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

143 篇 会议
125 篇 期刊文献
3 篇 学位论文

馆藏范围

271 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

239 篇 工学
- 98 篇 计算机科学与技术...
- 77 篇 电气工程
- 39 篇 机械工程
- 35 篇 控制科学与工程
- 27 篇 仪器科学与技术
- 21 篇 信息与通信工程
- 17 篇 材料科学与工程（可...
- 16 篇 生物医学工程（可授...
- 14 篇 测绘科学与技术
- 13 篇 软件工程
- 9 篇 土木工程
- 7 篇 环境科学与工程（可...
- 6 篇 农业工程
- 5 篇 电子科学与技术（可...
- 5 篇 石油与天然气工程
- 4 篇 建筑学
- 4 篇 化学工程与技术
60 篇 理学
- 22 篇 物理学
- 12 篇 生物学
- 11 篇 化学
- 11 篇 地球物理学
- 4 篇 地质学
- 4 篇 系统科学
49 篇 医学
- 39 篇 临床医学
- 11 篇 特种医学
- 10 篇 基础医学(可授医学...
- 6 篇 中西医结合
- 5 篇 医学技术（可授医学...
14 篇 农学
- 6 篇 作物学
13 篇 管理学
- 12 篇 管理科学与工程(可...
4 篇 艺术学
1 篇 教育学
1 篇 文学

主题

271 篇 watershed algori...
62 篇 image segmentati...
30 篇 segmentation
18 篇 image processing
15 篇 mathematical mor...
8 篇 region merging
8 篇 edge detection
7 篇 over-segmentatio...
7 篇 morphology
6 篇 distance transfo...
6 篇 feature extracti...
5 篇 deep learning
5 篇 mri
5 篇 image recognitio...
4 篇 region growing
4 篇 watersheds
4 篇 magnetic resonan...
4 篇 machine vision
4 篇 thresholding
4 篇 medical image pr...

机构

2 篇 sitac fairfax va...
2 篇 srm univ dept bi...
2 篇 zhejiang univ co...
2 篇 french space agc...
2 篇 dalian univ tech...
2 篇 addis ababa univ...
1 篇 univ bridgeport ...
1 篇 north china univ...
1 篇 shanxi agr univ ...
1 篇 cheongju univ de...
1 篇 shenyang aerosp ...
1 篇 univ brasilia de...
1 篇 aramco asia beij...
1 篇 univ sci & techn...
1 篇 guilin univ tech...
1 篇 univ sci & techn...
1 篇 wuhan univ sci &...
1 篇 chongqing univ c...
1 篇 amrita vishwa vi...
1 篇 school of electr...

作者

3 篇 cubero-castan e
3 篇 marthon p
3 篇 fjortoft r
2 篇 snekhalatha u.
2 篇 vanderlinden a
2 篇 li heng
2 篇 chakrabarti i
2 篇 vandyck d
2 篇 scheunders p
2 篇 jellison gp
2 篇 chen hao
2 篇 cui shi-gang
2 篇 wu xing-li
2 篇 mahanta a
2 篇 hui li
2 篇 zhang yong-li
2 篇 wilson dg
2 篇 sijbers j
2 篇 rambabu c
2 篇 jiao licheng

语言

258 篇 英文
8 篇 其他
2 篇 中文
1 篇 西班牙文
1 篇 土耳其文

检索条件"主题词=Watershed algorithm"

共 271 条记录，以下是201-210 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：

Automated Hand Radiograph Segmentation, Feature Extraction and Classification Using Feed Forward BPN Network in Assessment of Rheumatoid Arthritis 2nd

引用

2nd International Conference on Intelligent Computing and Applications (ICICA)

作者： Snekhalatha, U. Anburajan, M. SRM Univ Dept Biomed Engn Madras 603203 Tamil Nadu India

