检索结果-内蒙古大学图书馆

Skin-Colored Gesture Recognition and Support Vector Machines-Based Classification of Light Sources by Their Illumination Properties 3rd

引用

3rd International Conference on Computational Intelligence in Data Mining (ICCIDM)

作者： Bandyopadhyay, Shreyasi Choudhury, Sabarna Ghosh, Riya Santra, Saptam Ghosh, Rabindranath St Thomas Coll Engn & Technol Elect & Commun Dept Kolkata India

ISBN: (纸本)9789811038747;9789811038730

The illumination characteristics of light sources can determine whether the light source is a normal or a faulty one. The proposed work is based on moving a platform containing a light source in both horizontal and vertical directions by gesture recognition. The gesture recognition done by Fuzzy C means and snake algorithm-based skin color detection makes the recognition more accurate. The illumination values of the light source are obtained by a webcam. The set of data helps in classification of the state of an unknown light source (normal or faulty) by support vector machines with radial basis function as kernel with a yield of an error rate of about 0.6% marking the efficacy of the system and making the system a novel and sophisticated one.

关键词： Illumination characteristics Gesture recognition Skin color detection Fuzzy C means snake algorithm Support vector machines Radial basis function

来源：评论

学校读者我要写书评

暂无评论

Application of an Improved snake Model in Face Location Based on Skin-color

Application of an Improved Snake Model in Face Location Base...

引用

7th World Congress on Intelligent Control and Automation

作者： Huang Hanmin Jiang Zhen Chongqing Jiaotong Univ Sch Comp Sci Chongqing 400074 Peoples R China

ISBN: (纸本)9781424421138

In image processing and computer vision, snake (active contour model) is an effective tool in implementing brim detection or contour extraction of object. But the snake algorithm has the deadly shortcoming - the result is affected by the origin position. In this paper, proposed a new modified algorithm combining centric algorithm into the snake algorithm, so get the priority information of the origin position The algorithm reduces sensitivity to initialization while providing superior performance. Finally the results of the computer simulation show the advantage of the new algorithm.

关键词： face location face detection color space snake algorithm

来源：评论

学校读者我要写书评

暂无评论

Hybrid Ant Colony Optimization-Based Method for Focal of a Disease Segmentation in Lung CT Images 11th

Hybrid Ant Colony Optimization-Based Method for Focal of a D...

引用

11th International Conference on Swarm Intelligence (ICSI)

作者： Lu, Mingli Xu, Benlian Qin, Weijian Shi, Jian Changshu Inst Technol Sch Elect & Automat Engn Changshu 215500 Jiangsu Peoples R China Changshu Inst Technol Sch Mech Engn Changshu 215500 Jiangsu Peoples R China

ISBN: (纸本)9783030539559;9783030539566

The detection of chest CT scan images of the lung play a key role in clinical decision making for some lung disease, such as tumors, pulmonary tuberculosis, solitary pulmonary nodule, lung masses and so on. In this paper, a novel automated CT scan image segmentation algorithm based on hybrid Ant Colony algorithm and snake algorithm is proposed. Firstly, traditional snake algorithm is used to detect the possible edge points of focal of a disease. Then Ant Colony Optimization (ACO) algorithm is applied to search the possible edge points of focal of a disease repeatedly. Finally, real edges can be extracted according to the intensity of pheromones. Simulation experiment results demonstrate that the proposed algorithm is more efficient and effective than the methods we compared it to.

关键词： Ant Colony Optimization snake algorithm Image segmentation Edge detection

来源：评论

学校读者我要写书评

暂无评论

Using PCA and LVQ Neural Network for Automatic Recognition of Five Types of White Blood Cells

Using PCA and LVQ Neural Network for Automatic Recognition o...

