检索结果-内蒙古大学图书馆

您好，读者！请登录

内蒙古大学图书馆

首页
概况
党建
资源
服务
科研支持
- 论文收录引用证明
- 科技查新
知识产权
档案馆
帮助

咨询与建议

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

您的常用邮箱：*

您的手机号码：*

问题描述：

当前已输入0个字，您还可以输入200个字

全部搜索
期刊论文
图书
学位论文
标准
纸本馆藏
外文资源发现
数据库导航
超星发现

高级检索

时间限定

出版年份：

文献类型

图书期刊文献学位论文多媒体

馆藏选择

电子馆藏纸本馆藏

核心期刊

全部期刊 SCI 收录期刊 SSCI 收录期刊 EI 收录期刊 CSCD 收录期刊 CSSCI 收录期刊

语言

中文英文

文献类型

期刊文献图书学位论文标准纸本馆藏

帮助

文字说明：

T=题名（书名、题名），A=作者（责任者），K=主题词，P=出版物名称，PU=出版社名称，O=机构（作者单位、学位授予单位、专利申请人），L=中图分类号，C=学科分类号，U=全部字段，Y=年（出版发行年、学位年度、标准发布年）

检索规则说明：

AND代表“并且”；OR代表“或者”；NOT代表“不包含”；(注意必须大写,运算符两边需空一格)

检索范例：

范例一：(K=图书馆学 OR K=情报学) AND A=范并思 AND Y=1982-2016
范例二：P=计算机应用与软件 AND (U=C++ OR U=Basic) NOT K=Visual AND Y=2011-2016

分类表

所选分类

>> <<

限定检索结果

文献类型

10,884 篇 会议
408 册 图书
211 篇 期刊文献

馆藏范围

11,503 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

6,668 篇 工学
- 4,897 篇 计算机科学与技术...
- 2,591 篇 软件工程
- 1,624 篇 电气工程
- 1,440 篇 光学工程
- 1,106 篇 控制科学与工程
- 1,006 篇 信息与通信工程
- 859 篇 机械工程
- 428 篇 生物工程
- 383 篇 电子科学与技术（可...
- 349 篇 材料科学与工程（可...
- 330 篇 生物医学工程（可授...
- 320 篇 仪器科学与技术
- 210 篇 化学工程与技术
- 160 篇 交通运输工程
- 151 篇 安全科学与工程
- 103 篇 土木工程
- 85 篇 农业工程
3,014 篇 理学
- 2,354 篇 物理学
- 718 篇 数学
- 470 篇 生物学
- 202 篇 统计学（可授理学、...
- 194 篇 化学
- 93 篇 系统科学
1,203 篇 医学
- 1,144 篇 临床医学
- 146 篇 基础医学(可授医学...
- 102 篇 药学(可授医学、理...
838 篇 管理学
- 594 篇 管理科学与工程(可...
- 272 篇 图书情报与档案管...
- 123 篇 工商管理
177 篇 农学
- 163 篇 作物学
52 篇 法学
51 篇 经济学
50 篇 教育学
28 篇 文学
16 篇 艺术学
10 篇 军事学

主题

2,564 篇 machine vision
2,106 篇 image processing
1,895 篇 computer vision
928 篇 image segmentati...
804 篇 feature extracti...
790 篇 machine learning
581 篇 cameras
461 篇 deep learning
396 篇 image edge detec...
332 篇 pattern recognit...
330 篇 object detection
321 篇 computational mo...
277 篇 support vector m...
264 篇 accuracy
253 篇 neural networks
238 篇 training
236 篇 visualization
228 篇 image recognitio...
204 篇 image color anal...
201 篇 pixel

机构

31 篇 university of no...
31 篇 university of ox...
29 篇 graz university ...
29 篇 university of fr...
26 篇 istituto italian...
24 篇 google deepmind ...
24 篇 meta ai barcelon...
23 篇 politecnico di t...
20 篇 university of sc...
19 篇 center for machi...
17 篇 center for machi...
15 篇 tsinghua univers...
14 篇 university of ch...
13 篇 itmo univ st pet...
13 篇 department of el...
12 篇 harbin institute...
10 篇 shanghai jiao to...
10 篇 school of mechat...
10 篇 tongji universit...
10 篇 institute of aut...

