We formalize compressed sensing image reconstruction as an optimization problem, incorporating penalization of the spectral representation of images. Leveraging the original formulation of the Alternating Direction Me...
详细信息
ISBN:
(纸本)9798350349405;9798350349399
We formalize compressed sensing image reconstruction as an optimization problem, incorporating penalization of the spectral representation of images. Leveraging the original formulation of the Alternating Direction Method of Multipliers (ADMM), we introduce the innovative 3F-PnP algorithm. This algorithm integrates three filters: two deep learning neural network-based filters and the spectral BM3D denoiser, implemented through plug-and-play modules. Additionally, we show that the partial solutions of the ADMM optimization correspond precisely to the analysis and synthesis stages of the BM3D filter. Through numerical comparative analysis against ten state-of-the-art methods, we demonstrate the superiority of our algorithm in terms of improved accuracy and faster convergence rates.
In recent years, light field imaging has gained significant attention in the scientific community due to its ability to provide a more immersive representation of the 3D world. However, ensuring the quality of light f...
详细信息
ISBN:
(纸本)9798350350920
In recent years, light field imaging has gained significant attention in the scientific community due to its ability to provide a more immersive representation of the 3D world. However, ensuring the quality of light field images is crucial for their subsequent processing and applications. Deep learning methods, leveraging neural networks, have shown promising performance in image Quality Assessment (IQA). However, the unique characteristics of light field data pose a challenge for existing IQA methods. To address this challenge, we propose a Robust Large-scale Dataset for Assessing Light Field image Quality, named RLSD, specifically designed for evaluating the quality of light field images. The dataset comprises both real and synthetic scenes, covering a wide range of key low attributes and including three representative distortions: compression, noise, and blur. To obtain subjective evaluations, we adopt the single stimulus continuous quality evaluation (SSCQE) method and compute the Mean Opinion Score (MOS). We performed statistical analysis on the dataset and experimental results indicate that our proposed RLSD dataset includes various common scenes and distortion levels, making it suitable for designing and evaluating LF-IQA algorithms. The dataset is publicly available at the following link: "https://***/s/1kJmx4qsy8ywLPba-HwGCEg" (password: XY28).
Object segmentation within neural Radiance Fields (NeRF) plays a pivotal role, holding potential to enrich a myriad of downstream applications like NeRF editing. Most existing methods, heavily reliant on feature simil...
详细信息
ISBN:
(纸本)9798350344868;9798350344851
Object segmentation within neural Radiance Fields (NeRF) plays a pivotal role, holding potential to enrich a myriad of downstream applications like NeRF editing. Most existing methods, heavily reliant on feature similarity of 3D space, make it non-trivial to manipulate. Instead of intricate 3D interfaces, segmenting multiview images rendered from NeRF proves to be more intuitive, enhancing both visibility and interactivity. However, annotating multiple images places a heavy demand on users. To address this, we propose an interactive NeRF segmentation framework that leverages userinput from just one rendered view, automatically generating consistent prompts across all other views. Delving deeper, we propose the Semantic Prompt Generator (SPG) which employs a pre-trained SAM image encoder to extract image features. Cosine similarities between these features are then utilized to form positive-negative location pair prompts. Moreover, we propose the Position Prompt Generator (PPG) to capture geometric relationships across different views, generating consistent bounding box prompts. Our method seamlessly extends SAM's impressive segmentation capabilities into 3D scenarios without additional network training. Extensive evaluations confirm that our algorithm not only surpasses previous works in segmentation quality but also spends less time.
Agriculture, a pivotal sector in the Indian economy, plays a crucial role in national development. A significant challenge within this domain is the detection of crop diseases, with brown spot, leaf blast, and bacteri...
