检索结果-内蒙古大学图书馆

2024 International conference on image processing

作者： Guan, JingShuo Qi, Na Zhu, Qing Chen, Liang Beijing Univ Technol Beijing Peoples R China Fujian Normal Univ Fuzhou Peoples R China

ISBN: (纸本)9798350349405;9798350349399

Low-light image enhancement is a computer vision task that aims to improve the visual perceptual quality of images captured in poorly illuminated scenes. At present, deep learning-based low-light enhancement methods can obtain high-quality enhanced images. However, it does not consider the statistical characteristics of different regions, such as edge, structure, and texture. The uncertainty of image regions is not well characterized and utilized. To address this problem, we propose a novel UnCertainty-driven Cycle-Consistent Generative Adversarial Network (UTrCGAN) to improve the performance of low-light enhancement. UTrCGAN first decomposes the unpaired low/normal-light images into reflectance and illumination components based on the Retinex theory. Then a generative adversarial network guided by uncertainty constraint is proposed to enhance the illumination component, in which the quality of the enhanced image is further improved by the guidance of variance estimation. Experimental results on the widely-used LOL dataset show that UTrCGAN outperforms the state-of-the-art methods in terms of visual quality and quantitative metrics.

关键词： Low-light enhancement unpaired image generative adversarial network uncertainty-driven

来源：评论

学校读者我要写书评

暂无评论

A Review of image Enhancement methods Based on stochastic Resonance of Neuronal Networks 5

A Review of Image Enhancement Methods Based on Stochastic Re...

引用

5th IEEE International conference on Pattern Recognition and Machine Learning, PRML 2024

作者： Sun, Ximin Niu, Pingjuan Li, Yong Li, Xiaoming Zhao, Bingzhen Zhang, Bin Liu, Dan Sun, Bo State Gride Ecommerce Technology CO. LTD Tiangong University Laboratory of Metaverse in Electric Power Industry Tian'jin China Tiangong University Laboratory of Metaverse in Electric Power Industry Tian'jin China State Gride Ecommerce Technology CO. LTD Laboratory of Metaverse in Electric Power Industry Tian'jin China

ISBN: (纸本)9798350355925

stochastic resonance has always been a research hotspot in the field of image processing. The ability of the nervous system to detect signals is closely related to nonlinear and collective behavior in neural mediators. Neuronal noise is the most significant factor influencing this ability, and it is a natural endogenous fluctuation in brain activity. Experimental and theoretical studies have shown that noise is beneficial, not harmful, for the normal functioning of the nervous system. In this regard, it is generally agreed that noise of appropriate intensity can participate in the rhythmic activity of the brain, and that noise-induced oscillations enhance the performance of weak signal processing, especially when the frequency of the signal is approximately noise-induced rhythmic oscillations. This behavior in the biological nervous system can be explained by the concept of 'stochastic resonance'. Correspondingly, the stochastic resonance mechanism of neurons is used to denoise the image, which has a good effect. In this paper, we first introduce an image processing method using random resonance of neurons. Then, the commonly used evaluation indicators in the field of image processing are sorted out. Finally, the development trend of image processing using random resonance of neurons is prospected. © 2024 IEEE.

关键词： Circuit resonance

来源：评论

学校读者我要写书评

暂无评论

Texture classification using RGGD statistical model of CNN feature maps encoding 32

Texture classification using RGGD statistical model of CNN f...