作者

31 篇 andrea vedaldi
31 篇 horst bischof
30 篇 jan-michael frah...
30 篇 thomas brox
24 篇 cristian canton
24 篇 alessio del bue
24 篇 tatiana tommasi
19 篇 de-shuang huang
17 篇 ghassemian hassa...
15 篇 hassan ghassemia...
13 篇 abdenour hadid
12 篇 soltanian-zadeh ...
11 篇 miller jwv
11 篇 bryan scotney
11 篇 wang wei
10 篇 lensu lasse
10 篇 paul f. whelan
10 篇 hong liu
10 篇 voronin viachesl...
10 篇 maryam imani

语言

11,182 篇 英文
245 篇 其他
85 篇 中文
9 篇 土耳其文
2 篇 俄文
1 篇 西班牙文
1 篇 法文

检索条件"任意字段=Iranian Conference on Machine Vision and Image Processing"

共 11503 条记录，以下是461-470 订阅

全选清除本页清除全部题录导出标记到"检索档案"

详细简洁

排序：

Research on PCB Solder Joint Defect Detection Method Based on machine vision 14

Research on PCB Solder Joint Defect Detection Method Based o...

引用

14th International conference on Graphics and image processing (ICGIP)

作者： Chang, Yuanpei Xue, Ying Zhang, Yu Ma, Jiajun Li, Guangjie Wu, Dandan Zhan, Qiang Zuo, Jiancun Shanghai Polytechn Univ Coll Comp & Informat Engn Shanghai 201209 Peoples R China

ISBN: (纸本)9781510666313;9781510666320

Printed circuit boards (PCBs) are an essential component of electronic products, and detecting solder joint defects is critical in the PCB production process. machine vision technology allows detection with high efficiency and cost-effectiveness. Therefore, this paper summarizes the basic principles of image processing-based and machine learning-based methods for defect detection and compares the advantages and disadvantages of both methods with relevant performance evaluation indicators. Finally, this paper contains a summary and an outlook.

关键词： PCB solder joints defect detection machine vision machine learning

来源：评论

学校读者我要写书评

暂无评论

Robotic machine vision system for defective screw Identification using Fisher's LDA Techniques 3

Robotic machine vision system for defective screw Identifica...

引用

3rd International conference on Artificial Intelligence and Signal processing, AISP 2023

作者： Sahoo, Santosh Kumar Godi, Rakesh Kumar Department of Electronics and Instrumentation Engineering Hyderabad India Department of Information Technology Hyderabad India

ISBN: (纸本)9798350320749

The research work dedicated for the object identification difficulty resolved by the techniques of principal component analysis (PCA) and linear discriminant analysis (LDA) along with robotic machine vision system. The effectiveness of the proposed model is carefully considered for a case when the pictures of an object like Screw have not initially processed but managed them into a standard form in terms of back-ground, scaling, positioning and adjustment of intensity or brightness. Similarly, when processed a huge amount of image data sets it is necessary to use PCA and LDA for optimizing the computational difficulty. Here using the LDA and PCI the effectiveness of the model is analyzed. By an introducing the robotic machine vision system the identification accuracy can be enhanced to a greater label. © 2023 IEEE.

关键词： Principal component analysis

来源：评论

学校读者我要写书评

暂无评论

machine vision based automated inspection approach for clutch friction disc (CFD)

Machine vision based automated inspection approach for clutc...