引用

32nd Annual International Conference of the IEEE Engineering-in-Medicine-and-Biology-Society (EMBC 10)

作者： Tabrizi, P. R. Rezatofighi, S. H. Yazdanpanah, M. J. Univ Tehran Sch Elect & Comp Engn CIPCE Tehran Iran

ISBN: (纸本)9781424441242

Designing an effective classifier has been a challenging task in the previous methods proposed in the literature. In this paper, we apply a combination of feature selection algorithm and neural network classifier in order to recognize five types of white blood cells in the peripheral blood. For this purpose, first nucleus and cytoplasm are segmented using Gram-Schmidt method and snake algorithm, respectively;second, three kinds of features are extracted from the segmented areas. Then the best features are selected using Principal Component Analysis (PCA). Finally, five types of white blood cells are classified using Learning Vector Quantization (LVQ) neural network. The performance analysis of the proposed algorithm is validated by an expert's classification results. The efficiency of the proposed algorithm is highlighted by comparing our results with those reported in a recent article which proposed a method based on the combination of Sequential Forward Selection (SFS) as the feature selection algorithm and Support Vector Machines (SVM) as the classifier.

关键词： Gram-Schmidt method LVQ neural network PCA PCA neural network automatic cell recognition biomedical optical imaging blood cellular biophysics classification cytoplasm feature extraction feature extraction feature selection algorithm image classification image segmentation learning (artificial intelligence) learning vector quantization medical image processing neural nets nucleus peripheral blood principal component analysis principal component analysis segmentation sequential forward selection snake algorithm support vector machines support vector machines white blood cells

来源：评论

学校读者我要写书评

暂无评论

Contour extraction of moving objects

Contour extraction of moving objects

引用

14th International Conference on Pattern Recognition

作者： Qiu, LL Li, L Cornell Univ Dept Comp Sci Ithaca NY 14850 USA

ISBN: (纸本)0818685123

This paper proposes a novel approach to the contour extraction of moving objects in an image sequence. Our approach is to fuse information from color segmentation, motion segmentation, and active contour (snake) to achieve accurate extraction of the boundary of moving objects. It works well not only for a single moving object, but also for images having mutiple moving objects. Several experiments have been conducted to show the promise of our algorithm.

关键词： color segmentation reflectance ratio sequential labeling motion segmentation census transform morphological filter snake algorithm

来源：评论

学校读者我要写书评

暂无评论

Early Detection of Obstacle to Optimize the Robot Path Planning

引用

DRONES 2022年第10期6卷 265-265页

作者： Sharma, Kaushlendra Swarup, Chetan Pandey, Saroj Kumar Kumar, Ankit Doriya, Rajesh Singh, Kamred Udham Singh, Teekam Indian Inst Informat Technol Dept Comp Sci & Engn Nagpur 440006 Maharashtra India Saudi Elect Univ Coll Sci & Theoret Studies Dept Basic Sci Riyadh Male Campus Riyadh 13316 Saudi Arabia GLA Univ Dept Comp Engn & Applicat Mathura 281406 India Natl Inst Technol Dept Informat Raipur 492010 Madhya Pradesh India Natl Cheng Kung Univ Dept Comp Sci & Informat Engn Tainan 701 Taiwan Univ Petr & Energy Studies Sch Comp Sci Dehra Dun 248007 Uttarakhand India

Robot path planning is one of the core issues in robotics and its application. Optimizing the route discovery becomes more important while dealing with the robot-based application. This paper proposes the concept of early detection of the obstacle present in the workspace of the robots. To early detect the obstacle, this paper proposes the concept of a snake algorithm along with the traditional path planning algorithms. The contour detection part is merged with the different path planning algorithms to optimize the robot traversing and benefit it in producing good results. Obstacle-free optimized path is one of the core requirements for robots in any application. With the help of path planning algorithms, robots are enabled to derive those paths in a specific environment. The presence of an obstacle makes it difficult for any path planning algorithms to derive a smooth path. The purpose of using the snake algorithm is to detect an obstacle early. This method not only perceives the obstacle but also catches out the complete boundary of the obstacle, it, thus, provides the details of obstacle coordinates to the path planning algorithm. Conceiving the complete periphery of obstacles can have multiple advantages in many application areas. A*, PRM, RRT, and RRT Smooth algorithms are considered along with the snake algorithm to validate our work in three different experimental scenarios: Maze, Random Obstacles, and Dense case. Path length, Time-taken, and Move count are parameters taken to observe the results. The result obtained using the snake algorithm with four path planning algorithms is analyzed and compared in detail with the core A*, PRM, RRT, and RRTS. Finally, the result obtained using the proposed methodology gives some encouraging results and also predicts the exploration of the robot's path planning for more applications and fields.

