检索结果-内蒙古大学图书馆

Matching point pattern using a munkres genetic algorithm

Journal of Convergence Information Technology 2011年第12期6卷 376-383页

作者： Xing, Chong Wei, Wei Wu, Jianan Zhang, Chulei Zhou, You College of Computer Science and Technology Jilin University China Guanghua College of Changchun University China College of Computer Science and Technology Changchun University China College of Humanities and Sciences Northeast Normal University Changchun China

Point pattern Matching is a very important and significant aspect of many fields in computer vision and pattern recognition. Using point pattern matching technique could find an optimal transformation for one point pattern to the other under a distance measurement. Genetic Algorithm combines with Munkres algorithm is proposed for solving Point pattern Matching problem. The proposed algorithm can be used to perform reliable matching between two different views of an object or scene. A new formula is proposed and used as a reasonable fitness function. The advantages of Munkres and Genetic algorithm are used and combined together in this paper. The experimental results show that the new algorithm is very effective.

关键词： Genetic algorithms

来源：评论

学校读者我要写书评

暂无评论

Fast, recurrent, attentional modulation improves saliency representation and scene recognition

Fast, recurrent, attentional modulation improves saliency re...

引用

IEEE computer Society Conference on computer vision and pattern recognition Workshops (CVPRW)

作者： Xun Shi Neil D. B. Bruce John K. Tsotsos Department of Computer Science & Engineering and Centre of Vision Research York University Toronto ONT Canada

The human brain uses visual attention to facilitate object recognition. Traditional theories and models envision this attentional mechanism either in a pure feedforward fashion for selection of regions of interest or in a top-down task-priming fashion. To these well-known attentional mechanisms, we add here an additional novel one. The approach is inspired by studies of biological vision pertaining to the asynchronous timing of feedforward signals among different early visual areas and the role of recurrent connections from short latency areas to facilitate object recognition. It is suggested that recurrence elicited from these short latency dorsal areas improves the slower feedforward processing in the early ventral areas. We therefore propose a computational model that simulates this process. To test this model, we add such fast recurrent processes to a well-known model of feedforward saliency, AIM and show that those recurrent signals can modulate the output of AIM to improve its utility in recognition by later stages. We further add the proposed model to a back-propagation neural network for the task of scene recognition. Experimental results on standard video sequences show that the discriminating power of the modulated representation is significantly improved, and the implementation consistently outperforms existing work including a benchmark system that does not include recurrent refinement.

关键词： Computational modeling Visualization Feedforward neural networks Neurons Modulation Object recognition Spatiotemporal phenomena

来源：评论

学校读者我要写书评

暂无评论

Wide-angle micro sensors for vision on a tight budget

Wide-angle micro sensors for vision on a tight budget

引用

Conference on computer vision and pattern recognition (CVPR)

作者： Sanjeev J. Koppal Ioannis Gkioulekas Todd Zickler Geoffrey L. Barrows Harvard University USA Centeye Inc. USA

Achieving computer vision on micro-scale devices is a challenge. On these platforms, the power and mass constraints are severe enough for even the most common computations (matrix manipulations, convolution, etc.) to be difficult. This paper proposes and analyzes a class of miniature vision sensors that can help overcome these constraints. These sensors reduce power requirements through template-based optical convolution, and they enable a wide field-of-view within a small form through a novel optical design. We describe the trade-offs between the field of view, volume, and mass of these sensors and we provide analytic tools to navigate the design space. We also demonstrate milli-scale prototypes for computer vision tasks such as locating edges, tracking targets, and detecting faces.

关键词： Optical sensors Optical refraction Optical imaging Lenses Optical design

来源：评论

学校读者我要写书评

暂无评论

Real-time preprocessing for dense 3-D range imaging on the GPU: Defect interpolation, bilateral temporal averaging and guided filtering

Real-time preprocessing for dense 3-D range imaging on the G...

