide activation residual attention module (WARA). Specifically, we propose the nonlocal similarity prior module (NLS) to extract contextual associations between feature layers to alleviate the pressure of network complexity. NLS ensures the accuracy of the obtained global information utilizing SENet attention. Secondly, the adaptive cross-scale prior fusion (CSF) module is proposed to capture similarity relations of different scales adaptively and takes advantage of the internal prior information of the image to enhance texture details. Finally, we design an adaptive wide activation residual attention (WARA) module to learn more effective detail information. Extensive ablation and comparative experiments show that GCPAN obtains pleasing objective values and is visually closer to real images compared with other state-of-the-art methods. [ABSTRACT FROM AUTHOR]

Targeted malware attacks are usually more purposeful and harmful than untargeted attacks, so it is important to perform the malware family classification. In classification tasks, convolutional neural networks (CNN) have shown superior performance. However, clean samples with intentional small-scale perturbations (i.e. adversarial examples) may lead to incorrect decisions made by CNN-based classifiers. The most successful approach to improve the robustness of classifiers is adversarially trained on practical adversarial examples. Despite many attempts, previous works have not dealt with generating executable adversarial examples in a pure black-box manner to emulate adversarial threats. The aim of this work is to generate realistic adversarial malware examples and improve the robustness of classifiers against these attacks. We first explain the decision of malware classification by the saliency detection technique and argue that there are two similarities in saliency distribution of CNN classifiers. To explore the under-researched Malware to Malware threats that deceive PE malware classifiers into targeted misclassification, we propose the Saliency Append (SA) attack method based on the two saliency similarities, which produces adversarial examples via only one query, achieving higher attack success rate than other append-based attacks. We use these examples to improve the robustness of classifiers by adversarially trained on the generated adversarial examples. Compared to classifiers trained on other attacks, our approach produces classifiers that are significantly more robust against the proposed SA attack as well as others. [ABSTRACT FROM AUTHOR]

Objective: To perform a systematic literature review and meta-analysis of the two most common commercially available deep-learning algorithms for CT. Methods: We used PubMed, Scopus, Embase, and Web of Science to conduct systematic searches for studies assessing the most common commercially available deep-learning CT reconstruction algorithms: True Fidelity (TF) and Advanced intelligent Clear-IQ Engine (AiCE) in the abdomen of human participants since only these two algorithms currently have adequate published data for robust systematic analysis. Results: Forty-four articles fulfilled inclusion criteria. 32 studies evaluated TF and 12 studies assessed AiCE. DLR algorithms produced images with significantly less noise (22–57.3% less than IR) but preserved a desirable noise texture with increased contrast-to-noise ratios and improved lesion detectability on conventional CT. These improvements with DLR were similarly noted in dual-energy CT which was only assessed for a single vendor. Reported radiation reduction potential was 35.1–78.5%. Nine studies assessed observer performance with the two dedicated liver lesion studies being performed on the same vendor reconstruction (TF). These two studies indicate preserved low contrast liver lesion detection (> 5 mm) at CTDIvol 6.8 mGy (BMI 23.5 kg/m2) to 12.2 mGy (BMI 29 kg/m2). If smaller lesion detection and improved lesion characterization is needed, a CTDIvol of 13.6–34.9 mGy is needed in a normal weight to obese population. Mild signal loss and blurring have been reported at high DLR reconstruction strengths. Conclusion: Deep learning reconstructions significantly improve image quality in CT of the abdomen. Assessment of other dose levels and clinical indications is needed. Careful choice of radiation dose levels is necessary, particularly for small liver lesion assessment. [ABSTRACT FROM AUTHOR]

This paper presented a self-transfer learning network (STLN) for multicolor fabric defect detection. Deep neural networks were adopted to detect defects in objects with complex backgrounds such as multicolored fabrics. It is noteworthy that the more disturbances there are on the object surface, the more difficult it is to optimize the network and the more training samples will be required. At the same time, the distinct difference in different types of multi-colored fabrics makes model difficult to apply data information. To this end, the STLN in this paper, consisting of a dataset expansion module, a dataset filtering module, a feature extraction module, a defect detection module, and a category discrimination module, used only limited raw data without the help of external data, and expanded the training set by mining the features of the raw data to better optimize the network. It is experimentally demonstrated that the STLN can achieve higher accuracy compared to deep neural networks for detecting defects of multicolor fabrics with insufficient target data. [ABSTRACT FROM AUTHOR]

