检索结果-内蒙古大学图书馆

4th International conference on Innovative Practices in Technology and Management, ICIPTM 2024

作者： Maroor, Jnaneshwar Pai Sahu, Dillip Narayan Nijhawan, Ginni Karthik, A. Shrivastav, A.K. Chakravarthi, M. Kalyan Nmam Institute of Technology-Affiliated to Nitte [Deemed to Be University Department of Humanities Karnataka India Gangadhar Meher University Department of Mca Odisha India Lovely Professional University Phagwara India Institute of Aeronautical Engineering Hyderabad Dundigal India Department of Mathematics &humanities Haryana Mullana-Ambala India VIT-AP University School of Electronics Engineering Amaravathi India

ISBN: (纸本)9798350307757

In this study, we examine the relatively new subject of image-based time series forecasting by using deep convolutional neural networks (also known as CNNs). The use of statistical methods and accurate numerical data have always been prerequisites for accurate time series forecasting. However, as a result of the accomplishments of CNNs in computer vision and the development of deep learning, a fresh approach has emerged. This work outlines a method for transforming time series data into structures that are analogous to pictures in order to facilitate the use of CNNs for the modelling of temporal patterns and the development of more accurate forecasting models. The research contributes to a greater understanding of the usefulness of deep learning in time series forecasting by providing insights into the process of picking models based on criteria such as accuracy, processing capability, and the specific dataset requirements. Keywords - Time Series Forecasting, Deep Convolutional Neural Networks, image-based Forecasting, Deep Learning, Neural Networks, Predictive Modeling, Temporal Patterns, Model Comparison. © 2024 IEEE.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Comparison of Traditional Tool Combination and Deep Learning methods for Automatic Classification of Steel Surface Defects 3

Comparison of Traditional Tool Combination and Deep Learning...

引用

3rd International conference on Embedded Systems and Artificial Intelligence, ESAI 2024

作者： Mentouri, Zoheir Bouguettaya, Abdelmalek Doghmane, Hakim Gherfi, Kaddour Bendjoudi, Salim Research Center in Industrial Technologies Cheraga Algiers16014 Algeria Université 8 Mai 1945 Laboratory of Inverse Problems Guelma24000 Algeria Université 8 Mai 1945 Guelma24000 Algeria

ISBN: (纸本)9798331522056

In industry, the automatic recognition of surface defects of flat steel products still represents a real challenge. Indeed, in addition to constraints such as the image noise or blur, there is neither an agreed standard of these defects, which can be of different sizes, shapes, orientations, and locations, nor a standard defect identification method, whether based on traditional tools such as statistical-based, spatial/frequency filtering based or model-based or on newer techniques such as deep learning. Hence, the complexity of the algorithm that deals with this matter always depends on the specific needs of the application. This paper focuses on the comparison of deep learning approaches with a new combination of traditional tools, namely the Gabor wavelets (GW) and the Local Phase Quantization, respectively known for image abrupt change representation and for the invariance to image blur. Both approaches are assessed on the North University (NEU) and a Research Center (RC_DDB) datasets, which include surface defect images of hot rolled steel product. Interesting correct-prediction rates and processing times are achieved for both approaches, with slightly higher scores for the Deep Learning approaches in terms of accuracy, but better computation times for the proposed combination. © 2024 IEEE.

关键词： Gabor filters

来源：评论

学校读者我要写书评

暂无评论

A self-supervised CNN for image denoising with self-similarity prior 16

A self-supervised CNN for image denoising with self-similari...