引用

International Conference on computer vision Workshops (ICCV Workshops)

作者： Jakob Wasza Sebastian Bauer Joachim Hornegger Pattern Recognition Lab Department of Computer Science Friedrich-Alexander-Universität Erlangen-Nürnberg Germany Pattern Recognition Lab Department of Computer Science Erlangen Graduate School in Advanced Optical Technologies (SAOT) Friedrich-Alexander-Universität Erlangen-Nürnberg Germany

Recent advances in range imaging (RI) have enabled dense 3-D scene acquisition in real-time. However, due to physical limitations and the underlying range sampling principles, range data are subject to noise and may contain invalid measurements. Hence, data preprocessing is a prerequisite for practical applications but poses a challenge with respect to real-time constraints. In this paper, we propose a generic and modality-independent pipeline for efficient RI data preprocessing on the graphics processing unit (GPU). The contributions of this work are efficient GPU implementations of normalized convolution for the restoration of invalid measurements, bilateral temporal averaging for dynamic scenes, and guided filtering for edge-preserving denoising. Furthermore, we show that the transformation from range measurements to 3-D world coordinates can be computed efficiently on the GPU. The pipeline has been evaluated on real data from a Time-of-Flight sensor and Microsoft's Kinect. In a run-time performance study, we show that for VGA-resolution data, our preprocessing pipeline runs at ~100 fps on an off-the-shelf consumer GPU.

关键词： Graphics processing unit Pipelines Image restoration Real time systems Noise reduction Kernel Convolution

来源：评论

学校读者我要写书评

暂无评论

Are face recognition methods useful for classifying ships?

Are face recognition methods useful for classifying ships?

引用

Applied Imagery pattern recognition Workshop (AIPR)

作者： Josh Harguess Katie Rainey Computer & Vision Research Center / Department of ECE The University of Texas at Austin Austin TX USA Space and Naval Warfare Systems Center Pacific San Diego CA USA

Face recognition research has gained significant interest in recent years which has resulted in the development of many state-of-the-art methods. However, it is not well-known how domain specific these methods are to the problem of face recognition. Could these algorithms be used to classify and identify other objects, such as ships seen from electro-optical satellite imagery? Face recognition research shares many of the same challenges with many other types of classification research, such as illumination, pose and resolution variation. Therefore, a study of this type is warranted. We present a comparison of several classical (e.g. eigenfaces and fisherfaces) as well as recent state-of-the-art face recognition methods (e.g. sparse representation and local binary patterns) using one standard face database and two databases of ship images collected from satellite imagery. An analysis of these results as well as future directions conclude the paper.

关键词： Face recognition Databases Marine vehicles Face Feature extraction Training Vectors

来源：评论

学校读者我要写书评

暂无评论

CROHME2011: Competition on recognition of Online Handwritten Mathematical Expressions

CROHME2011: Competition on Recognition of Online Handwritten...

引用

International Conference on Document Analysis and recognition

作者： Harold Mouchere Christian Viard-Gaudin Dae Hwan Kim Jin Hyung Kim Utpal Garain IRCCyN/IVC — UMR CNRS 6597 Ecole Polytechnique de l'Université de Nantes France Division of Computer Science Korea Advanced Institute of Science and Technology Republic of Korea Computer Vision and Pattern Recognition (CVPR) Unit Indian Statistical Institute Kolkata India

ISBN: (纸本)9781457713507

A competition on recognition of online handwritten mathematical expressions is organized. recognition of mathematical expressions has been an attractive problem for the pattern recognition community because of the presence of enormous uncertainties and ambiguities as encountered during parsing of the two-dimensional structure of expressions. The goal of this competition is to bring out a state of the art for the related research. Three labs come together to organize the event and six other research groups participated the competition. The competition defines a standard format for presenting information, provides a training set of 921 expressions and supplies the underlying grammar for understanding the content of the training data. Participants were invited to submit their recognizers which were tested with a new set of 348 expressions. Systems are evaluated based on four different aspects of the recognition problem. However, the final rating of the systems is done based on their correct expression recognition accuracies. The best expression level recognition accuracy (on the test data) shown by the competing systems is 19.83% whereas a baseline system developed by one of the organizing groups reports an accuracy 22.41% on the same data set.

关键词： Grammar Handwriting recognition Training Accuracy Ink Organizing Communities

来源：评论

学校读者我要写书评

暂无评论

Texton-based fabric defect detection and recognition

引用

Iranian Journal of Electrical and computer Engineering 2011年第2期10卷 57-69页

作者： Behravan, M. Tajeripour, F. Azimifar, Z. Boostani, R. Computer Vision and Pattern Recognition Group School of Electrical and Computer Engineering Shiraz University Shiraz Iran

Automatic fabric defect classification is an essential stage in production line of textile manufactures. Here, a novel method for simultaneous detection and classification of fabric defects is presented. Each fabric defect type produces a locally specific type of texture. In this paper for the first time textons are used to describe local structure of fabric defects textures. In the method, an image is divided into several blocks in which features based on filter banks are extracted from them. According to these features, the algorithm determines defective windows and their defect types. The employed datasets in this study contain six types of well-known defects of patterned fabrics and four types of unpatterned fabric defects. Our experiments have yielded excellent results and this shows that descriptors based on texture properties of defective regions are suitable for classification task. The proposed method leads to improved and robust detection and classification results compared to the traditional methods. © 2011 ACECR.

