检索结果-内蒙古大学图书馆

14th IEEE International Conference on Communication Systems and Network Technologies, CSNT 2025

作者： Wang, Tianjian School of Computer Science and Technology Wuhan Qingchuan University Hubei Wuhan430204 China

ISBN: (纸本)9798331531935

To address the issue of low accuracy and poor robustness of perceptual learning in complex scenarios, a new method integrating computer vision and machine learning is adopted, that is, by applying deep neural networks, transfer learning and self-supervised learning, combined with multimodal data fusion strategy, to improve target recognition efficiency and learning ability. First, based on the preprocessing algorithm of improved Gaussian filtering and image segmentation, the quality of image features is improved. Data enhancement methods such as random rotation, flipping, and blurring are used to expand data distribution and improve model adaptability. Secondly, a convolutional neural network (CNN) is utilized in combination with an attention mechanism to extract multi-scale target features, and transfer learning is applied to transfer common features from pre-trained models to reduce dependence on large-scale labeled data. Finally, a contrastive learning framework is constructed to mine the correlation of unlabeled data. Transformer is used to realize the fusion of multimodal data of images and texts, and the model performance is optimized through multi-task learning. The mAP (Mean Average Precision) of the traditional method in dynamic occlusion scenarios is 60.5%, which is relatively weak. This may be because the traditional method cannot fully extract the effective features of the target under the occlusion of complex moving targets. The mAP of the method in this paper is 72.8%, which is higher than that of the traditional method. The perceptual learning method adopted in this paper effectively improves the accuracy and robustness in complex scenarios, and provides reliable technical support for intelligent applications. In the future, it can be combined with edge computing to further optimize the real-time processing capability and promote its application in the fields of unmanned driving and intelligent security. © 2025 IEEE.

关键词： image segmentation

来源：评论

学校读者我要写书评

暂无评论

Deepfake image and Video Detection Using Deep Learning Algorithms

Deepfake Image and Video Detection Using Deep Learning Algor...

引用

2025 International Conference on Multi-Agent Systems for Collaborative Intelligence, ICMSCI 2025

作者： Srinivasan, Srivanth Nischitha, P. Chavan, Akshita Mohana Rv College of Engineering® Bengaluru India Rv College of Engineering® Bengaluru India

ISBN: (纸本)9798331509828

Deep learning (DL) algorithms are swiftly finding applications in computer vision and natural language processing. Nonetheless, they can also be employed for creating convincing deepfakes, which are challenging to distinguish from reality. The advancements in image and video technology and tools, especially on social media platforms, potentially lead to misuse for malicious purposes like blackmail or defamation. To tackle this issue, several group of researchers tried upon spreading or creating awareness on real or fake data. The proposed approach involves combining Deepfake generation using GANs and Autoencoders with a Deepfake detection method. The aim of this initiative is exclusively to combat disinformation and online fraud for the welfare of the general population. Deepfakes, products of AI, have become increasingly realistic, rendering it nearly difficult to distinguish the content. Auto-encoders with sufficient time can achieve about 92 % accuracy. As the generator improves, the discriminator performance worsens as it struggles to differentiate real or fake data. A perfect generator results in 50% accuracy. With advancements in computational capacity and data availability, the proposed DDM (Deepfake Detection Model) has achieved greater accuracy rate of up to 92.3%. © 2025 IEEE.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Recognition and evaluation of cutaneous condition through assorted artificial intelligence reliant algorithms

引用

International Journal of Information Technology (Singapore) 2025年 1-13页

作者： Mishra, Manmohan Yadav, Ajay Kumar Mazumdar, Bireshwar Dass Gupta, Prashant K. Panwar, Arvind Bharadwaj, Shivam Department of Computer Application United Institute of Management Prayagraj India School of Computer Science & Engineering Technology Bennett University Plot Nos 8-11 TechZone II Uttar Pradesh Greater Noida 201310 India Galgotias University Plot No. 2 Yamuna Expy opposite Buddha International Circuit Sector 17A Uttar Pradesh Prayagraj 203201 India