引用

16th IEEE International conference on Signal processing (ICSP)

作者： Fang, Wenqian Li, Hongwei China Univ Geosci Sch Math & Phys Wuhan Peoples R China

ISBN: (数字)9781665460569

ISBN: (纸本)9781665460569

Recently, a kind of blind-spot based self-supervised learning denoising method has attracted extensive research. The key of this kind of methods is to input Bernoulli-sampled instances and train network to recover the unsampled pixels. Based on the assumption that the image pixel is locally correlated while the noise exhibits statistical independence, the network will only recover the clean signal. Non-local self-similar priors play an important role in traditional image denoising methods, and can provide effective information for the reconstruction of unsampled pixels. We take blind-spot based method one step further by introducing non-local self-similarity prior into network processing flow. Specifically, we take the similar patch group as the processing unit, and design a non-local module in the network architecture to fuse the local and non-local information. Experiments show that the proposed non-local module can significantly improve the denoising performance.

关键词： self-supervise image denoising CNN self-similarity prior

来源：评论

学校读者我要写书评

暂无评论

Spectrally Optimized Feature Identification (SOFI): A Novel Band Selection Method for Hyperspectral image Analysis

Spectrally Optimized Feature Identification (SOFI): A Novel ...

引用

International conference on Machine Intelligence for GeoAnalytics and Remote Sensing (MIGARS)

作者： Chugh, Rohit Nidamanuri, Rama Rao Nelakuditi, Usha Rani Dileep, Malavika Davood, Asha Indian Inst Space Sci & Technol Dept Earth & Space Sci Thiruvananthapuram India Vignan Univ Dept Elect & Commun Engn Guntur Andhra Pradesh India Marian Coll Engn Thiruvananthapuram India

ISBN: (纸本)9798350345421

Hyperspectral data acquired from ground, drone or low-altitude airborne platforms have evolved to be the data of choice for various spectral imaging applications. The enormous interest of the scientific and industrial community in using hyperspectral imaging calls for automated processing and analysis methods. Enabling the use of external reference spectral libraries for hyperspectral image processing, statistical optimal bands selection (OBS) is the approach for handling dimensionality. The existing OBS algorithms are data and application specific. We present an adaptive evolutionary computing-based OBS algorithm, Spectrally Optimized Feature Identification (SOFI), to identify spectral bands optimal for different application domains. We demonstrate the practical applicability of the proposed algorithm by implementing it for identifying appropriate spectral bands for crop discrimination on a diverse landscape using airborne hyperspectral imagery acquired over a part of Anand district, India.

关键词： Hyperspectral imaging Optimal bands selection Feature selection Evolutionary optimization

来源：评论

学校读者我要写书评

暂无评论

Dual-Channel Deep Convolutional Neural Network for Limited-Angle CT image Restoration 9

Dual-Channel Deep Convolutional Neural Network for Limited-A...

引用

9th International conference on Communication, image and Signal processing, CCISP 2024

作者： Chen, Yu Zhang, LingLi School of Mathematics and Statistics Chongqing Jiaotong University Chongqing400074 China Chongqing University of Arts and Sciences Chongqing Key Laboratory of Statistical Optimization and Complex Data Chongqing402160 China Chongqing University of Arts and Sciences Chongqing Key Laboratory of Group & Graph Theories and Applications Chongqing402160 China

ISBN: (纸本)9798350356656

Based on the excellent performance of computed tomography (CT) in visualizing the inside of objects, it has become one of the indispensable technologies in the fields of medical diagnosis and industrial inspection. However, due to uncontrollable factors such as radiation dose and detection environment, it is necessary to consider how to obtain projection information within a certain scanning rotation angle range in most cases. In these situations, the reconstructed images using traditional analytical algorithms and iterative algorithms will suffer from limited-angle artifacts. Recently, deep learning technology has gained great attention in the field of image restoration due to its powerful learning ability and its rapid development and application. In order to make up for the limitations of traditional methods in suppressing artifacts in limited-angle CT reconstruction, this paper designs a dual-channel deep convolutional network to remove artifacts in reconstructed images with preserving the details and edges. Simulated and real experiments demonstrate that the presented network can effectively restore images, compared with the classical network. © 2024 IEEE.

关键词： Computerized tomography

来源：评论

学校读者我要写书评

暂无评论

Local and Global Thresholding-Based Breast Cancer Detection Using Thermograms 4th

Local and Global Thresholding-Based Breast Cancer Detection ...

