检索结果-内蒙古大学图书馆

3rd international conference on Artificial Intelligence and Pattern Recognition (AIPR)

作者： Kumar, Vinayshekhar Bannihatti Kumar, Sujay S. Saboo, Varun PES Inst Technol Dept Comp Sci Bengaluru Karnataka India

ISBN: (纸本)9781467391870

Dermatological diseases are the most prevalent diseases worldwide. Despite being common, its diagnosis is extremely difficult and requires extensive experience in the domain. In this research paper, we provide an approach to detect various kinds of these diseases. We use a dual stage approach which effectively combines computer vision and Machine Learning on clinically evaluated histopathological attributes to accurately identify the disease. In the first stage, the image of the skin disease is subject to various kinds of pre-processing techniques followed by feature extraction. The second stage involves the use of Machine learning algorithms to identify diseases based on the histopathological attributes observed on analysing of the skin. Upon training and testing for the six diseases, the system produced an accuracy of up to 95 percent.

关键词： Dermatology image processing computer vision Machine Learning Data Mining Computational Intelligence Automated Disease Diagnosis

来源：评论

学校读者我要写书评

暂无评论

Parallel implementation of image sharpening method using grid warping 26

Parallel implementation of image sharpening method using gri...

引用

26th international conference on computer Graphics and vision, GraphiCon 2016

作者： Gusev, A.D. Nasonov, A.V. Krylov, A.S. Laboratory of Mathematical Method of Image Processing Faculty of Computational Mathematics and Cybernetics Lomonosov Moscow State University Moscow Russia

The development of image sharpening algorithms is a challenging problem. The paper presents a parallel implementation of grid warping algorithm for the problem of image sharpening. The algorithm shifts pixels toward edge centerlines to make the edges sharper instead of changing pixel values directly. This approach does not amplify noise level and does not add ringing effect. © Proceedings of the 26th international conference on computer Graphics and vision, GraphiCon 2016. All rights reserved.

关键词： Pixels

来源：评论

学校读者我要写书评

暂无评论

Research of the Defects in PET Preform 21

Research of the Defects in PET Preform

引用

21st international conference on Methods and Models in Automation and Robotics (MMAR)

作者： Laucka, Andrius Andriukaitis, Darius Markevicius, Vytautas Zilys, Mindaugas Kaunas Univ Technol Dept Elect Engn LT-51368 Kaunas Lithuania

ISBN: (纸本)9781509018666

image technologies nowadays are used not only for keeping personal events safe, but also are widely applied in conjunction with automated electronic systems. computer vision is widely used for inspection of the production quality in industries. Food industry is not an exception. Containers for food industry are made in very large quantities. This article contains of defect analysis of both external and side area of the bottleneck. Defects were divided into groups according to which the filters are created. For the control of PET preparation quality an automated computer vision algorithms were developed. The algorithms and methods were used for the detection of defective products mainly based on the image segmentation, digital production, erosion, smoothing. The most effective filters for the defect detection of the workpieces have been determined. It was carried out that efficiency of algorithms are close to 100 %.

关键词： PET digital image processing image segmentation computer vision smoothing methods

来源：评论

学校读者我要写书评

暂无评论

vision BASED INFORMATION RETRIEVAL 13

VISION BASED INFORMATION RETRIEVAL

引用

13th IEEE international computer conference on Wavelet Active Media Technology and Information processing (ICCWAMTIP)

作者： Khan, Asif Li, Jian-Ping Khann, Mohd Yusuf Univ Elect Sci & Technol China Chengdu Sichuan Peoples R China Indian Inst Technol Roorkee Uttar Pradesh India

ISBN: (纸本)9781509061266

vision phenomena with natural strategy are an ideal approach and easy task for human being to see, feel and understand. But that unstructured random scene perception and understanding is a challenging problem in visual image and processing research area. vision science plays an important role in education, health, military etc. Accordingly here a new model "FL-SHODHANI" has been proposed for the above analysis. This model proceeds with an improvement of pictorial information, storage image data, transmission and representation of images. Then they obtained attributes are considered as sense with the observation, based on task limit. Accordingly this research work also studied various real world application problems related to medical, robotics, agriculture and geo-navigation using the above proposed method. Issues concerning drifts and robustness are analyzed and discussed here with respect to the original framework. Hopefully the contribution made by this research work will make a new vista in the filled of advanced technology for the betterment of our global society.