引用

32nd European Signal processing conference (EUSIPCO)

作者： Abbad, Zakariae El Maliani, Ahmed Drissi El Hassouni, Mohammed Abbassi, Mohamed Tahar Kadaoui Bombrun, Lionel Berthoumieu, Yannick Mohammed Univ Rabat ENSIAS Rabat Morocco Mohammed Univ Rabat FS Rabat Morocco Mohammed Univ Rabat FLSH Rabat Morocco Univ Sidi Mohamed Ben Abdellah LMSA FSDM Fes Morocco Univ Bordeaux CNRS Bordeaux INP IMSUMR 5218 Bordeaux France Bordeaux Sci Agro F-33175 Gradignan France

ISBN: (纸本)9789464593617;9798331519773

The symmetric positive definite (SPD) matrices play an important role in diverse domains, including computer vision and signal processing, due to their unique ability to capture the intrinsic structure of nonlinear data using Riemannian geometry. Despite their significance, a notable gap exists in the absence of statistical distributions capable of effectively characterizing the statistical properties within the SPD matrices space. This paper addresses this gap by introducing a novel Riemannian Generalized Gaussian distribution (RGGD). The primary aspect of this work includes presenting the precise expression for the probability density function (PDF) of the RGGD model, along with the parameter estimation method based on the maximum likelihood for this distribution. The second aspect of this work entails harnessing the second-order statistical information captured in the feature maps originating from the initial layers of deep convolutional neural networks (DCNNs) using the RGGD stochastic model within an image classification framework. The third aspect of this work includes also the comparison of the three-parameter RGGD model with its two-parameter predecessors, namely the Riemannian Gaussian distribution (RGD) and the Riemannian Laplacian distribution (RLD). Besides the mathematical foundations, the model's efficiency is validated through experiments conducted on the three well-known datasets, showcasing its effectiveness in capturing the underlying statistics of SPD matrices.

关键词： Symmetric positive definite matrices Generalized Gaussian distribution texture Riemannian geometry Rao's distance Riemannian metric

来源：评论

学校读者我要写书评

暂无评论

A statistical Approach to Monte Carlo Denoising 24

A Statistical Approach to Monte Carlo Denoising

引用

2024 SIGGRAPH Asia conference

作者： Sakai, Hiroyuki Freude, Christian Auzinger, Thomas Hahn, David Wimmer, Michael Tech Univ Wien Vienna Austria IST Austria Klosterneuburg Austria

ISBN: (纸本)9798400711312

The stochastic nature of modern Monte Carlo (MC) rendering methods inevitably produces noise in rendered images for a practical number of samples per pixel. The problem of denoising these images has been widely studied, with most recent methods relying on data-driven, pretrained neural networks. In contrast, in this paper we propose a statistical approach to the denoising problem, treating each pixel as a random variable and reasoning about its distribution. Considering a pixel of the noisy rendered image, we formulate fast pair-wise statistical tests-based on online estimators-to decide which of the nearby pixels to exclude from the denoising filter. We show that for symmetric pixel weights and normally distributed samples, the classical Welch t-test is optimal in terms of mean squared error. We then show how to extend this result to handle non-normal distributions, using more recent confidence-interval formulations in combination with the BoxCox transformation. Our results show that our statistical denoising approach matches the performance of state-of-the-art neural image denoising without having to resort to any computation-intensive pretraining. Furthermore, our approach easily generalizes to other quantities besides pixel intensity, which we demonstrate by showing additional applications to Russian roulette path termination and multiple importance sampling.

关键词： Monte Carlo rendering path tracing denoising image filtering statistics

来源：评论

学校读者我要写书评

暂无评论

Drone-towed electromagnetic and magnetic systems for subsurface characterization and archaeological prospecting

引用

NEAR SURFACE GEOPHYSICS 2024年第6期22卷 617-635页

作者： Vilhelmsen, Tobias B. Grayver, Alexander V. Dossing, Arne Tech Univ Denmark DTU Space Geomagnetisme & Geospace Centrifugevej 356 DK-2800 Kongens Lyngby Denmark Univ Cologne Inst Geophys & Meteorol Cologne Germany