Our skin is the hefty organ that envelops and shields body. It prevents us from numerous fatal and non fatal diseases. It is observed that due to bacteria or other causes of infection, skin faces certain minor or life threatening diseases. The most prioritized step toward restoring health is early illness signs identification. Identifying Cutaneous Condition from clinical images is one of the foremost challenges in medical image investigation. In the presented study we will enlighten the various Artificial Intelligence techniques falling under the categories of supervised machine learning including Probabilistic classifier (Naïve Bayes), Statistical algorithm (Logistic Regression), Ensemble learning (Random Decision Trees), Data analysis technique (Convolutional Neural Network) and Kernel approach (Support Vector machine) to identify and classify the cutaneous condition appropriately so that corrective measures of skin treatment can be endow with. The proposed approach entails collecting images as input, preprocessing, segmenting, feature extraction and lastly applying the classification algorithms to derive the Cutaneous Condition categories. Additional trials are conducted using the different approaches as indicated and it was discovered from the suggested tests that the Convolutional Neural Network strategy yields the best results overall. The proposed model is trained, tested, and evaluated using the International Skin Imaging Collaboration (ISIC) 2019 challenge dataset and Human Against machine with 10,000 training images (HAM10000) for the detection of manifold Cutaneous Condition. © Bharati Vidyapeeth's Institute of Computer applications and Management 2025.

关键词： Artificial intelligence Confusion matrix Convolutional neural networks Cutaneous condition image processing machine learning

来源：评论

学校读者我要写书评

暂无评论

Accurate image Registration Using Evolutionary Algorithms 5th

Accurate Image Registration Using Evolutionary Algorithms

引用

5th International Conference on Data Science, machine Learning and applications, ICDSMLA 2023

作者： Gobi, N. Kumar, Ritesh Kumar, Deepak Singh, Ashutosh Kr. Karnataka Bangalore India Maharishi School of Engineering & Technology Maharishi University of Information Technology Uttar Pradesh Lucknow India Department of Mathematics Vivekananda Global University Jaipur India Department of Electronics and Communication Engineering Noida Institute of Engineering and Technology Uttar Pradesh Noida India

ISBN: (纸本)9789819780426

Photograph registration is aligning or more excellent snapshots of the same bodily object or scene;it's widely used in many regions of image processing and pc imaginative and prescient. Evolutionary algorithms are optimization algorithms stimulated with herbal choice aid and used efficiently for image registration. The principal advantage of evolutionary algorithms is their potential to remedy complex optimization tasks without relying on a given set of heuristics. Additionally, they require fewer parameters for the convergence than conventional optimization algorithms with gradient descent and might reap better accuracy with reduced computational time. Evolutionary algorithms can also deal with multiple goals simultaneously, making them suitable for photo registration packages. Genetic algorithms can deal with both simple and complex problems and can be efficiently deployed for registration responsibilities in a disbursed computing place. Evolutionary algorithms have been used efficaciously for many picture registration programs, which include medical imaging, satellite picture registration, and face reputation. Their combination of high accuracy and low computational time makes them a famous desire for registration troubles inside the subject of pc vision. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Genetic algorithms

来源：评论

学校读者我要写书评

暂无评论

Retinal image Analysis for Detection of Diabetic Macular Edema Using Transfer Learning 8

Retinal Image Analysis for Detection of Diabetic Macular Ede...

引用

8th International Conference on Data Science and machine Learning applications, CDMA 2025

作者： Asim, Tayyaba Akbar, Shahzad Shahzore, Usama Rehman, Amjad Saba, Tanzila Ayesha, Noor Riphah College of Computing Riphah International University Faisalabad Pakistan Prince Sultan University AIDA Lab. CCIS Riyadh Saudi Arabia Zhengzhou University Zhengzhou China Henan450001 China

ISBN: (纸本)9798331539696

Diabetic Macular Edema (DME) is a disease of the eye's retina and it's a major factor of causing vision problems and leads towards blindness if it is undiagnosed. Early detection of DME can prevent vision loss and may reduce diabetic-related problems like cardiovascular issues. Therefore, this study presents a method for detecting DME through Optical Coherence Tomography (OCT) and fundus images using transfer learning. The proposed method is based on four stages: Pre-processing, augmentation, segmentation through DeepLabV3+, and binary classification of DME by using two (02) publicly available datasets;the first dataset is Messidor-2, which contains fundus images, and the second dataset is Retinal images of Optical Coherence Tomography (OCT). In the Messidor-2 dataset, the total number of images is 1744, and Retinal OCT images dataset consists of 84,495 images total, separated into four categories (CNV, DME, DRUSEN, NORMAL). In the proposed method, Convolutional Neural Networks (CNN) architectures ResNet50 and VGG-19 have been used for the detection of the DME. Convolutional Neural Networks (CNNs) have been extensively used in medical imaging analysis and classification. Using the well-known ResNet50 architecture for classification of each dataset, the proposed model yielded an accuracy of 98.79%, 99% of F1 Score, 98.43% of Precision, and recall of 98.89%. By using VGG-19, the proposed model gives an accuracy of 98.81%, 98.94% of Fl Score, 98.1 % of Precision and recall of 98.73%. When both models (ResNet50 and VGG-19) were compared, the VGG-19 gave the best accuracy. © 2025 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Surface quality and orientation estimation using speckle imaging of ground specimens

