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

1,620 篇 会议
14 册 图书
12 篇 期刊文献

馆藏范围

1,646 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

1,160 篇 工学
- 888 篇 计算机科学与技术...
- 587 篇 软件工程
- 313 篇 光学工程
- 270 篇 信息与通信工程
- 258 篇 电气工程
- 174 篇 生物工程
- 146 篇 控制科学与工程
- 119 篇 机械工程
- 107 篇 生物医学工程（可授...
- 56 篇 电子科学与技术（可...
- 48 篇 材料科学与工程（可...
- 48 篇 化学工程与技术
- 47 篇 安全科学与工程
- 37 篇 仪器科学与技术
- 35 篇 交通运输工程
- 23 篇 建筑学
- 23 篇 网络空间安全
543 篇 理学
- 340 篇 物理学
- 194 篇 数学
- 175 篇 生物学
- 57 篇 化学
- 57 篇 统计学（可授理学、...
206 篇 医学
- 195 篇 临床医学
- 60 篇 基础医学(可授医学...
- 45 篇 药学(可授医学、理...
- 23 篇 公共卫生与预防医...
172 篇 管理学
- 96 篇 管理科学与工程(可...
- 78 篇 图书情报与档案管...
- 31 篇 工商管理
28 篇 农学
- 28 篇 作物学
19 篇 法学
17 篇 经济学
7 篇 教育学
5 篇 军事学
1 篇 文学

主题

307 篇 computer vision
228 篇 image processing
102 篇 image segmentati...
92 篇 feature extracti...
70 篇 deep learning
50 篇 object detection
42 篇 cameras
39 篇 image edge detec...
35 篇 convolutional ne...
34 篇 visualization
34 篇 image recognitio...
32 篇 machine learning
32 篇 image reconstruc...
31 篇 neural networks
30 篇 image color anal...
28 篇 computational mo...
28 篇 shape
28 篇 training
26 篇 image analysis
25 篇 face recognition

机构

6 篇 university of ch...
5 篇 comput & inf sci...
5 篇 department of co...
4 篇 chitkara univers...
4 篇 image processing...
4 篇 beijing institut...
4 篇 college of compu...
3 篇 shanghai jiao to...
3 篇 dept of electr &...
3 篇 south china univ...
3 篇 inria sophia-ant...
3 篇 school of comput...
3 篇 department of ma...
3 篇 shenyang institu...
3 篇 department of co...
3 篇 school of electr...
3 篇 school of comput...
3 篇 college of compu...
3 篇 dept of control ...
3 篇 department of in...

作者

6 篇 andayani u.
5 篇 syahputra m.f.
5 篇 mohana
5 篇 siregar b.
4 篇 yang yang
4 篇 hassan ghassemia...
4 篇 li hui
4 篇 shohreh kasaei
4 篇 e.j. delp
3 篇 luo haibo
3 篇 paul joseph sure...
3 篇 wang wei
3 篇 wang qian
3 篇 ying liu
3 篇 maryam imani
3 篇 saurav sumeet
3 篇 weickert joachim
3 篇 muchtar m.a.
3 篇 xin wang
3 篇 aggarwal j.k.

语言

1,615 篇 英文
25 篇 其他
9 篇 中文
1 篇 德文
1 篇 土耳其文

检索条件"任意字段=3rd International Conference on Computer Vision and Image Processing, CVIP 2018"

共 1646 条记录，以下是301-310 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：

Performance analysis of saliency detection in images

Performance analysis of saliency detection in images

引用

3rd international conference on Advancement in Nanoelectronics and Communication Technologies (ICANCT)

作者： Reddy, Maram Sreerama Nithya, B. Natl Inst Technol Comp Sci & Engn Dept Trichy 620015 Tamil Nadu India