In recent years, single-image super-resolution (SISR) has acquired tremendous progress with the development of deep learning. However, the majority of SISR methods based on deep learning focus on building more complex networks, which inevitably lead to the problems of computational and memory costs. Thus, these methods may fail to be applied in real-world scenarios. To solve this problem, this paper proposes a lightweight convolution network combined with transformer for SISR named as MMSR. Specifically, an efficient convolutional neural network (CNN) based on multi-scale feature fusion is designed for local feature extraction, which is called MFF-CNN. In addition, we propose a simple and efficient multiple attention block (MAB) to further utilize the context information in features. MAB incorporates channel attention and transformer to help network obtain similar features at a long-term dependence, making full use of global information to further refine texture details. Finally, this paper provides comprehensive results for different settings of the entire network. Experimental results on common used datasets demonstrate that the proposed method can achieve better performances at the 2 × , 3 × and 4 × scales than other state-of-the-art lightweight methods. [ABSTRACT FROM AUTHOR]

Writer identification based on handwriting recognition is considered one of the most common research areas in pattern recognition and biometrics. It has attracted much attention in recent decades due to the urgent need to develop biometric systems for many security applications. In this paper, Deep Writer Identification Network (DeepWINet), an effective deep Convolutional Neural Network (CNN) for writer identification, is proposed. The proposed model is evaluated in two different ways. In the first scenario, DeepWINet's CNN activation features, computed from the connected components of the writing, are passed to a customized nearest neighbor classifier for writer identification. In the second scenario, DeepWINet is evaluated as an end-to-end CNN network where the predicted results are averaged using an efficient strategy, Score Averaging Component-Decision Combiner. The proposed approach achieves competitive or the highest State-Of-The-Art performance on eight challenging handwritten databases with different languages. [ABSTRACT FROM AUTHOR]

Psoriasis is a condition of the skin, it causes skin cells to swell, resulting in itchy red patches. Psoriasis now impacts 40% of the population. In current days, technology has emerged as the primary method for identifying psoriatic skin condition by segmenting affected skin images. Furthermore, several researchers have reported promising machine learning approaches for segmenting psoriasis skin images. Even now, the model's accuracy and time consumption need to be enhanced more consequently, in this paper, we offer an Adaptive Golden Eagle Optimization (IGEO) on the basis of Convolutional Neural Network (CNN) for autonomous segmentation of psoriasis skin images. Following pre-processing, the input images are segmented by the IGEO-CNN approach, with the weight and bias parameters of CNN tuned using this IGEO. Modifying the random sequence on the basis of tent map increases the study effectiveness of the GEO approach. Finally, artifacts are eliminated from the segmented output images using the threshold module. We achieve 97% accuracy via simulation. [ABSTRACT FROM AUTHOR]

In the world, several sign languages (SL) are used, and BSL (Baby Sign Language) is the process of communication between the parents and baby using gestures. Communication by gestures is a non-verbal process that utilizes motion to pass on realities, expressions and feelings to people. SL is the communication mode in which the information is conveyed via movement of body parts like cheeks, eyebrows and head. Even though many research works based on SL are available, research in BSL remains a challenge. Hence, this paper presents an optimization-based automated recognition of the deep BSL system, which determines the gesture signalled by the kids. Initially, the image frames are extracted from the videos and data augmentation processes are performed. After pre-processing, the features are extracted from the frames using the Enhanced Convolution Neural Network (ECNN). The optimal characteristics are then selected by a new Life Choice Based Optimizer (LCBO). Finally, the classification is carried out by the Deep Long Short-Term Memory (DLSTM) scheme. The implementation is performed on the Python platform, and the performances are evaluated using several performance metrics such as accuracy, precision, kappa, f1-score and recall. The performance of the proposed approach (ECNN-DLSTM) is compared with several deep and machine learning approaches and obtains an accuracy of 99% and a kappa of 96%. [ABSTRACT FROM AUTHOR]

Traditional recognition methods are simple to extract features and need to be manually extracted with high complexity and unstable accuracy. The expression recognition method of deep learning still has the problems of poor network representation ability and low recognition rate. In order to fully represent the complex texture and edge features of expression images, a deep learning method of expression recognition based on Gabor representation combined with PCNN was proposed. Firstly, different Gabor representations are obtained through a set of Gabor filter banks with different proportions and directions, and the corresponding convolutional neural network model is trained to generate G-CNNs. Then, the Pulse Coupled Neural Network (PCNN) was introduced to fuse the different outputs of G-CNNs. Experiments in CK+ and JAFFE databases show that the average recognition rates of this method obtained 94.87% and 96.91%, time is 2097 ms and 6142 ms. Compared with other methods, the experimental results verify the effectiveness and superiority of the proposed method. The proposed method improves the recognition rate on the premise of ensuring the recognition efficiency. [ABSTRACT FROM AUTHOR]