ISBN: (纸本)9789811016455;9789811016448

Rheumatoid arthritis is a chronic autoimmune disorder which affects the multiple joints especially small joints in hands and feet of both the sides of the body. Even though modern imaging techniques such as MRI, PET, SPECT, color Doppler ultrasound was used to quantify the inflammatory conditions of RA, radiograph was considered as the gold standard technique in evaluation of RA. The aim and objective of the study were given as follows (i) to perform an automated segmentation of hand from the radiograph using DTCWT based watershed algorithm;(ii) to compare the measured statistical features of the joint space of the hand using GLCM method, and (iii) to perform feed forward back propagation network for classification of subjects into RA and normal with high accuracy. The dual tree complex wavelet transform based watershed algorithm was found to be satisfactory in segmenting the hand automatically using the digitized radiograph. The feed forward BPN network was utilized for the classification of subjects into normal and RA patients from statistical features (total inputs, n = 45) extracted from hand X-ray image. The calculated accuracy of the classifier was found to be 95.7 %, whereas its sensitivity and specificity was found to be 88.2 and 98.1 % respectively. When both the statistical features as well as geometric features (total inputs, n = 53) were used in the feed forward BPN network, it was found that accuracy was 92.9 %, whereas its sensitivity and specificity were found to be 82.4 and 96.2 % respectively.

关键词： Dual tree complex wavelet transforms Feature extraction Feed forward back propagation network Rheumatoid arthritis watershed algorithm

来源：评论

学校读者我要写书评

暂无评论

NEW TENSORIAL MORPHOLOGICAL GRADIENTS IN DTI IMAGE SEGMENTATION algorithm 11

NEW TENSORIAL MORPHOLOGICAL GRADIENTS IN DTI IMAGE SEGMENTAT...

引用

11th International Computer Conference on Wavelet Active Media Technology and Information Processing (ICCWAMTIP)

作者： Lin, Tao Liu, Xiao-Yun Zhang, Xiang-Fen Ma, Yan Liu, Zhe-Xing SHNU Coll Informat Mech & Elect Engn Shanghai 200234 Peoples R China Southern Med Univ Inst Biomed Engn Guangzhou 510515 Guangdong Peoples R China

ISBN: (纸本)9781479972081

Calculating morphological gradient is the key step of watershed algorithm. In this article, new tensorial similarity morphological gradient is defined based on the eight neighborhoods, and new tensor anisotropy morphological gradients are put forward, which are then used in the watershed segmentation framework to segment DTI image. The results of the segmentation experiments on the corpus callosum show that: Compared to other tensor anisotropy morphological gradients based watershed segmentation methods, the one based on newly proposed tensor anisotropy morphological gradients can more quickly and accurately position and depict the segmentation outline of the image, which can also better protect the edge information of the important region.

关键词： Diffusion tensor imaging Morphological gradient Tensor similarity watershed algorithm Corpus callosum

来源：评论

学校读者我要写书评

暂无评论

Color Image Segmentation Techniques: A Survey 1st

Color Image Segmentation Techniques: A Survey

引用

1st International Conference on Microelectronics, Computing & Communication Systems (MCCS)

作者： Jain, Sneha Laxmi, Vijaya Birla Inst Technol Mesra Dept Elect & Elect Engn Ranchi Bihar India

ISBN: (纸本)9789811055652;9789811055645

In today's world, where digital image processing is becoming an essential part of technology, segmentation of images poses a challenging problem. Before any complex task that has to be done on images, segmentation is a prerequisite. Segmentation ensures the simplification of a problem by changing the representation of an image from a complex one to a more analytical and easier form. Pixels of segmented regions share common characteristics. Perfect segmentation is difficult to obtain. There exist many techniques which have been applied such as edge-based segmentation, region-based segmentation, morphological operations, thresholding and clustering methods. Segmentation has a crucial role in image analysis. The accuracy of segmentation determines the success or failure of computer algorithms. Therefore, there is a need to develop efficient and less time-consuming algorithms for segmentation. This paper summarizes a number of segmentation methods.

关键词： Clustering Edge maximization technique Segmentation Thresholding watershed algorithm

来源：评论

学校读者我要写书评

暂无评论

The monitoring population density of pests based on edge-enhancing diffusion filtering and image processing

引用

1st International Conference on Computer and Computing Technologies in Agriculture (CCTA 2007)

作者： Wang, Yuehuan Weng, Guirong Soochow Univ Sch Mech & Elect Engn Suzhou 215021 Peoples R China

ISBN: (纸本)9780387772523

As is known, agriculture is very important in China, but the problem about pests has hampered the further development of Chinese agriculture. Digital image-processing technology and mathematical morphology are referred to as the main research methods, and tiny pets like aphids among field are referred to as the research objects. Image processing technology such as edge-enhancing diffusion filtering, mathematical morphology and watershed segmentation algorithm is used to monitor pest population density, which greatly raises efficiency of pest data acquisition. After the segmentation of the image of the pests, the number of the insect individuals can be obtained from the background by using image processing technology. Computer image processing technology provides a possibility to solve this problem and becomes a very important direction to monitor regional pest population density.