详细信息
Agriculture, a pivotal sector in the Indian economy, plays a crucial role in national development. A significant challenge within this domain is the detection of crop diseases, with brown spot, leaf blast, and bacterial blight being prevalent afflictions in rice crops. This study presents an innovative approach, integrating Gray-level Co-occurrence Matrix (GLCM) and Intensity-Level Based Multi-Fractal Dimension (ILMFD) for feature extraction in disease identification. The efficacy of this integrated technique was evaluated through a comparison with various classifiers. Specifically, the Artificial neural Network (ANN), Support Vector Machine (SVM), and Neuro-Genetic Algorithm (Neuro-GA) were employed to ascertain their precision in disease detection. It was observed that the combination of GLCM and ILMFD with the Neuro-GA classifier achieved an accuracy exceeding 90%. Remarkably, when paired with the SVM classifier, this integrated approach yielded a precise accuracy of 96.7% in detecting brown spot disease in rice. These findings not only validate the effectiveness of the GLCM and ILMFD methods in feature extraction but also highlight the superior performance of the SVM classifier in crop disease detection. This research contributes significantly to the field, offering a robust solution for accurate disease diagnosis in rice crops, thereby aiding in the sustainable management of agricultural practices.
Noise attenuation is crucial in ground-penetrating radar (GPR) data processing. In recent years, deep learning (DL) methods have shown excellent performance in GPR denoising tasks, but they typically focus only on rec...
详细信息
Noise attenuation is crucial in ground-penetrating radar (GPR) data processing. In recent years, deep learning (DL) methods have shown excellent performance in GPR denoising tasks, but they typically focus only on recovering the target signal, which can lead to over-denoising. To enhance the generalizability and the practicality of denoising networks, we propose a strategy to generate random dielectric models from natural image datasets, which can quickly construct model datasets with low redundancy and reasonable distribution. To enhance the fidelity of GPR denoising, we leverage the powerful nonlinear fitting capabilities of convolutional neural networks (CNNs) and introduce a closed-loop denoising network framework for GPR. The framework consists of a denoising sub-network and a noise extraction sub-network, effectively achieving signal-noise separation in noised GPR data. Specifically, the denoising sub-network is used to recover weak reflection signals and initially remove noise, while the noise extraction sub-network is used to restore the true noise, mitigating the problem of over-denoising. A key innovation of our approach is the integration of bandpass filtering, which enhances the robustness of network training and supports effective weak signal recovery. This network framework forms a closed loop through the residual loss between the signal-noise separation results and the noised GPR data, the closed-loop structure is capable of further refining the signal and noise prediction results of the two subnetworks, thereby enhancing the numerical accuracy of the signal-to-noise separation results. Finally, the effectiveness of the GPR closed-loop denoising network is verified from multiple perspectives using both synthetic and field measured data. The results indicate that our proposed method is more competitive in GPR denoising tasks.
In recent years, human and object detection has increased research in different real-time applications. Due to improvement in the field of deep learning, various methods have been designed for human, object detection ...
详细信息
In recent years, human and object detection has increased research in different real-time applications. Due to improvement in the field of deep learning, various methods have been designed for human, object detection and recognition. Hence, Hybrid Deep Convolutional neural Network (HDCNN) is developed for human and object detection from the video frames. The HDCNN is a combination of Convolutional neural Network (CNN) and Emperor Penguin Optimization (EPO). Here, EPO is utilized to increase the system parameters of the CNN structure. Initially, pre-processing is applied to eliminate the noise presented in the image and image quality is enhanced. Here, the Gaussian filter is used for the background subtraction in the images. The three different types of databases are considered to validate the proposed methodology. The proposed HDCNN method is tested in MATLAB and compared with existing methods like Deep neural Network (DNN), CNN and CNN-Firefly Algorithm (FA), respectively. The proposed method is justified with the statistical measurements like accuracy, precision, recall and F-Measure, respectively.
End-systolic elastance of the left ventricle along with the waveforms of pressure and volumetric blood flow in particular sectors of the circulatory system are of importance in diagnosing various problems like dilated...