关键词： Machine vision Objects grasping Human-robot interaction Information retrieval

来源：评论

学校读者我要写书评

暂无评论

image processing for data acquisition and machine learning of helicopter flight dynamics

Image processing for data acquisition and machine learning o...

引用

2016 international conference on image processing, computer vision, and Pattern Recognition, IPCV 2016

作者： Tappan, Dan Hempleman, Matt Department of Computer Science Eastern Washington University CheneyWA United States

ISBN: (纸本)1601324421

Learning to fly a full-sized helicopter is a complex iterative process of mapping interdependent causes to effects via inputs to outputs in real time in a wildly dynamic, messy, and unforgiving environment. This work presents a prototype system for noninvasively acquiring otherwise inaccessible data from the controls, instruments, and flight dynamics of a Robinson R22 helicopter with an array of cameras and sensors and thenprocessing these images with OpenCV-based solutions into corresponding numerical form for later use in a machine-learningproject. It describes a hardware and software architecture for safely and successfully calibrating the system, running a breadth and depth of representative experiments, and qualitatively and quantitativelypresenting and validating the results. © CSREA Press.

关键词： Data handling

来源：评论

学校读者我要写书评

暂无评论

Pupil detection for head-mounted eye tracking in the wild: an evaluation of the state of the art

引用

MACHINE vision AND APPLICATIONS 2016年第8期27卷 1275-1288页

作者： Fuhl, Wolfgang Tonsen, Marc Bulling, Andreas Kasneci, Enkelejda Univ Tubingen Percept Engn Grp Tubingen Germany Max Planck Inst Informat Perceptual User Interfaces Grp Saarbrucken Germany

Robust and accurate detection of the pupil position is a key building block for head-mounted eye tracking and prerequisite for applications on top, such as gaze-based human-computer interaction or attention analysis. Despite a large body of work, detecting the pupil in images recorded under real-world conditions is challenging given significant variability in the eye appearance (e.g., illumination, reflections, occlusions, etc.), individual differences in eye physiology, as well as other sources of noise, such as contact lenses or make-up. In this paper we review six state-of-the-art pupil detection methods, namely ElSe (Fuhl et al. in Proceedings of the ninth biennial ACM symposium on eye tracking research&applications, ACM. New York, NY, USA, pp 123130, 2016), ExCuSe (Fuhl et al. in computer analysis of images and patterns. Springer, New York, pp 39-51, 2015), Pupil Labs (Kassner et al. in Adjunct proceedings of the 2014 ACM international joint conference on pervasive and ubiquitous computing (UbiComp), pp 1151-1160, 2014. doi: 10.1145/2638728.2641695), SET (Javadi et al. in Front Neuroeng 8, 2015), Starburst (Li et al. in computer vision and pattern recognition-workshops, 2005. IEEE computer society conference on CVPR workshops. IEEE, pp 79-79, 2005), and Swirski (Swirski et al. in Proceedings of the symposium on eye tracking research and applications (ETRA). ACM, pp 173-176, 2012. doi: 10.1145/2168556.2168585). We compare their performance on a large-scale data set consisting of 225,569 annotated eye images taken from four publicly available data sets. Our experimental results show that the algorithm ElSe (Fuhl et al. 2016) outperforms other pupil detection methods by a large margin, offering thus robust and accurate pupil positions on challenging everyday eye images.

关键词： Pupil detection Head-mounted eye tracking Data set computer vision image processing

来源：评论

学校读者我要写书评

暂无评论

Support and monitoring trajectory paths for vehicles using mobile devices 26

Support and monitoring trajectory paths for vehicles using m...