引用

Procedia Computer Science 2025年 253卷 2096-2105页

作者： Deep Singh N. Arunachalam Department of Mechanical Engineering Indian Institute of Technology Madras Chennai Tamil Nadu India PIN - 600036

In the current era, machine vision systems are being implemented widely in varied fields due to its key features, such as rapid processing, non-contact-based technology and in-situ measurements. This technology also possesses wide applications in the manufacturing sector. The surface texture properties of any machined component vary based on the manufacturing process, machining parameters, tool and machine conditions etc. As the surface texture of the machined components greatly influences the functional performance, it is vital to examine the surface characteristics. The surface texture of the machine component can be assessed by implementing a series of image processing techniques on its speckle images. Speckle image refers to the randomly distributed granular pattern which is obtained when a rough or textured surface is illuminated using a laser beam. This paper focuses on estimating the orientation of the workpiece and examining the surface characteristics based on the post-processing of the speckle images. The hardened steel workpieces used in this investigation were ground by varying the process parameters and speckle images were obtained at 0°, 30°, 60° and 90° orientations. The shifted power spectral density of the ground sample images contains high-energy coefficients which mimic a line and its orientation varies based on the sample orientation. The Hough transform technique was applied to the binary image of shifted PSD to efficiently determine the orientation. Furthermore, correlations have been established between several surface texture characteristics and GLCM parameters with the surface roughness of ground samples.

关键词： Speckle image Grinding image processing Power spectral density (PSD) Hough transform Gray level co-occurrence matrix

来源：评论

学校读者我要写书评

暂无评论

A lightweight pineapple detection network based on YOLOv7-tiny for agricultural robot system

引用

COMPUTERS AND ELECTRONICS IN AGRICULTURE 2025年 231卷

作者： Li, Jiehao Li, Chenglin Zeng, Shan Luo, Xiwen Chen, C. L. Philip Yang, Chenguang South China Agr Univ Coll Engn Key Lab Key Technol Agr Machine & Equipment Minist Educ Guangzhou 510642 Peoples R China South China Univ Technol Sch Comp Sci & Engn Guangzhou 510641 Peoples R China Univ Liverpool Dept Comp Sci Liverpool L693BX England

Automatic detection of pineapples in complex agricultural environments poses several challenges. During harvesting, pineapples that are suitable for collection exhibit intricate scaly surface textures and a wide range of colors. Moreover, occlusion by leaves and fluctuating lighting conditions further complicate the detection of pineapples. In this paper, we propose a high-precision lightweight detection network based on the improved You Only Look Once version 7-tiny (Pineapple-YOLO) for the robot vision system to realize realtime and accurate detection of pineapple. The Convolutional Block Attention Module (CBAM) is embedded into the backbone network to enhance the feature extraction capability, and the Content-Aware Reassembly of Features (CARAFE) is introduced to perform up-sampling operations and expand the receptive field. The Scylla Intersection over Union (SIoU) loss function is used instead of the Complete Intersection over Union (CIoU) loss function to consider the vector angles and redefine the penalty criteria. Finally, the K-means++ clustering algorithm is used to re-cluster the labels of the pineapple dataset and update the size of the anchor. The experimental results show that Pineapple-YOLO achieves a mAP@0.5 of 89.7%, which is a 6.15% improvement over the original YOLOv7-tiny, demonstrating its superiority over other mainstream target detection models. Furthermore, in diverse natural environments where the agricultural robot operates, the Pineapple-YOLO algorithm sustains a commendable 92% success rate in fruit picking, achieved within an average time of 12 s. This demonstrates the efficiency of the visual module in practical engineering applications.