The adoption of convolutional neural network (CNN) models in high-stake domains is hindered by their inability to meet society's demand for transparency in decision-making. So far, a growing number of methodologies have emerged for developing CNN models that are interpretable by design. However, such models are not capable of providing interpretations in accordance with human perception, while maintaining competent performance. In this paper, we tackle these challenges with a novel, general framework for instantiating inherently interpretable CNN models, named E pluribus unum interpretable CNN (EPU-CNN). An EPU-CNN model consists of CNN sub-networks, each of which receives a different representation of an input image expressing a perceptual feature, such as color or texture. The output of an EPU-CNN model consists of the classification prediction and its interpretation, in terms of relative contributions of perceptual features in different regions of the input image. EPU-CNN models have been extensively evaluated on various publicly available datasets, as well as a contributed benchmark dataset. Medical datasets are used to demonstrate the applicability of EPU-CNN for risk-sensitive decisions in medicine. The experimental results indicate that EPU-CNN models can achieve a comparable or better classification performance than other CNN architectures while providing humanly perceivable interpretations. [ABSTRACT FROM AUTHOR]

Recent years, thanks to the prosperous development of deep convolutional neural network, image denoising task has achieved unprecedented achievements. However, previous researches have difficulties in keeping the balance between noise removing and textual details preserving, even bringing the negative effect, such as local blurring. To overcome these weaknesses, in this paper, we propose an innovative multi-attention complementary fusion network (MACFNet) to restore delicate texture details while eliminating noise to the greatest extent. To be specific, our proposed MACFNet mainly composes of several multi-attention complementary fusion modules (MACFMs). Firstly, we use feature extraction block (FEB) to extract basic features.Then, we use spatial attention (SA), channel attention (CA) and patch attention (PA) three different kinds of attention mechanisms to extract spatial-dimensional, channel-dimensional and patch-dimensional attention aware features, respectively. In addition, we attempt to integrate three attention mechanisms in an effective way. Instead of directly concatenate, we design a subtle complementary fusion block (CFB), which is skilled in incorporating three sub-branches characteristics adaptively. Extensive experiments are carried out on gray-scale image denoising, color image denoising and real noisy image denoising. The quantitative results (PSNR) and visual effects all prove that our proposed network achieves great performance over some state-of-the-art methods. [ABSTRACT FROM AUTHOR]

This paper designs a set of wire rope broken wire damage detection systems, which realizes the complete process of wire rope damage identification, location, cutting, and classification. The system uses the designed two-dimensional magnetic flux leakage (MFL) detection device and line array camera to collect the MFL signal and visible light signal of the steel wire rope, respectively, and reduce the noise of the MFL signal through the filtering algorithm combined with modified ensemble empirical mode decomposition (MEEMD) and wavelets. The magnetic signals in two dimensions are fused by a guided image filtering method, which realizes the enhancement of MFL images. Then, a wavelet transform-based convolutional autoencoder (WTCAE) is proposed for visible light defect detection and localization. Finally, a convolutional neural network is used to identify broken filaments. The experimental results show that the system has a high detection sensitivity. [ABSTRACT FROM AUTHOR]

Medical image categorization is essential for a variety of medical assessments and education functions. The purpose of medical image classification is to organize medical images into useful categories for the purpose of illness diagnosis or study, making it one of the most pressing issues in the field of image recognition. On the other hand, traditional methods have plateaued in their effectiveness. Additionally, a substantial amount of time and energy is required when employing them to extract and choose categorization features. Alzheimer's disease is one of the most frequent sources of dementia in elderly patients. Metabolic diseases affect a huge population worldwide, and henceforth, there is a vast scope of applying machine learning to find treatments to these diseases. As a relatively new machine learning technique, deep neural networks have shown great promise for a variety of categorization problems. In this research, a model for diagnosing and tracking the development of Alzheimer's disease that is both accurate and easy to understand has been developed. By following the developed procedure, medical professionals may make deliberations with solid justification. Early diagnosis utilizing these machine learning algorithms has the potential to minimize mortality rates associated with Alzheimer's disease. This research work has developed a convolutional neural network using a shallow convolution layer to identify Alzheimer's disease in medical image patches. The total accuracy of proposed classifications is around 98%, which is greater than the accuracy of the most popular existing approaches. [ABSTRACT FROM AUTHOR]