引用

26th international conference on Electronics, Communications and Computing (CONIELECOMP)

作者： Ojeda-Andablo, Jenny A. Paz-Trejo, Javier Carvajal-Gamez, Blanca E. Ferrer-Tenorio, Jorge Inst Politecn Nacl Escuela Super Comp SEPI ESCOM Juan Dios Batiz S-N Profes U Adolfo Lopez Mateos Mexico City 07738 DF Mexico

ISBN: (纸本)9781509000791

Currently artificial intelligence combined with computer vision has helped in performing daily activities, the current tendency of semi-autonomous vehicles assisted by artificial intelligence and computer vision has created a new field of image processing research. The image processing to support autonomous route tracking systems they have been tested in controlled media. In this investigation we perform the implementation of a system of guide and trajectory tracking in real scenarios (not controlled media) as road and city streets. Propose a new method for detecting lines as the Hough transform, in a simple and efficient for the detection of lane on a mobile manner. With the above determined whether or not the vehicle conserves his lane by opening angles of triangles detected with the mobile camera, to support and assist the driver. The methodology is tested to determine its performance qualitatively and quantitatively.

关键词： Autonomous vehicles tracking lines Hough transform artificial intelligence computer vision

来源：评论

学校读者我要写书评

暂无评论

A two-phase fuzzy system for edge detection

A two-phase fuzzy system for edge detection

引用

2016 international conference on image processing, computer vision, and Pattern Recognition, IPCV 2016

作者： Sleit, Azzam Saadeh, Maha AlMobaideen, Wesam Department of Computer Science King Abdulla II School for Information Technology University of Jordan P.O. Box 13898 Amman11942 Jordan

ISBN: (纸本)1601324421

Edge detection is a preliminary process in many image processing and computer vision applications. It detects important events in the image where sharp discontinuity in pixels' intensity is found. Several edge detection techniques have been proposed including Sobel, Canny, Prewitt, and many others. Since fuzzy logic is a powerful tool to manage the uncertainty efficiently, it can be used in edge detection to decide whether a certain pixel is an edge pixel or not. In this paper, a two-phase fuzzy inference system is proposed to detect edges in gray level images. In the first phase the discontinuity in pixels' intensity is evaluated according to various directions, while in the second phase the final decision is determined based on the results obtained from the first phase. The proposed algorithm is implemented using MATLAB and experimental results show improvement when compared with other edge detection techniques. © CSREA Press.

关键词： Edge detection

来源：评论

学校读者我要写书评

暂无评论

A Formal Algebra Implementation for Distributed image and Video Stream processing 16

A Formal Algebra Implementation for Distributed Image and Vi...

引用

10th international conference on Distributed Smart Cameras (ICDSC)

作者： Helala, Mohamed A. Pu, Ken Q. Qureshi, Faisal Z. Univ Ontario Inst Technol Fac Sci Oshawa ON Canada

ISBN: (纸本)9781450347860

We are interested in building scalable computer vision systems for distributed processing of big visual data. We apply data streaming concepts, namely stream algebra operators, which have been proven effective in the database literature. The operators collectively form an algebra over data streams. The algebra has well defined semantics. It naturally describes online computer vision algorithms and their feedback control and tuning algorithms. In this work, we present the first implementation of such algebra at large scale. Our implementation provides a high level programming interface for constructing and executing vision workflow graphs while hiding the data transfer and concurrency details. It also allows feedback control and dynamic reconfiguration of vision algorithms. A case study is discussed showing a streaming workflow for online lane and road boundary detection and describing the flexibility and effectiveness of the algebra for building complex distributed applications.

关键词： stream algebra workflow graphs programming frameworks distributed vision processing

来源：评论

学校读者我要写书评

暂无评论

Multiscale method for ridge detection on ophthalmological images 26

Multiscale method for ridge detection on ophthalmological im...

引用

26th international conference on computer Graphics and vision, GraphiCon 2016

作者： Mamaev, N.V. Yurin, D.V. Krylov, A.S. Laboratory of Mathematical Methods of Image Processing Faculty of Computational Mathematics and Cybernetics Lomonosov Moscow State University Moscow Russia

We propose a method for ridge detection and consider its application for detection of blood vessels on eye fundus images. The algorithm is based on multiscale application of non-maxima suppression to Laplacian of an image. The multiscale algorithm is based on the image pyramid similar to SIFT pyramid. This pyramid is used for a generalization of the multiscale non-maxima suppression method. Merging of the results of detection is performed using mathematical morphology methods. We test the proposed algorithm with DRIVE ophthalmological image database. © Proceedings of the 26th international conference on computer Graphics and vision, GraphiCon 2016. All rights reserved.

关键词： Mathematical morphology

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：