检索结果-内蒙古大学图书馆

2nd International conference on Augmented Intelligence and Sustainable systems, ICAISS 2023

作者： Devisurya, V. Paulson, J. Seshadhri, M. Varshini, P. Nagaraj, P. Muneeswaran, V. Kongu Engineering College Department of Information Technology Erode India Kalasalingam Academy of Research and Education Department of Computer Science and Engineering Virudhunagar India Kalasalingam Academy of Research and Education Department of Electronics and Communication Engineering Virudhunagar India

ISBN: (纸本)9798350325799

To ensure functionality and durability, engineering constructions must have fractures identified and repaired. Since cracks are typically discovered through visual inspection, the examiner's personal judgment plays a vital part in both the detection of concrete cracks and the estimation of their characteristics. In the past, this has helped with both the evaluation of the crack phenomenon and the repair of various structures. The number of engineering structures has expanded as a result of industrial development, but relative to that, the level of skill in the crack-detecting field has not improved. Therefore, a quicker yet more precise method is required. The image processing method detects the cracks and their characteristics simultaneously. The formulation of the algorithm and the implementation is simple. However, other flaws, such as mistaking noises for fractures and a lack of accuracy in spotting micro-cracks, have turned into major obstacles for this technology. Finding transverse cracks in concrete structures is another critical problem. Therefore, a thorough analysis of the most recent articles is required to establish an accurate technique. In order to comprehend the potential of this technology, a critical study of the image-processing phenomenon and a thorough literature review has been done in this paper. A universal DenseNet121 classification-based algorithm with camera pictures for crack identification could be an effective strategy with greater accuracy. © 2023 IEEE.

关键词： image enhancement

来源：评论

学校读者我要写书评

暂无评论

Rough Fuzzy Multi-view Clustering Based on Self-Weighting Strategy

Rough Fuzzy Multi-view Clustering Based on Self-Weighting St...

引用

Natural Language processing (ICNLP), International conference on

作者： Huarong Jing xiumei Cai Chengmao Wu The School of Automation Xi’an University of Posts and Telecommunications Xi’an China The School of Electronic Engineering Xi’an University of Posts and Telecommunications Xi’an China

ISBN: (数字)9798350349115

ISBN: (纸本)9798350349122

Multi-view clustering has achieved great progress, but it is difficult to effectively solve the problem of noisy image segmentation. To address this, this paper proposes a self-weighting rough fuzzy multi-view clustering algorithm oriented to the segmentation of noisy interference images. Firstly, it divides the conventional fuzzy partition matrix into two types: difference and consistency, and uses a balance coefficient to ensure stable collaboration between different and common information. Secondly, by combining rough set and fuzzy set theories, it divides the lower approximation region and boundary region for the clustering center, which can solve the issue of clustering structural uncertainty. Moreover, a new self-weighting mechanism is proposed, which adds product constraints and an exponential factor to effectively balance the impact of each view on the clustering results and improve the performance of the algorithm. Finally, to meet the segmentation needs of noisy images, spatial information and kernel metrics are introduced to improve the robustness of the algorithm. Experiments on some noisy images show that the evaluation metrics of our proposed algorithm are all better than the six compared algorithms, with better segmentation performance, and the accuracy is all higher than 0.94.

关键词： image segmentation Uncertainty Clustering algorithms Rough sets Interference Robustness Natural language processing Partitioning algorithms Noise measurement Kernel

来源：评论

学校读者我要写书评

暂无评论

Adaptive Broad Learning Network for LPI Radar Waveform Recognition 9

Adaptive Broad Learning Network for LPI Radar Waveform Recog...