Detecting salient objects in an image has a vast number of applications across the web, and mostly it is done manually. Since the internet is growing faster than ever, it is not a feasible solution for high-scale dynamic applications. Hence, image processing automation with computer vision and machine learning has become a burning topic of research in the past few years. Saliency based image cropping is a task of identifying the notable segments in an image and be able to accommodate these parts in the crop ratio for any given specific viewport. It helps not only in image cropping but also with object recognition, visual tracking and visual restoration, etc. To address this, a novel approach for saliency detection is proposed based on heat map analysis and boundary prior. In this approach, the images go through heat map anal-ysis to identify salient objects based on machine learning model. After that, the images are segmented based on color and texture difference and then major contours are identified. The contours and the obtained saliency coordinates are accommodated inside the crop for each viewport requirement. The crop coordinates then go through two more processes, firstly a shift center process where the crop center is moved towards the important but lesser salient object, and then an inclusivity rule checks that the image is not cropped at coordinates without any salient objects. The simulation results reveal that the proposed algorithm attains better results than the cutting-edge algorithm of Twitter with similarity index of 89.89%.(c) 2022 Elsevier Ltd. All rights *** and peer-review under responsibility of the scientific committee of the 3rd international Con-ference on "Advancement in Nanoelectronics and Communication Technologies".

关键词： Saliency detection image processing Viewport Heat map Inclusivity rule Similarity index

来源：评论

学校读者我要写书评

暂无评论

Integrating computer vision and Crowd Sourcing to Infer Drug Use on Streets: A Case Study with 311 Data in San Francisco 3rd

Integrating Computer Vision and Crowd Sourcing to Infer Dr...

引用

3rd international conference on Intelligent Edge processing in the IoT Era, Edge-IoT 2022, and the 4th international conference on Smart Governance for Sustainable Smart Cities, SmartGov 2022

作者： Yi, Hye Seon Bhuiyan, Tanvir Chellappan, Sriram University of South Florida TampaFL33620 United States

ISBN: (纸本)9783031359811

Use of illegal drugs has been a bane of society for decades, and the problem is only increasing globally. Billions of dollars, time, effort and expertise among various stakeholders are being invested to combat this problem, but novel approaches are still needed. In this paper, we investigate the exciting possibility of leveraging big-data provided by the crowd to detect illegal drug use on streets. Our discussions with stakeholders revealed that drug use can be inferred via detection of any of the following components - syringes (including barrels and plungers), needles, needle caps, vials and tourniquets. We also learnt that in localities, where drug is common, these items are casually discarded on streets. Motivated by these, we conducted an investigation centered around San Francisco. We collected images from their SF311 platform where the public can actually upload their observations in the city for service. From more than 5 million images uploaded, we extracted 1, 759 images that contained one or more of drug use components mentioned above. We designed and validated state of the art computer vision techniques to both detect and localize components of interest with an uploaded image. Results demonstrate high utility, as we report later in the paper. To the best of our knowledge, our study is amongst the first to tackle the problem of detecting drug use automatically via AI techniques from crowd uploaded images. We believe that our study has practical impact. © 2023, ICST Institute for computer Sciences, Social Informatics and Telecommunications Engineering.

关键词： Needles

来源：评论

学校读者我要写书评

暂无评论

Cultural-Aware AI Model for Emotion Recognition

Cultural-Aware AI Model for Emotion Recognition

引用

Iranian Machine vision and image processing (MVIP)

作者： Mehrdad Baradaran Payam Zohari Abtin Mahyar Hossein Motamednia Dara Rahmati Saeid Gorgin Department of Computer and Data Sciences Shahid Beheshti University Tehran Iran Department of Computer Engineering Khaje Nasir University Of Technology Tehran Iran High Performance Computing Laboratory School of Computer Science Institute for Research in Fundamental Sciences Tehran Iran Faculty of Computer Science and Engineering Shahid Beheshti University Tehran Iran Department of Computer Engineering Chosun University Gwangju South Korea

Emotion AI is a research domain that aims to understand human emotions from visual or textual data. However, existing methods often ignore the influence of cultural diversity on emotional interpretation. In this paper, we propose a multimodal deep learning model that integrates cultural awareness into emotion recognition. Our model uses images as the primary data source and comments from individuals across different regions as the secondary data source. Our results show that our model achieves robust performance across various scenarios. Our contribution is to introduce a novel fusion approach that bridges cultural gaps and fosters a more nuanced understanding of emotions. Due to the best of our knowledge, few works are using this approach, for Emotion AI, combining different types of data sources and models. We evaluate our model on the ArtELingo dataset, which contains image-comment pairs with Chinese, Arabic, and English annotations. The experimental results in the evaluation phase demonstrate an impressive 80% recognition accuracy for the model that merges image-text features.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Linear and Non-Linear Filter-based Counter-Forensics Against image Splicing Detection 7th

Linear and Non-Linear Filter-based Counter-Forensics Against...