引用

International conference on Advances in Materials and Mechanical Engineering. (ICAMME)

作者： Kaushik, Sujata Jain, Anjali Chaudhary, Tina Chauhan, N. R. IGDTUW MAE Dept Delhi 110035 India

machine vision is a technology and method used to provide automated image-driven analysis in applications such as inspection, process control, and guidance, and is very popular in industries nowadays. Computer/machine vision has been extensively developed and used in production to achieve precise automatic control. This paper presented an image processing approach, a subset of machine vision, for the visual inspection system of the Clutch Friction Disc (CFD) produced for 2 wheelers. image processing is used to inspect different parts of the CFD. After previous operations of production, a part enters the inspection system, where the geometry and size of the part are inspected, and then image processing technology is used to decide to accept or reject the product. This paper presented the work constructed using a python program with OpenCV which aims to identify the major defects in clutch friction plates, by using different image processing techniques. With the proposed approach decision can be made automatically that whether the processed part will be accepted or rejected and then will be identified as "Ok tested" and "Faulty" pieces. Copyright (C) 2022 Elsevier Ltd. All rights reserved.

关键词： machine vision Automated inspection image processing Python OpenCV Clutch friction plates (CFD)

来源：评论

学校读者我要写书评

暂无评论

Why are Visually-Grounded Language Models Bad at image Classification? 38

Why are Visually-Grounded Language Models Bad at Image Class...

引用

38th conference on Neural Information processing Systems, NeurIPS 2024

作者： Zhang, Yuhui Unell, Alyssa Wang, Xiaohan Ghosh, Dhruba Su, Yuchang Schmidt, Ludwig Yeung-Levy, Serena Stanford University United States University of Washington United States Tsinghua University China

image classification is one of the most fundamental capabilities of machine vision intelligence. In this work, we revisit the image classification task using visually-grounded language models (VLMs) such as GPT-4V and LLaVA. We find that existing proprietary and public VLMs, despite often using CLIP as a vision encoder and having many more parameters, significantly underperform CLIP on standard image classification benchmarks like imageNet. To understand the reason, we explore several hypotheses concerning the inference algorithms, training objectives, and data processing in VLMs. Our analysis reveals that the primary cause is data-related: critical information for image classification is encoded in the VLM's latent space but can only be effectively decoded with enough training data. Specifically, there is a strong correlation between the frequency of class exposure during VLM training and instruction-tuning and the VLM's performance in those classes;when trained with sufficient data, VLMs can match the accuracy of state-of-the-art classification models. Based on these findings, we enhance a VLM by integrating classification-focused datasets into its training, and demonstrate that the enhanced classification performance of the VLM transfers to its general capabilities, resulting in an improvement of 11.8% on the newly collected imageWikiQA dataset. © 2024 Neural information processing systems foundation. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Paired medical image enhancement for improved diagnosis of intracranial hemorrhage

Paired medical image enhancement for improved diagnosis of i...

引用

2023 International conference on machine vision, image processing and Imaging Technology, MVIPIT 2023

作者： Song, Huanxin Zhang, Xiufeng Xie, Yuxi Minzu University School of Science Dalian Dalian China Dalian Minzu University School of Mechanical Electronical and Engineering Dalian China

ISBN: (纸本)9798350306545

In this paper, an approach is presented for enhancing medical images using conditional generative adversarial networks. The generator employs the Nested U-Net Architecture (UNet++) in conjunction with the Global Attention Mechanism (GAM), while the discriminator is trained using patchGAN to discriminate. A comprehensive objective function is developed to supervise adversarial training, evaluating image quality based on overall likeness, content of the image, local texture, and stylistic elements. Additionally, a dataset named 'Computed Tomography images for Intracranial Hemorrhage Detection and Segmentation (CTIIHDS)' is introduced. To facilitate model training, reference images are generated and paired with the dataset, referred to as CTIIHDS2. The study also encompasses ablation experiments, comparison experiments, and segmentation experiments, which validate the model's capability to enhance medical images through paired data training. Significantly, the improved images contribute to the standard model's performance in medical image segmentation. The findings highlight the method's suitability for preprocessing intracranial hemorrhage detection and segmentation. © 2023 IEEE.

关键词： image enhancement

来源：评论

学校读者我要写书评

暂无评论

Improved Randomized Hough Transform Based on Circular Power Theory 2

Improved Randomized Hough Transform Based on Circular Power ...