引用

9th International conference on Intelligent Computing and Signal processing, ICSP 2024

作者： Wang, Dong Cui, Tianshu Li, Ruike Huang, Yonghui Zhu, Yan National Space Science Center Chinese Academy of Sciences Beijing China University of Chinese Academy of Sciences Beijing China China Academy of Aerospace Science and Innovation Beijing China Key Laboratory of Electronics and Information Technology for Space Systems Beijing China

ISBN: (纸本)9798350376548

Low probability of intercept (LPI) radar waveform recognition is a crucial branch in the field of electronic reconnaissance, serving as a vital method for acquiring information from non-cooperative radar sources. In recent times, deep learning models have demonstrated significant breakthroughs in the field of LPI radar waveform recognition (LWR). While these models significantly enhance recognition accuracy, the abundance of parameters and computations in the model renders training time-consuming, and the model structure lacks flexibility and scalability. To address these challenges, we propose an adaptive broad learning network (ABLN) for LWR. The ABLN transforms the time-frequency images (TFIs) of radar signals into feature nodes and enhancement nodes, with waveform types represented as output nodes. We further introduced a strategy for adaptively adjusting network parameters to reduce computational overheads, facilitating expedited optimization of the model structure. The simulation results show that ABLN has superior performance compared with other LWR methods. © 2024 IEEE.

关键词： image enhancement

来源：评论

学校读者我要写书评

暂无评论

Enhancing Sign Language Recognition Using Deep Convolutional Neural Networks 14

Enhancing Sign Language Recognition Using Deep Convolutional...

引用

14th International conference on Information, Intelligence, systems and Applications, IISA 2023

作者： Kanavos, Athanasios Papadimitriou, Orestis Mylonas, Phivos Maragoudakis, Manolis University of the Aegean Department of Information and Communication Systems Engineering Samos Greece University of West Attica Department of Informatics and Computer Engineering Athens Greece Ionian University Department of Informatics Corfu Greece

ISBN: (纸本)9798350318067

The advancements in sensing technologies and AI algorithms have opened up a wide range of possibilities for developing applications to meet the needs of individuals who are deaf or hard of hearing. Sign language plays a vital role in the lives of people with hearing and speaking disabilities. This research aims to explore digital image processing and machine learning methods for efficiently building a sign language dataset and creating a sign language interface system. The proposed system utilizes a Convolutional Neural Network (CNN) to analyze and interpret hand gestures and poses, converting them into natural language. The developed CNN model specifically focuses on improving the accuracy of predicting the American Sign Language alphabet. Despite variations in dataset conditions and size, the model achieved an exceptional accuracy rate of 98.73%. Additionally, it demonstrated a low loss value of 0.0539, indicating its robust performance. © 2023 IEEE.

关键词： image classification

来源：评论

学校读者我要写书评

暂无评论

Classification and recognition of soybean leaf diseases in Madhya Pradesh and Chhattisgarh using Deep learning methods 2

Classification and recognition of soybean leaf diseases in M...

引用

2nd International conference on Paradigm Shifts in Communications Embedded systems, Machine Learning and Signal processing, PCEMS 2023

作者： Dixit, Shriniket Kumar, Anant Haripriya, Akash Bohre, Khitij Srinivasan, Kathiravan SCOPE Vellore India School of Bioscience and Technology Vellore India Oriental College of Science and Technology SCOPE Bhopal India Acropolis Institute of Technology SCOPE Indore India

ISBN: (纸本)9798350310719

Soybean is a major economic crop worldwide. So proper disease control measures must be implemented to reduce losses. These diseases can significantly affect the yield and quality of soybeans. Machine vision and pattern recognition technologies can help accurately diagnose crop diseases and minimize financial losses for soybean farmers. Many research papers discuss the use of deep learning algorithms for imagebased disease detection, including for soybean crops based on CNN, SVM, KNN, etc. However, lacking a well-curated dataset for soybean diseases is a challenge. Additionally, many existing research papers focus more on demonstrating the approach's feasibility rather than providing solutions to the specific problems faced in a particular region. The proposed deep learning-based classification system for soybean leaf diseases can help identify Angular Leaf spots, Bacterial blight, Soybean Rust, and Downy mildew. An image dataset was created, and image-enhancing techniques were applied during pre-processing. The proposed classifier system achieved an efficiency of 83.9%, 93.01%, and 71.98% in classifying diseases using CNN, Resnet-V2, and KNN classifiers, respectively. © 2023 IEEE.