引用

7th international conference on computer vision and image processing, cvip 2022

作者： Das, Debjit Bhunia, Banalata Naskar, Ruchira Chakraborty, Rajat Subhra Department of Information Technology Indian Institute of Engineering Science and Technology West Bengal Shibpur Howrah711103 India Vellore Institute of Technology Tamil Nadu Vellore India Department of Computer Science and Engineering Indian Institute of Technology Kharagpur West Bengal Kharagpur721302 India

ISBN: (纸本)9783031314063

Digital images are widely used as primary sources of evidence in today’s world, spanning security, forensics, and legal domains. However, image tampering poses a shallow technical skill barrier with the wide availability of sophisticated, easy-to-use image manipulation software. Tampered images are often used intentionally for unlawful and malicious purposes. One of the most common forms of image manipulation attack is image splicing, which is performed by combining regions from multiple source images to synthesize an artificial image that looks natural. Digital forensic measures have been widely explored in the literature to detect such type of image forgery. However, the recent growth of counter-forensics poses a threat to such forensic/security measures. Forensic techniques can be easily deceived by adopting counter-forensic manipulation of forged images. In this work, we explore different linear and non-linear filtering-based counter-forensic modifications to digital images and hence investigate the after-effects of those, in terms of severity of such manipulations in rendering state-of-the-art forensic splicing detection methods useless. In this paper, we implement two forensic image splicing detection techniques based on feature extraction from image along with machine learning and deep CNN with transfer learning. Then, different filtering techniques have been applied to the image dataset, investigating their effectiveness as a counter-forensic attack against image splicing detection. Experimental results show that the Gaussian filter and Average filter are the two most effective counter-forensic filtering methods against image splicing detection, suggesting the need for further strengthening the existing family of forensic techniques. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2023.

关键词： Median filters

来源：评论

学校读者我要写书评

暂无评论

Facial Expression Recognition System 3rd

Facial Expression Recognition System

引用

3rd international conference on Smart Systems - Innovations in Computing (SSIC)

作者： Pokharel, Rahisha Kaur, Mandeep Rakesh, Nitin Nand, Parma Sharda Univ Dept Comp Sci & Engn Greater Noida Uttar Pradesh India

ISBN: (纸本)9789811628771;9789811628764

A significant subject in the field of computer vision and artificial intelligence is outward appearance acknowledgment. There are two mode of correspondence one is verbal, and another is non-verbal [Xiaoxi, M., Weisi, L.: Facial emotion recognition. In: IEEE 2nd international conference on Signal and image processing (2017)]. Among verbal and non-verbal methods for correspondence, outward appearance is non-verbal methods for correspondence. Outward appearance assumes a crucial job which encourages human to communicate their feelings, express their emotions, psychological wellness, viewpoint, and so on [Kaur, M., Vashisht, R.: Comparative study of facial expression recognition techniques. Int. J. Comput. Appl. (2011)]. Understanding gets simpler when human and computer interact with each other if computer can react to non-verbal correspondence of human which is only feelings communicated. In this paper, a calculation is introduced for object discovery dependent on Viola-Jones algorithm. In this paper, there are introduced the consequences of acknowledgment of seven emotion states (neutral, happy, sad, fear, disgust, fear, surprised) in view of outward appearances. The grouping of the highlights was performed utilizing managed learning strategy, i.e., convolutional neural network (CNN).

关键词： CNN computer vision Emotion recognition Facial expression image Viola–Jones algorithm

来源：评论

学校读者我要写书评

暂无评论

An Improved U-Net image Segmentation Network for Crankshaft Surface Defect Detection

An Improved U-Net Image Segmentation Network for Crankshaft ...