关键词： Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Analysis of patterns of motor behavior in gamers with down syndrome

Analysis of patterns of motor behavior in gamers with down s...

引用

IEEE computer Society Conference on computer vision and pattern recognition Workshops (CVPRW)

作者： Jeremy Svendsen Alexandra Branzan Albu Naznin Virji-Babul University of Victoria Victoria BC Canada Down Syndrome Research Foundation Vancouver BC Canada

This paper reports on the computer vision-based analysis of weight-shifting patterns in Down Syndrome subjects. The subjects were filmed while playing a snowboarding game in a virtual reality environment. To capture local changes in posture during motion performance, we introduce the concept of parabolic bounding box. This concept aims at capturing information about the lateral curvature of the human body in motion. This information is aggregated into histograms of motion curvatures. This novel motion representation is useful for differentiating between normal and abnormal weight shifting patterns, and for presenting subject specific information about the frequency of these patterns over the entire duration of the game.

关键词： Histograms Torso Games Humans Virtual reality computer vision Video sequences

来源：评论

学校读者我要写书评

暂无评论

Human action recognition in videos using keypoint tracking

Human action recognition in videos using keypoint tracking

引用

IEEE Signal Processing and Communications Applications (SIU)

作者： Yunus Emre Kara Lale Akarun Bilgisayar Mühendisliği Bölümü Boğaziçi Üniversitesi Istanbul Turkey

In this study, a new system for computer vision-based recognition of human actions is presented. The proposed system uses videos as input. The approach is invariant of the location of the action and zoom levels, the appearance of the person, partial occlusions including self-occlusions and some viewpoint changes. It is robust against temporal length variations. Keypoints are tracked through time and the trajectories of tracked keypoints are used for interpreting the human action in the video. Then, features from videos are extracted. A group of features for describing a trajectory are proposed. Trajectories are clustered using these trajectory features. The clustered trajectories are used for describing an image sequence. Image sequence descriptors are the normalized histograms of the clusters of trajectories. At the final stage, the proposed system uses the descriptors of the image sequences in a supervised learning approach.

关键词： Videos Conferences Humans computer vision pattern recognition Trajectory Support vector machines

来源：评论

学校读者我要写书评

暂无评论

A large-scale benchmark dataset for event recognition in surveillance video

A large-scale benchmark dataset for event recognition in sur...

引用

Conference on computer vision and pattern recognition (CVPR)

作者： Sangmin Oh Anthony Hoogs Amitha Perera Naresh Cuntoor Chia-Chih Chen Jong Taek Lee Saurajit Mukherjee J. K. Aggarwal Hyungtae Lee Larry Davis Eran Swears Xioyang Wang Qiang Ji Kishore Reddy Mubarak Shah Carl Vondrick Hamed Pirsiavash Deva Ramanan Jenny Yuen Antonio Torralba Bi Song Anesco Fong Amit Roy-Chowdhury Mita Desai

We introduce a new large-scale video dataset designed to assess the performance of diverse visual event recognition algorithms with a focus on continuous visual event recognition (CVER) in outdoor areas with wide coverage. Previous datasets for action recognition are unrealistic for real-world surveillance because they consist of short clips showing one action by one individual [15, 8]. Datasets have been developed for movies [11] and sports [12], but, these actions and scene conditions do not apply effectively to surveillance videos. Our dataset consists of many outdoor scenes with actions occurring naturally by non-actors in continuously captured videos of the real world. The dataset includes large numbers of instances for 23 event types distributed throughout 29 hours of video. This data is accompanied by detailed annotations which include both moving object tracks and event examples, which will provide solid basis for large-scale evaluation. Additionally, we propose different types of evaluation modes for visual recognition tasks and evaluation metrics along with our preliminary experimental results. We believe that this dataset will stimulate diverse aspects of computer vision research and help us to advance the CVER tasks in the years ahead.

关键词： Vehicles Surveillance Cameras Humans Visualization computer vision Benchmark testing

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：