引用

2nd International conference on image processing, Computer vision and machine Learning, ICICML 2023

作者： Zhou, Qinbang Zhang, Kezhi Zhang, Zhaoliang Yu, Hui Commercial Aircraft Corporation of China Ltd ShangHai Aircraft Design and Research Institute Shanghai China

ISBN: (纸本)9798350331417

Circle extraction is a fundamental task in computer vision, which is widely applied in automated inspection and assembly. However, existing circle detection algorithms often exhibit limitations in terms of noise resistance and computation speed. This paper addresses these challenges by proposing a novel approach to circle detection, which is based on a clustering and fitting method in the context of computer vision assignments. The main objective of this research is to enhance the performance of the Randomized Hough Transform, a widely used technique for circle detection. To achieve this, the proposed method leverages the concept of circular power theory to identify potential circles and mitigate the accumulation of invalid cells associated with multiple circles. By selecting circles in which three points align on the same circle, the proposed method effectively reduces the accumulation of invalid cells during the random sampling process. Experimental results demonstrate the improved robustness and computational accuracy of the proposed circle detection method on both synthetic data and real-world images. © 2023 IEEE.

关键词： circle detection computer vision randomized hough transform

来源：评论

学校读者我要写书评

暂无评论

Revisiting the Role of Language Priors in vision-Language Models 41

Revisiting the Role of Language Priors in Vision-Language Mo...

引用

41st International conference on machine Learning, ICML 2024

作者： Lin, Zhiqiu Chen, Xinyue Pathak, Deepak Zhang, Pengchuan Ramanan, Deva CMU United States Meta United States

vision-language models (VLMs) are impactful in part because they can be applied to a variety of visual understanding tasks in a zero-shot fashion, without any fine-tuning. We study generative VLMs that are trained for next-word generation given an image. We explore their zero-shot performance on the illustrative task of image-text retrieval across nine popular vision-language benchmarks. Our first observation is that they can be repurposed for discriminative tasks (such as image-text retrieval) by simply computing the match score of generating a particular text string given an image. We call this probabilistic score the Visual Generative Pre-Training Score (VisualGPTScore). While the VisualGPTScore produces near-perfect accuracy on some retrieval benchmarks, it yields poor accuracy on others. We analyze this behavior through a probabilistic lens, pointing out that some benchmarks inadvertently capture unnatural language distributions by creating adversarial but unlikely text captions. In fact, we demonstrate that even a "blind" language model that ignores any image evidence can sometimes outperform all prior art, reminiscent of similar challenges faced by the visual-question answering (VQA) community many years ago. We derive a probabilistic post-processing scheme that controls for the amount of linguistic bias in generative VLMs at test time without having to retrain or fine-tune the model. We show that the VisualGPTScore, when appropriately debiased, is a strong zero-shot baseline for vision-language understanding, oftentimes producing state-of-the-art accuracy. Copyright 2024 by the author(s)

关键词： Visual languages

来源：评论

学校读者我要写书评

暂无评论

Object Tracking Robot Using SIFT Based Computer vision 1

Object Tracking Robot Using SIFT Based Computer Vision

引用

1st IEEE International conference on Electronics, Computing, Communication and Control Technology, ICECCC 2024

作者： Deepak Kamath, K. Rizvi, Dabir Hasan Adarsh, U. Karthik, B. Elumalai, R. CMR Institute of Technology Dept. of ECE Bengaluru India

ISBN: (纸本)9798350371802

Latterly, we have seen an immense increase in the amount of research, development and investment dedicated to the field of Autonomous Vehicle Technology or in common terms - Self-Driving Vehicles. While modern autonomous vehicles commonly use machine and Deep Learning models using data from sensors to understand the environment and move autonomously, this project demonstrates the use of a digital image processing algorithm- SIFT, to enable a robot to track specific objects in an environment and follow them. The implementation of an efficient and innovative image tracking algorithm for autonomous vehicles is the most important outcome of this work. This paper mentions a few use cases of this work along with the potential and future scope of it. © 2024 IEEE.

关键词： Computer vision

来源：评论

学校读者我要写书评

暂无评论

Cross-Domain Few-Shot Incremental Learning for Point-Cloud Recognition

Cross-Domain Few-Shot Incremental Learning for Point-Cloud R...