关键词： digital image-processing monitoring population mathematical morphology watershed algorithm edge-enhancing filtering

来源：评论

学校读者我要写书评

暂无评论

Implementation of Gray-level Clustering algorithm for Image Segmentation

Implementation of Gray-level Clustering Algorithm for Image ...

引用

International Conference and Exhibition on Biometrics Technology

作者： Kavitha, A. R. Chellamuthu, C. Jerusalem Coll Engn Velachery Main Rd Madras 600100 Tamil Nadu India RMK Coll Engnyy Karaipettai India

The watershed algorithm is an important technique for image segmentation which converts the gray-level image to a segmented image. We propose a watershed algorithm based on the mean value, the standard deviation of the histogram and the PSNR within a sub-interval, a novel recursive algorithm for deriving clustered images that is also used to increase the quality of an image. The clustered images using the watershed algorithm produce close results to that of the original image. (C) 2010 Published by Elsevier Ltd

关键词： watershed algorithm Image processing clustering algorithm image segmentation histogram

来源：评论

学校读者我要写书评

暂无评论

The algorithm for Detecting Malfunctions by Means of the SURF Feature Points Based on Probability and Statistics 10

The Algorithm for Detecting Malfunctions by Means of the SUR...

引用

10th IEEE International Conference on Software Engineering and Service Science (ICSESS)

作者： Fan, WenTao Qiu, Kaijin Southwest Univ Coll Comp & Informat Sci Chongqing Peoples R China

ISBN: (纸本)9781728109459

The malfunctions detection of the high voltage electric wire mainly obtains the detection target image periodically by the drone and sends it back to the ground to compare the images to determine whether there is a failure. However, since the drone acquires images at different times in the sky, each time the image obtained is tilted, there is a certain difference in contrast and exposure, which seriously interferes with the detection of the fault. At present, image-based malfunction detection methods mainly include: methods based on image grayscale, shape and texture features, wavelet transform and image segmentation. These methods are complicated to operate and have long running time, which is difficult to meet the experimental requirements. We can detect the malfunctions by the distribution of the matching points of the image. The algorithm based on probability and statistics can reduce the effects of rotation, translation and noise during image processing. Dividing the image into blocks and calculating the number of image feature points to determine if there is a fault is simple and effective. Experimental results show that the algorithm can effectively detect whether the specified area is faulty.

关键词： image malfunction detection SURF algorithm watershed algorithm image feature point

来源：评论

学校读者我要写书评

暂无评论

An Integrated Target Recognition Method Based on Improved Faster-RCNN for Apple Detection, Counting, Localization, and Quality Estimation 4

An Integrated Target Recognition Method Based on Improved Fa...

引用

4th IEEE International Conference on Power, Electronics and Computer Applications, ICPECA 2024

作者： Yan, Zihao Zhang, Huishan Li, Liping School of Integrated Circuits Anhui University Hefei China College of Electronic Information Engineering Anhui University Hefei China

ISBN: (纸本)9798350359589

Aiming at the problems of the dense target distribution, poor positioning ability to pick robots, and inaccurate ripeness judgment in the picking orchard scene, this paper proposes an apple image recognition model with a high recognition rate, high speed, and high accuracy, which can effectively analyze the data of quantity, location, ripeness and quality estimation in the apple image. Firstly, the Faster R-CNN network is improved by introducing Efficient Channel Attention (ECA) and multi-scale fusion feature pyramid (FPN) for fruit detection and recognition localization. Then the distance transform-based watershed algorithm is used for image segmentation to fit the apple edge image while combining with the fitted circle determination algorithm to establish a mathematical model for apple volume estimation to calculate the quantity as well as the quality of apples. Finally, the apples are classified into four categories according to their ripeness, and the improved Faster R-CNN network is used to improve the ripeness detection effect, and the results show that the average fruit recognition accuracy of the improved method proposed in this paper is 95.42%, which significantly improves the accuracy of fruit detection. © 2024 IEEE.

关键词： Apple Counting Faster R-CNN Localization Maturity testing watershed algorithm

来源：评论

学校读者我要写书评

暂无评论

Cracks in Time: Analyzing Structural Deterioration in Ancient Monuments 3

Cracks in Time: Analyzing Structural Deterioration in Ancien...