引用

4th International conference on Machine Intelligence and Signal processing, MISP 2022

作者： Mishra, Vartika Rath, Subhendu Rath, Santanu Kumar NIT Rourkela Odisha Rourkela769008 India VCU RichmondVA23219 United States

ISBN: (纸本)9789819900466

In a recent study, to detect breast cancer abnormalities, thermography has been observed to be a qualitative modality. Due to an increase in blood vessel activity, the cancer cells and the tissues become hotter. Thus, by using thermography, the thermograms of the image are captured which depict the surface temperature of the breast, where the hot spot is indicated by the higher temperature. This modality has increased the non-invasiveness in detecting breast abnormalities. The different channels of the RGB (Red, Green, and Blue) image gives information of the different intensity of the color with respect to the image. In this work, the breast thermograms corresponding to the red channel are extracted for analysis. Further, three different thresholding methods viz., Otsu thresholding, Adaptive Mean Thresholding, and Adaptive Gaussian Thresholding methods are applied which depict the local image characteristics of the image. The image enhancement methods improve the quality of the image. Further, the statistical features are extracted from the obtained thresholded images, and two different classifiers Random Forest and Decision Tree are applied for classifying the normal and abnormal breasts. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： image enhancement

来源：评论

学校读者我要写书评

暂无评论

Breast image classification based on ResNet and Random forest multilayer classifier model 5

Breast image classification based on ResNet and Random fores...

引用

5th International conference on Bio-engineering for Smart Technologies, BioSMART 2023

作者： Rui, Tang Tianyi, Wang Yifan, Xu Hongji, Sun Toe, Teoh Teik Fuzhou University Mechanical Manufacturing and Automation Fuzhou China Fuzhou University Digital Media Technology Fuzhou China Nanyang Technological University Ntu Business Ai Lab Singapore

ISBN: (纸本)9798350338492

In this paper,a more optimal breast cancer detection model based on ResNet and random forest models is developed based on the combination of diagnostic methods of breast cancer pathology slice images and breast cancer detection studies. The proposed model is based on ResNet to classify breast MRI images, and random forest to select some samples and their features to compensate for the overfitting of ResNet in small sample data, and random forest to compensate for the overfitting of ResNet in small sample *** random forest compensates the disadvantage that ResNet generates a lot of redundancy when the sample features are of high *** the two models complement each other,the efficiency of image processing and the accuracy of image classification of the model are ***,a statistical analysis of the test results of the breast cancer detection model in this paper concluded that this model is more accurate and efficient in detecting classified breast cancer than a single machine learning model. © 2023 IEEE.

关键词： image classification

来源：评论

学校读者我要写书评

暂无评论

An End-to-end Learning Based Covolutional Neural Network for Single image Defogging Algorithm 2023

An End-to-end Learning Based Covolutional Neural Network for...

引用

5th International Symposium on Signal processing Systems, SSPS 2023

作者： Li, Qiqing Li, Ru Shen, Xin Lv, Wei School of Aliyun Big Data Applications Zhuhai College of Science and Technology China School of Aliyun Big Data Applications City University of Macau China

ISBN: (纸本)9798400700040

In the era of big data, there are more and more outdoor camera acquisition equipment. Due to the influence of extreme weather, such as fog, camera acquisition equipment is easy to lead to the decline of image quality and destroy the value of image application. Therefore, this paper will propose an advanced dehazing algorithm to make the foggy image clearer. Based on the principle of residual neural network, combined with attention mechanism and feature pyramid idea, this paper proposes an end to-end learning single image dehazing algorithm. Let the network learn the relationship between channels and pixels, and use the feature pyramid multi-scale fusion feature to restore the foggy image to a clear image. The SSIM score was 0.9687 and the PSNR score was 29.16. Very good results have been achieved on the RESIDE outdoor dataset. This paper finds the scores obtained by testing DCP, AOD-NET, DeHazeNet, and GFN methods on the same dataset. Compared with these four methods, there is a significant improvement. In particular, it is 15.39% higher than the DCP method on SSIM and 10.03% higher on PSNP. © 2023 ACM.