引用

Iranian Machine vision and image processing (MVIP)

作者： Ashkan Moosavian Elmira Bagheri Alireza Yazdanijoo Amir Hossein Barshooi Department of Agricultural Engineering Technical and Vocational University (TVU) Tehran Iran School of Automotive Engineering Iran University of Science and Technology (IUST) Tehran Iran Irankhodro Powertrain Company (IPCo) Tehran Iran

Crankshaft is one of the mechanical components of the vehicle engine, and quality control of it holds significant importance in the production line. In this paper, a vision-based system was developed to detect apparent structural defects on the crankshaft surface. By examining the different approaches in computer vision tasks, the semantic segmentation technique was chosen to solve this problem. In the first stage, a dataset consisting of 400 crankshaft experimental images with structural defects such as scratch, pitting, and grinding were collected. Then, the Convolutional Neural Network (CNN) with MobileNet architecture was trained to detect apparent defects, and an Intersection over Union (IoU) evaluation criteria of 64.7% was obtained. In the third stage, some image processing techniques were used to increase the performance. By applying the DexiNed edge detection filter on the train-set images, the IoU was increased by 8.4%. Considering the importance of this issue in the automotive industry, it has been tried again to boost the performance by augmenting the dataset images. On the other hand, this can also prevent overfitting of the model. By training the model under the same conditions as the previous stages, the IoU in this stage increased by 13.2% and reached 86.3%.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Real-time Multiple Analog Gauges Reader for an Autonomous Robot Application 17

Real-time Multiple Analog Gauges Reader for an Autonomous Ro...

引用

17th international Joint Symposium on Artificial Intelligence and Natural Language processing (iSAI-NLP) / 3rd international conference on Artificial Intelligence and Internet of Things (AIoT)

作者： Trairattanapa, Visarut Phimsiri, Sasin Utintu, Chaitat Cherdchusakulcha, Riu Tosawadi, Teepakorn Thamwiwatthana, Ek Tungjitnob, Suchat Tangamonsiri, Peemapol Takutruea, Aphisit Keomeesuan, Apirat Jitnaknan, Tanapoom Suttichaya, Vasin Al & Robot Ventures Co Ltd Bangkok Thailand

ISBN: (数字)9781665457279

ISBN: (纸本)9781665457279

With the development of robotic technology, autonomous robots have been extended to production industries to substitute manual tasks like routine operations. In the general manufacturer, analog gauges are the most commonly utilized and required operators for manual reading. Accordingly, an analog gauge reading can be considered a fundamental feature for the operator robots to be fully automated for inspection purposes. This paper presents the methods for reading multiple analog gauges automatically using a camera. The processing pipeline consists of two main stages: 1) gauge detector for extracting individual gauges and 2) gauge reader for estimating gauge values. For gauge detectors, we propose three different YOLOv5 architecture sizes. The gauge readers are mainly categorized into computer-vision approach (CV), and deep learning regression approaches. The deep learning approaches consist of two CNN-based backbones, ResNet50 and EfficientNetV2B0, and one transformer-based SwinTransformer. Finally, we introduce the feasibility of the combination of each gauge detector and reader. As a result, the YOLOv5m detector with EfficientNetV2B0 CNN backbone reader theoretically achieves the best performance but is not practical for industrial applications. In contrast, we introduce the YOLOv5m detector with the CV method as the most robust multiple gauge reader. As a result, it reaches the comparative performances to the EfficientNetV2B0 backbone and is more compatible with robotic applications.

关键词： Analog Gauge Reader computer vision image processing Object Detection image Regression

来源：评论

学校读者我要写书评

暂无评论

Classification of Skin Lesions using Deep Learning Models with Transfer Learning Techniques 3

Classification of Skin Lesions using Deep Learning Models wi...