关键词： path length move count path planning snake algorithm random obstacles

来源：评论

学校读者我要写书评

暂无评论

Segmentation and classification of knee joint ultrasonic image via deep learning

引用

APPLIED SOFT COMPUTING 2020年第PartB期97卷 106765-106765页

作者： Long Zhili Zhang Xiaobing Li Cong Niu Jin Wu Xiaojun Li Zuohua Harbin Inst Technol Shenzhen 518055 Peoples R China

The knee is one of the most complicated joints in the human body, but it could be easily injured. Ultrasound imaging is an important technology for the diagnosis of the knee disease. To assist doctors in the treatment and reduce errors of judgment, we investigate the segmentation of disease regions and the automated identification of the typical knee joint diseases. First, we use deep learning to segment the Region of Interest (ROI). To solve the mis-segmentation and poor edge segmentation that occur when the ultrasound image is directly fed into the deep neural network, an image segmentation framework is proposed that integrates snake preprocessing, dilated convolution to expand the receptive fields, and multi-channel learning. Second, due to the small difference in features among various categories of ultrasound images, a hybrid algorithm is proposed based on the Resnet rough classification and quadratic training with graph embedding. Finally, the experiments show that the proposed image segmentation framework achieves 10% greater accuracy than a common segmentation network. By visualizing the feature vectors extracted from the classification network, we verify that the feature vectors are closer on similar images after quadratic training by graph embedding. Employing the optimization with quadratic training, we increase the classification accuracy by 11% compared to the Resnet approach. (C) 2020 Elsevier B.V. All rights reserved.

关键词： Deep learning Image segmentation Image classification Graph embedding snake algorithm Knee ultrasound image

来源：评论

学校读者我要写书评

暂无评论

Dynamic clustering and propagation of congestion in heterogeneously congested urban traffic networks

引用

Transportation Research Procedia 2017年 23卷 962-979页

作者： Mohammadreza Saeedmanesh Nikolas Geroliminis Ecole Polytechnique Federale de Lausanne (EPFL) School of Architecture Civil and Environmental Engineering (ENAC) Urban Transport Systems Laboratory (LUTS) Lausanne Switzerland

The problem of clustering in urban traffic networks has been mainly studied in static framework by considering traffic conditions at a given time. Nevertheless, it is important to underline that traffic is a strongly time-variant process and it needs to be studied in the spatiotemporal dimension. Investigating the clustering problem over time in the dynamic domain is critical to better understand and reveal the hidden information during the process of congestion formation and dissolution. The primary motivation of the paper is to study the spatiotemporal relation of congested links, observing congestion propagation from a macroscopic perspective, and finally identifying critical pockets of congestion that can aid the design of peripheral control strategies. To achieve this, we first introduce a static clustering method to partition the heterogeneous network into homogeneous connected sub-regions. This method guarantees connectivity of the cluster, which eases the development of a dynamic framework. The proposed clustering approach obtains a feasible set of connected homogeneous components in the network called snakes, which represent a sequence of connected links with similar level of congestion. Secondly, the problem is formulated as a mixed integer linear optimization to find major skeleton of clusters out of this feasible set by minimizing a heterogeneity index. Thirdly, a fine-tuning step is designed to assign the unclustered links of the network to proper clusters while keeping the connectivity. The approach is extended to capture spatiotemporal growth and formation of congestion. The dynamic clustering is based on an iterative and fast procedure that considers the spatiotemporal characteristics of congestion propagation and identifies the links with the highest degree of heterogeneity due to time dependent conditions and finally re-cluster them while by minimizing heterogeneity and imposing connectivity. The developed framework can be directly implemented in a

关键词： graph partitioning congestion propagation aggregate modeling mixed integer linear programming snake algorithm

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：