详细信息
End-systolic elastance of the left ventricle along with the waveforms of pressure and volumetric blood flow in particular sectors of the circulatory system are of importance in diagnosing various problems like dilated cardiomyopathy, left-ventricular hypertrophy, pulmonary hypertension, or ischemic heart disease. The objective of the paper is to broaden the spectrum of available methods to estimate those parameters since currently accessible techniques are often costly or troublesome. Six models have been developed - three of them estimate endsystolic elastance, two perform regression of volumetric blood flow, and one predicts blood pressure. Training datasets have been collected applying the unique hybrid-digital model. The input of the designed models consists of two or three different waveforms representing pressure and volumetric blood flow in particular areas, including heart ventricles, atria, and pulmonary vessels, in addition to the heart rate value. The basis of each model comprises bidirectional Long Short-Term Memory layers along with the dropout and feed-forward layers. Models that estimate end-systolic elastance achieved various accuracy. One of them performed exceptionally well since the absolute error did not exceed 0.169 mmHg cm3 which is a negligibly small value. The root-mean-square error (RMSE) of the model predicting pressure waveform reached 0.165 mmHg in the worst case. Regression of the volumetric blood flow resulted in 6.062 cm3 s worst-case RMSE for the model focusing on the pulmonary valve and 15.979 cm3 s for pulmonary veins model. Computed results, especially those of the models estimating endsystolic elastance, indicate that it is possible to utilize neural networks to estimate those parameters with sufficient accuracy.
The unmanned aerial vehicle equipment is inevitably interfered by environmental noise in the process of image acquisition. Suppress noise to enhance images is a hot topic that scholars strive to study. The stochastic ...
详细信息
With the proliferation of social media data, Multimodal Named Entity Recognition (MNER) has received much attention;using different data modalities is crucial for the development of natural language processing and neu...
详细信息
ISBN:
(纸本)9798350359329;9798350359312
With the proliferation of social media data, Multimodal Named Entity Recognition (MNER) has received much attention;using different data modalities is crucial for the development of natural language processing and neural networks. However, existing methods suffer from two drawbacks: 1) textimage pairs in the data only sometimes correspond to each other, and it is impossible to rely on contextual information due to the short text nature of social media. 2) Despite the introduction of visual information, heterogeneity gaps may occur in previous complex fusion methods, leading to misidentification. This paper proposes a new synthetic image with a selected graphic alignment network(SAMNER) to address these challenges and construct a matching relationship between external images and text. To solve the graphic mismatch problem, we use a stable diffusion model to generate the images and perform entity labeling. Specifically, we generate images and perform entity labeling through the stable diffusion model to generate the image with the highest match to the text, filter the generated images by the internal image set to generate the best image, and then perform multimodal fusion to predict the entity labeling, we design a simple and effective multimodal attentional alignment mechanism to obtain a better visual representation, and we conduct a large number of experiments. The experiments prove that our model produces competitive results on the two publicly available datasets.
Phishing attacks are one of the challenges of the Internet and its users. Phishing attacks are an example of social engineering attacks based on deceiving users. In phishing attacks, fake pages that are very similar t...
详细信息
Phishing attacks are one of the challenges of the Internet and its users. Phishing attacks are an example of social engineering attacks based on deceiving users. In phishing attacks, fake pages that are very similar to legitimate pages are created on the Internet. In phishing attacks, the victim is directed to fake pages, and their valuable information is stolen. Most of the targets of phishing attacks include online payment services, banking, and online sales, so the losses of these attacks are significant. One way to detect phishing attacks is to use machine learning and deep learning methods. The challenge of machine learning and deep learning methods is intelligent feature selection. The lack of feature extraction and intelligent feature selection reduces the accuracy of learning methods in detecting phishing attacks. This paper presents a combined method with deep learning, machine learning, and swarm intelligence algorithms to detect phishing attacks. In the first phase, the dataset is balanced by deep learning based on the GAN. In the second step, the convolutional neural network extracts the primary features from the links and code of web pages. In the third step, the white shark optimizer algorithm selects the essential features. In the last step, the LSTM neural network classifies the samples. The proposed method has been evaluated on ISCX-URL-2016 and Phishtank datasets for feature extraction and selection. The proposed method's accuracy, precision, and sensitivity in the ISCX-URL-2016 dataset are 97.94, 97.82, and 97.76%, respectively. In the Phishtank dataset, the proposed method has accuracy, precision, and sensitivity of 96.78, 95.67, and 95.71%. The proposed method is more accurate than LSTM, CNN, CNN-LSTM, CNN + GA, DNN, VAE-DNN, and AE-DNN methods in detecting phishing.
暂无评论