关键词： statistical tests

来源：评论

学校读者我要写书评

暂无评论

Strong-lensing source reconstruction with variationally optimized Gaussian processes

引用

MONTHLY NOTICES OF THE ROYAL ASTRONOMICAL SOCIETY 2022年第1期512卷 661-685页

作者： Karchev, Konstantin Coogan, Adam Weniger, Christoph Univ Amsterdam Gravitat Astroparticle Phys Amsterdam GRAPPA Inst Theoret Phys Amsterdam Sci Pk 904 NL-1098 XH Amsterdam Netherlands Univ Amsterdam Delta Inst Theoret Phys Sci Pk 904 NL-1098 XH Amsterdam Netherlands SISSA Scuola Int Super Studi Avanzati Via Bonomea 265 I-34136 Trieste Italy

Strong-lensing images provide a wealth of information both about the magnified source and about the dark matter distribution in the lens. Precision analyses of these images can be used to constrain the nature of dark matter. However, this requires high-fidelity image reconstructions and careful treatment of the uncertainties of both lens mass distribution and source light, which are typically difficult to quantify. In anticipation of future high-resolution data sets, in this work we leverage a range of recent developments in machine learning to develop a new Bayesian strong-lensing image analysis pipeline. Its highlights are (a) a fast, GPU-enabled, end-to-end differentiable strong-lensing image simulator;(b) a new, statistically principled source model based on a computationally highly efficient approximation to Gaussian processes that also takes into account pixellation;and (c) a scalable variational inference framework that enables simultaneously deriving posteriors for tens of thousands of lens and source parameters and optimizing hyperparameters via stochastic gradient descent. Besides efficient and accurate parameter estimation and lens model uncertainty quantification, the main aim of the pipeline is the generation of training data for targeted simulation-based inference of dark matter substructure, which we will exploit in a companion paper.

关键词： gravitational lensing: strong methods: statistical techniques: image processing dark matter

来源：评论

学校读者我要写书评

暂无评论

Glaucoma Detection on Eye Fundus image using Machine Learning Method

Glaucoma Detection on Eye Fundus Image using Machine Learnin...

引用

2023 International conference on Artificial Intelligence Robotics, Signal and image processing, AIRoSIP 2023

作者： Bagaskara, Dhimas Chandra Saidah, Sofia Magdalena, Rita Telkom University School of Electrical Engineering Bandung Indonesia

ISBN: (纸本)9798350327472

Glaucoma is an eye disease caused by continuous pressure on the optic nerve papillae. It can be caused by an unbalanced cycle of the aqueous humor fluid. People with glaucoma have a reduced field of vision that can lead to blindness, depending on the severity. Glaucoma can be detected in several ways, there are Confocal Scanning Laser Ophthalmoscopy (CSLO), Heidelberg Retinal Tomography (HRT), and Optical Coherence Tomography (OCT). However, these methods are expensive. Another alternative to early detection of glaucoma is using detection on digital fundus images, which are faster and require lower costs. In this research, a system of digital fundus image detection was designed using a machine learning model with the Gray Level Co-occurrence Matrix (GLCM), Decision Tree, and Random Forest algorithms. The GLCM algorithm is used to perform feature extraction. Meanwhile, Decision Tree and Random Forest algorithms are used to classify fundus images as glaucoma or normal. The purpose of this research is to assist in the early detection of glaucoma quickly and accurately. The result of the accuracy value is higher when using the Decision Tree algorithm. The results show that when using the Decision Tree algorithm, the highest accuracy value is 85%, with the combination of correlation, dissimilarity, contrast, ASM, and homogeneity features, and when using the Random Forest algorithm, the highest accuracy value is 82.5% with using all six second-order statistical features. © 2023 IEEE.

关键词： Optical coherence tomography

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：