关键词： image enhancement

来源：评论

学校读者我要写书评

暂无评论

An Enhanced Approach to Content-based image Retrieval using Harris Hawks Optimization and Automated image Captioning 8

An Enhanced Approach to Content-based Image Retrieval using ...

引用

8th International conference on I-SMAC (IoT in Social, Mobile, Analytics and Cloud), I-SMAC 2024

作者： Padate, Roshni Gupta, Ashutosh Chakrabarti, Prasun Sharma, Arvind Fr. Conceicao Rodrigues College of Engineering Computer Engineering Mumbai India Sir Padampat Singhania University Computer Science and Engineering Udaipur India Sir Padampat Singhania University Department of Mathematics Udaipur India

ISBN: (纸本)9798350376425

This paper introduces an innovative approach to Content-Based image Retrieval (CBIR) that leverages Harris Hawks Optimization (HHO) to improve feature selection and retrieval accuracy. CBIR systems are increasingly important in fields such as medical imaging and remote sensing, where efficient and accurate image retrieval is essential. Inspired by the cooperative hunting strategies of Harris hawks, the HHO algorithm efficiently balances exploration and exploitation, optimizing the feature extraction process to enhance retrieval outcomes. The proposed system is evaluated on various datasets and compared to other optimization techniques, such as Particle Swarm Optimization (PSO) and Genetic algorithms (GA). The findings show that the HHO-optimized system outperforms these methods in terms of precision, recall, and F1-scores, while also reducing retrieval ***, the incorporation of image captioning into the CBIR framework further improves the user experience. By integrating Computer Vision (CV) and Natural Language processing (NLP), the system generates descriptive captions along- side retrieved images, offering valuable textual context. This capability allows users to quickly evaluate the relevance of retrieved images, particularly in complex fields like medical imaging. Experimental results demonstrate that the combination of HHO-based optimization and image captioning significantly enhances both retrieval accuracy and user satisfaction, making it a powerful solution for large-scale image retrieval tasks. © 2024 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Research on the Algorithm of License Plate Recognition Based on MPGAN Haze Weather

引用

IEICE TRANSACTIONS ON INFORMATION AND systems 2022年第5期E105D卷 1085-1093页

作者： Zhang, Weiguo Lu, Jiaqi Zhang, Jing Li, Xuewen Zhao, Qi Xian Univ Sci & Technol Xian Peoples R China

The haze situation will seriously affect the quality of license plate recognition and reduce the performance of the visual processing algorithm. In order to improve the quality of haze pictures, a license plate recognition algorithm based on haze weather is proposed in this paper. The algorithm in this paper mainly consists of two parts: The first part is MPGAN image dehazing, which uses a generative adversarial network to dehaze the image, and combines multi-scale convolution and perceptual loss. Multi-scale convolution is conducive to better feature extraction. The perceptual loss makes up for the shortcoming that the mean square error (MSE) is greatly affected by outliers;the second part is to recognize the license plate, first we use YOLOv3 to locate the license plate, the STN network corrects the license plate, and finally enters the improved LPRNet network to get license plate information. Experimental results show that the dehazing model proposed in this paper achieves good results, and the evaluation indicators PSNR and SSIM are better than other representative algorithms. After comparing the license plate recognition algorithm with the LPRNet algorithm, the average accuracy rate can reach 93.9%.

关键词： image dehazing generative adversarial network multi-scale convolution perceptual loss license plate recognition

来源：评论

学校读者我要写书评

暂无评论

A super-resolution algorithm for tire images based on second-order channel attention 6

A super-resolution algorithm for tire images based on second...