引用

3rd IEEE International Conference on Mobile Networks and Wireless Communications, ICMNWC 2023

作者： Snehapriya, M. Umamageswari, A. SRM Institute of Science and Technology Department of Computer Science and Engineering Ramapuram Campus Chennai India

ISBN: (纸本)9798350317022

The preservation and analysis of ancient monuments, marked by the passage of time and structural deterioration, present a unique challenge in understanding the history embedded within their weathered surfaces. This research proposes a comprehensive approach to enhance the visual representation of these monuments by employing a combination of image processing techniques and advanced deep learning algorithms. The first component of methodology involves the application of Histogram Equalization, a classic image enhancement technique, to effectively boost contrast and reveal subtle details within the images of ancient monuments. This step aims to unveil the intricate patterns of structural deterioration caused by natural and anthropogenic factors. Following this, the watershed algorithm is employed to segment and identify distinct regions of interest within the images. By isolating cracks and damaged areas, this algorithm facilitates a more granular analysis of the structural decay, providing insights into the specific locations and extents of deterioration. To further refine the analysis and accommodate the intricacies of ancient monument imagery, this paper introduces the Fast R- CNN (Convolutional Neural Network) algorithm. This deep learning model is trained to recognize and classify different types of cracks and damages, offering a more nuanced understanding of the historical processes contributing to the structural decay of the monuments. By integrating these three approaches, the experimental result provides a holistic and detailed analysis of structural deterioration in ancient monuments with the accuracy of 95%. The combination of classical image processing techniques and cutting-edge deep learning algorithms offers a powerful toolset for researchers and conservationists seeking to unravel the mysteries hidden within the cracks of time. © 2023 IEEE.

关键词： Fast R-CNN Histogram Equalization Support Vector Machine watershed algorithm

来源：评论

学校读者我要写书评

暂无评论

Three-Dimensional Video Inpainting Using Gradient Fusion and Clustering 13

Three-Dimensional Video Inpainting Using Gradient Fusion and...

引用

13th International Conference on Natural Computation, Fuzzy Systems and Knowledge Discovery (ICNC-FSKD)

作者： Lai, Yili Tang, Xianghong Lou, Xingxin Hangzhou Dianzi Univ Sch Commun Engn Hangzhou Zhejiang Peoples R China

ISBN: (纸本)9781538621653

For the foreground and background segmentation in Three-Dimensional(3D) video inpainting, the inaccuracy of the foreground extraction will easily affect the quality of the repaired image. In order to solve this problem, this paper combines watershed algorithm with marker for foreground extraction, making full use of the structural information of the depth image. In order to enhance the ability of distinguishing the foreground object, introducing K -means clustering to mark it in the gradient image. The experimental results show that the improved algorithm overcomes the defect of original watershed algorithm in image segmentation, which is likely to occur the over segmentation phenomenon, and it also can completely extract the texture information of the foreground object, making the repaired image have better visual effect, and the peak signal-tonoise ratio(PSNR) is increased by 1 to 3 dB, compared to the other algorithm.

关键词： 3D video inpainting watershed algorithm the depth image K-means clustering marker Criminisi algorithm

来源：评论

学校读者我要写书评

暂无评论

Study on Coordinate Information Generation Method of Interested Area in IMRT Inverse Planning System

引用

International Conference on Materials Engineering for Advanced Technologies (ICMEAT2011)

作者： Chen, Zhen Li, Guoli Zhejiang Univ Technol Sch Comp Sci & Technol Hangzhou Zhejiang Peoples R China Zhejiang Univ Technol Sch Informat Engn Hangzhou Zhejiang Peoples R China

ISBN: (纸本)9783037851517

In inverse planning system of Intensity Modulated Radiation Therapy (IMRT), the coordinate of interested area (target, organ at risk) is the necessary information for optimization algorithm. This paper analyzes several classical region filling algorithms firstly. Based on the VTK toolkits, Bezier curve algorithm, and the improved watershed algorithm, a method using interactive delineation tool to save the coordinate information of interested area is realized. The information in the delineated area is accurately extracted by the method.

关键词： IMRT inverse planning interested area Visualization Toolkit Bezier Curse algorithm watershed algorithm

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28页 << < 17 18 19 20 21 22 23 24 25 26 > >>

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：