关键词： Agricultural robotics Target detection image processing Lightweight networks Pineapple

来源：评论

学校读者我要写书评

暂无评论

Multichannel Object Detection with Event Camera

Multichannel Object Detection with Event Camera

引用

International image processing, applications and Systems Conference (IPAS)

作者： Rafael Iliasov Alessandro Golkar Chair of Spacecraft Systems Technical University of Munich Munich Germany

ISBN: (数字)9798331506520

ISBN: (纸本)9798331506537

object detection based on event vision has been a dynamically growing field in computer vision for the last 16 years. In this work, we create multiple channels from a single event camera and propose an event fusion method (EFM) to enhance object detection in event-based vision systems. Each channel uses a different accumulation buffer to collect events from the event camera. We implement YOLOv7 for object detection, followed by a fusion algorithm. Our multichannel approach outperforms single-channel-based object detection by 0.7% in mean Average Precision (mAP) for detection overlapping ground truth with IOU = 0.5.

关键词： Computer vision Event detection machine vision AI accelerators Object detection Cameras Feature extraction Real-time systems

来源：评论

学校读者我要写书评

暂无评论

A Survey on Graph Neural Networks and its applications in Various Domains

引用

SN Computer Science 2025年第1期6卷 1-12页

作者： Murgod, Tejaswini R. Reddy, P. Srihith Gaddam, Shamitha Sundaram, S. Meenakshi Anitha, C. Department of Artificial Intelligence & Machine Learning BNM Institute of Technology Karnataka Bengaluru India Department of Computer Science and Engineering NITTE Meenakshi Institute of Technology Karnataka Bengaluru India

Graph Neural Networks (GNNs) are neural models that use message transmission between graph nodes to represent the dependency of graphs. Variants of Graph Neural Networks (GNNs), such as graph recurrent networks (GRN), graph attention networks (GAT), and graph convolutional networks (GCN), have shown remarkable results on a variety of deep learning tasks in recent years. In this study, we offer a generic design pipeline for GNN models, go over the variations of each part, classify the applications in an organized manner, and suggest four outstanding research issues. Dealing with graph data, which provides extensive connection information among pieces, is necessary for many learning tasks. A model that learns from graph inputs is required for modelling physics systems, learning molecular fingerprints, predicting protein interfaces, and identifying illnesses. Reasoning on extracted structures (such as the dependency trees of sentences and the scene graphs of photos) is an important research issue that also requires graph reasoning models in other domains, such as learning from non-structural data like texts and images. Graph Neural Networks (GNNs) are primarily designed for dealing with graph-structured data, where relationships between entities are modeled as edges in a graph. While GNNs are not traditionally applied to image classification problems, researchers have explored ways to leverage graph-based structures to enhance the performance of Convolutional Neural Networks (CNNs) in certain scenario. GNN have been increasingly applied to Natural Language processing (NLP) tasks, leveraging their ability to model structured data and capture relationships between elements in a graph. GNN are also applied for traffic related problems particularly in modeling and optimizing traffic flow, analyzing transportation networks, and addressing congestion issues. GNN can be used for traffic flow prediction, dynamic routing & navigation, Anomaly detection, public transport network

关键词： Computer vision Graph neural networks Intrusion detection Natural language processing Neural networks Traffic control

来源：评论

学校读者我要写书评

暂无评论

On the recent activities of IP005 Special Research Committee on image processing of the JSNDI: machine vision applications in NDT

引用

INSIGHT 1998年第4期40卷 276-278页

作者： Koshimizu, H Suga, Y Ishii, A Chukyo Univ Sch Cognit & Comp Sci Toyota 4700348 Japan Keio Univ Dept Mech Engn Kouhoku Ku Yokohama Kanagawa 223 Japan Univ Electrocommun Chofu Tokyo 182 Japan

The IP005, 005 Special Research Committee on image processing for NDI of the Japanese Society of Non-Destructive Inspection (JSNDI) was established in 1979 as the fifth traversal research infrastructure among X-ray, ultrasonic and other NDI technology groups. This committee was chaired by M Onoe, E Yamamoto, M Takagi and H Yamada. It became more active in the early summer of 1996 under renewed organisation and includes more than 70 members led by the authors. In this article, the current activities of IP005 are introduced and some of the objectives for new machine vision applications especially in NDT are discussed. Topics presented in recent meetings are introduced in section I, while sections 2 and 3 deal with special working groups for automatic weld inspection and welding via image processing and for new NDI applications such as food inspection.

关键词： Nondestructive Testing Automatic welding Welding robot vision Food inspection Research Committees image processing

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：