引用

IEEE/CVF Winter conference on Applications of Computer vision (WACV)

作者： Tan, Yuwen Xiang, Xiang Huazhong Univ Sci & Technol Key Lab Image Proc & Intelligent Control Minist Educ Sch Artificial Intelligence & Automat Wuhan 430074 Peoples R China

ISBN: (纸本)9798350318920;9798350318937

Sensing 3D objects is critical when 2D object recognition is not accessible. A robot pre-trained on a large point-cloud dataset will encounter unseen classes of 3D objects after deploying it. Therefore, the robot should be able to learn continuously in real-world scenarios. Few-shot class-incremental learning (FSCIL) requires the model to learn from few-shot new examples continually and not forget past classes. However, there is an implicit but strong assumption in the FSCIL that the distribution of the base and incremental classes is the same. In this paper, we focus on cross-domain FSCIL for point-cloud recognition. We decompose the catastrophic forgetting into base class forgetting and incremental class forgetting and alleviate them separately. We utilize the base model to discriminate base samples and new samples by treating base samples as in-distribution samples, and new objects as out-of-distribution samples. We retain the base model to avoid catastrophic forgetting of base classes and train an extra domain-specific module for all new samples to adapt to new classes. At inference, we first discriminate whether the sample belongs to the base class or the new class. Once classified at the model level, test samples are then passed to the corresponding model for class-level classification. To better mitigate the forgetting of new classes, we adopt the soft label and hard label replay together. Extensive experiments on synthetic-to-real incremental 3D datasets show that our proposed method can balance the performance between the base and new objects and outperforms the previous state-of-the-art methods.

关键词： 3D computer vision Algorithms Algorithms Algorithms and algorithms formulations image recognition and understanding machine learning architectures

来源：评论

学校读者我要写书评

暂无评论

An Improved Cell nuclei Segmentation Method Based on U-Net++

An Improved Cell nuclei Segmentation Method Based on U-Net++

引用

2023 International conference on machine vision, image processing and Imaging Technology, MVIPIT 2023

作者： Wu, Zhaohe Wen, Zhengzhu Chen, Yaqian Peng, Xiaoju Li, Zechen Yanbian University College of Engineering Yanji China Yanbian University College of Geography and Ocean Sciences Yanji China

ISBN: (纸本)9798350306545

Segmentation of nuclei plays a crucial role in the field of medical image processing, particularly in the identification and examination of diseasesAlthough the U-Net ++ has shown good results in this task, there are still some limitations, and further improvement is needed to improve its segmentation accuracy. In this study, we investigate the limitations of U-Net++ and propose an enhanced model that incorporates the CBAM attention mechanism and BasicBlock residual block into the original U-Net++ *** CBAM attention mechanism enables adaptive adjustment of both channel and spatial dimensions of the feature map, while the BasicBlock residual block effectively addresses the issues of gradient vanishing and challenging model training in deep *** validate the efficacy of the enhanced U-Net++ model, we experimented on a publicly available DSB2018 nucleus dataset. The experimental results demonstrate that the enhanced U-Net++ model achieves a 0.75 % increase in IOU and a 2.13 % improvement in the DICE similarity coefficient, indicating superior performance compared to the original model. © 2023 IEEE.

关键词： image enhancement

来源：评论

学校读者我要写书评

暂无评论

没有更多数据了...

全选清除本页清除全部题录导出标记到“检索档案”

共500页 << < 43 44 45 46 47 48 49 50 51 52 > >>

检索报告对象比较合并检索0

隐藏清空

合并搜索

回到顶部

执行限定条件

内容：

评分：

请选择保存的检索档案：

请选择收藏分类：

订阅名称：

通借通还

温馨提示：

图书名称：

借书校区：

取书校区：

手机号码：

邮箱地址：

一卡通帐号：

电话和邮箱必须正确填写，我们会与您联系确认。

联系人：

所在院系：

联系邮箱：

联系电话：

内蒙古自治区呼和浩特市赛罕区大学西街235号邮编: 010021

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：