引用

3rd IEEE international conference on Recent Advances in Systems Science and Engineering, RASSE 2023

作者： Mekala, Paparao Surendiran, B. Vishnu, G. Jaideep Sai, G. Subash, P. NIT Puducherry Department of Computer Science and Engineering Puducherry609609 India

ISBN: (纸本)9798350341676

One of the most powerful strategies for improving skin cancer patient's chances of survival is finding the disease at its earliest possible stage for diagnosis. It is an essential step to find out the type of cancer in order to ensure efficient treatment machine learning and deep learning have seen explosive growth in the past few years, particularly for the detection and categorization of even the deadliest diseases such as cancer. The use of deep convolutional neural networks (DCNN) has also increased significantly due to their revolutionary impact on computer vision and medical image processing. In this work, we are using three different Deep learning models for skin lesions classification. The main goal of this work is to classify skin lesions in RGB images using deep learning methods such as Densely connected Convolutional Neural Networks, Residual Neural Networks, and Convolutional Neural Networks. The existing methods are costly and time-consuming. This has been a problem for many patients who are in need of critical medical attention. But, due to the emergence of deep learning techniques, this problem could be overcome at a better cost than naive methods. This project aims to Classify an image using Neural networks. image pre-processing is done on an image. After implementing three different deep learning models to classify the skin lesions from the images, we select the most accurate model and use it moving forward. The model classifies the skin lesion type from the test case images and will come to know which type of skin cancer the patient is suffering from. These kinds of use cases are closely related to the training data. Generalizability can be achieved by carefully picking the right data, collecting more of such data, and using it for training. © 2023 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

An Efficient Face Recognition Method Based on CNN

An Efficient Face Recognition Method Based on CNN

引用

Power Electronics, computer Applications (ICPECA), IEEE international conference on

作者： Xiu He Feng Ding Guangzhou Xinhua University Guangzhou China

As a prevailing research in artificial intelligence, the application of computer vision is widely used in many fields which are closely related to people's livelihood, such as industrial automation, new retail industry, smart transportation and security monitoring. And the proposed face recognition method is a branch in the field of computer vision, it integrates neural networks, biology, image signal processing, machine learning and other fields, which promote research and cross-development among different disciplines. Hence, this paper focuses on face recognition method by using convolutional neural network(CNN), and CNN has the property of "weight sharing", which has been widely popularized in image recognition, it can greatly simplify the work of large-scale network training. The experiments demonstrate that the proposed face recognition method is successful, and the accuracy of the proposed method can be as high as 98%.

关键词： Training computer vision image recognition image color analysis Face recognition Color Signal processing

来源：评论

学校读者我要写书评

暂无评论

A point cloud registration method based on improved beetle antennae search algorithm and ICP 3

A point cloud registration method based on improved beetle a...

引用

3rd international conference on Machine Learning and computer Application, ICMLCA 2022

作者： Wang, Hua Han, Yi-Fei Zhang, Shuang Zhu, Guo-Kai Changchun University of Science and Technology Changchun China Changchun Institute of Technology Changchun China

ISBN: (纸本)9781510664814

Since a single stereo vision sensor cannot completely represent the whole picture of the object, it is necessary to use point cloud registration to realize the whole construction of the object, so as to help the robot complete subsequent operations according to the point cloud information of the complete object. Aiming at the defects of the ICP algorithm in the traditional point cloud registration algorithm, which takes a long time and requires a high initial pose of the point cloud, a point cloud registration method based on improved beetle antennae search algorithm and ICP is proposed. In this method, the initial point cloud pair to be registered is preprocessed by subsampling, etc., and then the application of Moth-flame optimization algorithm to the population is used for reference in rough registration to improve the beetle antennae search algorithm, so that the point cloud pair has a better initial pose. Finally, the KD-TREE is introduced in the process of accurate registration to improve the ICP algorithm and achieve the final point cloud registration. The experimental simulation results show that compared with the traditional ICP algorithm, the registration accuracy of the proposed algorithm is improved by 64.1% on average, and the registration efficiency is improved by 82.0% on average, which effectively improves the ICP algorithm's low speed and accuracy in point cloud registration. © 2023 SPIE.

关键词： Stereo image processing

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165页 << < 27 28 29 30 31 32 33 34 35 36 > >>

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：