引用

6th International conference on Artificial Intelligence and Pattern Recognition, AIPR 2023

作者： Li, Yutong Bi, Ping Liu, Ying Xu, Jian Center for Image and Information Processing Xi'an University of Posts and Telecommunications China

ISBN: (纸本)9798400707674

Tire images are a type of crime scene investigation image that is useful in case detection. However, due to restrictions on the acquisition conditions, these images have a low resolution. image super-resolution may be able to solve this problem. The super-resolution method, which uses the transformer structure as its backbone, has provided the best reconstruction results to date. Although these algorithms can model global features, they disregard correlations between channel features and do not prioritize the channels that are conducive to reconstruction. For textured tire images that contain textural characteristics, a second-order channel attention image super-resolution algorithm is proposed. It builds a parallel transformer layer to quantify the connection between channel features using second-order covariance statistics, such that the channels that contribute considerably to the results get more attention. Furthermore, it presents a non-linear reconstruction module, in which the dropout layer is connected after the upper-sampling layer, which can not only recover finer image details but also increase the network's stability and robustness. The results of the tire dataset and standard test dataset experiments indicate that our approach may give a more realistic and finely detailed image. Its PSNR value is greater than 0.06-0.12 dB, allowing for high-quality image reconstruction. © 2023 ACM.

关键词： Tires

来源：评论

学校读者我要写书评

暂无评论

A method of detecting run-on essays based on the degree of tangency 7

A method of detecting run-on essays based on the degree of t...

引用

7th International conference on Intelligent Computing and Signal processing, ICSP 2022

作者： Zhang, Haotian Zhu, Zhengdong Hu, Yahong Liu, Pengjie Xi'an Jiaotong University School of Software Engineering Xi'an China Xi'an Jiaotong University School of Computer Science and Technology Xi'an China Zhejiang University of Technology College of Computer Science and Technology Hangzhou China

ISBN: (纸本)9781665478571

This study proposes a method to detect whether an essay is off-topic or not based on the degree of tangency, because of the lack of accurate and efficient algorithms for off-topic detection in domestic essay-assisted grading systems. This study uses the LDA topic model to extract the topic in the set of topic requirements and reference essays and extracts the topic words of the essays to be evaluated, based on which the proposed method of calculating the topic degree is used to calculate the topic degree, to measure the relevance of the essays to the topic, and finally filter the runaway essays by setting a reasonable threshold. The experimental results show that this method is more effective than the traditional TF-IDF algorithm based on the vector space model and can detect more run-on essays, and the accuracy rate is higher, with the F value reaching over 90%, which achieves the intelligent processing of essay run-on detection and can be effectively applied in English composition teaching. © 2022 IEEE.

关键词： Statistics

来源：评论

学校读者我要写书评

暂无评论

New Type-2 Fuzzy Logic Algorithm Based image Segmentation for Medical Imaging Applications 9

New Type-2 Fuzzy Logic Algorithm Based Image Segmentation fo...

引用

9th IEEE International conference on Smart Structures and systems, ICSSS 2023

作者： Sangeetha, S. Latha, B. Anna University Veltech Multitech Dr. Rangarajan Dr. Sakunthala Engineering College Department of Information Technology Chennai India Sri Sairam Engineering College Department of Computer Science and Engineering Chennai India

ISBN: (纸本)9798350384208

Medical image segmentation is a plan that has a lot of potential. The achievement of automated picture segmentation makes it simple to gather biomedical and anatomical information. In terms of the subject, more study and work have increased efficacy. In the field of image processing, this work provides a type-2 fuzzy system-based image application. Computer aided diagnosis and medical image analysis both heavily rely on segmentation. This study presents a fuzzy type 2 algorithm based automated threshold selection method for the division of therapeutic pictures. It has been established that fuzzy set theory may be an effective tool for recitation surroundings when the facts are unclear or inaccurate. The algorithms have been put into practice and evaluated using brain MRI (magnetic resonance imaging) images. The outcomes have been evaluated and documented. The comparison of the controller's efficiency of CNN has 92%. © 2023 IEEE.

关键词： image segmentation

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：