Drone-based geophysical surveying is an emerging measuring platform. High time-cost efficiency and flexibility to survey over inaccessible areas make drones attractive or sometimes the only feasible option to carry geophysical measurements. This study presents a new drone-towed electromagnetic induction and magnetic gradient sensor system used for near-surface characterization and areal *** system uses various datasets to enhance processing and interpretation. The system includes;an electromagnetic induction instrument;magnetic sensors;GNSS-IMU system;photogrammetry;Lidar model data;and geoid model data. Robust data processing and stochastic inversion subsurface characterization for archaeological prospecting with drone-towed electromagnetic induction and magnetic gradient sensor systems. Robust statistical methods were used to process the *** conducted the fieldwork at one of the ancient Viking settlements in Denmark. The surveyed area was approximately 100x$\times$200 m. We then implemented and applied a one-dimensional laterally constrained non-linear stochastic inversion to image the subsurface electrical conductivity. The inversion results show a consistent conductive layer at 5-8 m depths, likely associated with the groundwater level. This conductive layer is disrupted under a prominent anomaly within a 2-4 m wide area. Our analysis showed that this conductivity disruption could be a flint mine extending 7 m deep. This anomaly also has a strong signature in magnetic gradient data.

关键词： airborne EM archaeogeophysics data processing magnetic modelling

来源：评论

学校读者我要写书评

暂无评论

Semantic Ensemble Loss and Latent Refinement for High-Fidelity Neural image Compression

Semantic Ensemble Loss and Latent Refinement for High-Fideli...

引用

2024 conference on Visual Communications and image processing

作者： Li, Daxin Bai, Yuanchao Wang, Kai Jiang, Junjun Liu, Xianming Harbin Inst Technol Fac Comp Harbin Peoples R China

ISBN: (纸本)9798331529543;9798331529550

Recent advancements in neural compression have surpassed traditional codecs in PSNR and MS-SSIM measurements. However, at low bit-rates, these methods can introduce visually displeasing artifacts, such as blurring, color shifting, and texture loss, thereby compromising perceptual quality of images. To address these issues, this study presents an enhanced neural compression method designed for optimal visual fidelity. We have trained our model with a sophisticated semantic ensemble loss, integrating Charbonnier loss, perceptual loss, style loss, and a non-binary adversarial loss, to enhance the perceptual quality of image reconstructions. Additionally, we have implemented a latent refinement process to generate content-aware latent codes. These codes adhere to bit-rate constraints, and prioritize bit allocation to regions of greater importance. Our empirical findings demonstrate that this approach significantly improves the statistical fidelity of neural image compression.

关键词： Generative image Compression Learned image Compression

来源：评论

学校读者我要写书评

暂无评论

stochastic DEEP image PRIOR FOR MULTISHOT COMPRESSIVE SPECTRAL image FUSION

STOCHASTIC DEEP IMAGE PRIOR FOR MULTISHOT COMPRESSIVE SPECTR...

引用

IEEE International conference on Acoustics, Speech, and Signal processing (ICASSP)

作者： Jacome, Roman Monroy, Brayan Bacca, Jorge Arguello, Henry Univ Ind Santander Bucaramanga 680002 Colombia

ISBN: (纸本)9798350302615

The Deep image Prior (DIP) technique has been successfully employed in Compressive Spectral Imaging (CSI) as a non-data-driven deep model approach. DIP methodology updates the deep network's weights by minimizing a loss function that considers the difference between the measurements and the forward operator of the network's output. However, this method often yields local minima as all the measurements are evaluated at each iteration. This paper proposes a stochastic deep image prior (SDIP) approach, which stochastically trains DIP networks using random subsets of measurements from different CSI sensors in a CSI fusion (CSIF) setting, resulting in the improvement of the convergence through stochastic gradient descent optimization. The proposed SDIP method improves upon the deterministic DIP and requires less computational time since fewer forward operators are required per iteration. The SPID method provides comparable performance against the state-of-the-art CSIF techniques based on supervised data-driven and unsupervised methods, achieving up to 5 dB in the reconstruction.

关键词： Multishot Acquisition Synthetic Aperture Imaging stochastic Gradient Descent Deep image Prior

来源：评论

学校读者我要写书评

暂无评论

stochastic Optimization of Vector Quantization methods in Application to Speech and image processing 48

Stochastic Optimization of Vector Quantization Methods in Ap...

引用

48th IEEE International conference on Acoustics, Speech and Signal processing, ICASSP 2023

作者： Vali, Mohammad Hassan Backstrom, Tom Aalto University Department of Signal Processing and Acoustics Finland

ISBN: (纸本)9781728163277

Vector quantization (VQ) methods have been used in a wide range of applications for speech, image, and video data. While classic VQ methods often use expectation maximization, in this paper, we investigate the use of stochastic optimization employing our recently proposed noise substitution in vector quantization technique. We consider three variants of VQ including additive VQ, residual VQ, and product VQ, and evaluate their quality, complexity and bitrate in speech coding, image compression, approximate nearest neighbor search, and a selection of toy examples. Our experimental results demonstrate the trade-offs in accuracy, complexity, and bitrate such that using our open source implementations and complexity calculator, the best vector quantization method can be chosen for a particular problem. © 2023 IEEE.

关键词： Vector quantization

来源：评论

学校读者我要写书评

暂无评论

Assessment of the Current Local Transport Situation via Online processing of Monitoring Data and its Application for Traffic Regulation 17

Assessment of the Current Local Transport Situation via Onli...

引用

17th International conference on Management of Large-Scale System Development, MLSD 2024

作者： Solovyev, Anatoliy A. Valuev, Andrey M. Mechanical Engineering Research Institute Named after A.A.Blagonravov of Ras Laboratory of Dynamics of Man-Machine Systems Moscow Russia

ISBN: (纸本)9798350375718

A new approach to adaptive traffic light control at an intersection is being developed by using automatic control methods while constantly monitoring local traffic flow. methods of providing it with the necessary data, both characterizing the current local situation and statistical dependencies for the stochastic dynamics of traffic flows, are considered. methods for obtaining estimates of the values of monitored local traffic indicators are determined. The experience of computer modeling using the proposed method shows the expected reduction in traffic delays, as well as the possibility of choosing the most effective control method for a specific traffic situation. © 2024 IEEE.

关键词： stochastic models

来源：评论

学校读者我要写书评

暂无评论

The Lattice Overparametrization Paradigm for the Machine Learning of Lattice Operators 3rd

The Lattice Overparametrization Paradigm for the Machine Lea...

引用

3rd International Joint conference on Discrete Geometry and Mathematical Morphology (DGM)

作者： Marcondes, Diego Barrera, Junior Univ Sao Paulo Inst Math & Stat Dept Comp Sci Sao Paulo Brazil Texas A&M Univ Dept Elect & Comp Engn College Stn TX USA

ISBN: (纸本)9783031577925;9783031577932

The machine learning of lattice operators has three possible bottlenecks. From a statistical standpoint, it is necessary to design a constrained class of operators based on prior information with low bias, and low complexity relative to the sample size. From a computational perspective, there should be an efficient algorithm to minimize an empirical error over the class. From an understanding point of view, the properties of the learned operator need to be derived, so its behavior can be theoretically understood. The statistical bottleneck can be overcome due to the rich literature about the representation of lattice operators, but there is no general learning algorithm for them. In this paper, we discuss a learning paradigm in which, by overparametrizing a class via elements in a lattice, an algorithm for minimizing functions in a lattice is applied to learn. We present the stochastic lattice descent algorithm as a general algorithm to learn on constrained classes of operators as long as a lattice overparametrization of it is fixed, and we discuss previous works which are proves of concept. Moreover, if there are algorithms to compute the basis of an operator from its overparametrization, then its properties can be deduced and the understanding bottleneck is also overcome. This learning paradigm has three properties that modern methods based on neural networks lack: control, transparency and interpretability. Nowadays, there is an increasing demand for methods with these characteristics, and we believe that mathematical morphology is in a unique position to supply them. The lattice overparametrization paradigm could be a missing piece for it to achieve its full potential within modern machine learning.

关键词： lattice overparametrization discrete morphological neural networks image processing mathematical morphology U-curve algorithms stochastic lattice descent

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：