检索结果-内蒙古大学图书馆

作者： Gall, Juergen Fossati, Andrea Van Gool, Luc BIWI ETH Zurich Switzerland ESAT-PSI IBBT KU Leuven Belgium

ISBN: (纸本)9781457703942

Unsupervised categorization of objects is a fundamental problem in computer vision. While appearance-based methods have become popular recently, other important cues like functionality are largely neglected. Motivated by psychological studies giving evidence that human demonstration has a facilitative effect on categorization in infancy, we propose an approach for object categorization from depth video streams. To this end, we have developed a method for capturing human motion in real-time. The captured data is then used to temporally segment the depth streams into actions. The set of segmented actions are then categorized in an un-supervised manner, through a novel descriptor for motion capture data that is robust to subject variations. Furthermore, we automatically localize the object that is manipulated within a video segment, and categorize it using the corresponding action. For evaluation, we have recorded a dataset that comprises depth data with registered video sequences for 6 subjects, 13 action classes, and 174 object manipulations. © 2011 IEEE.

关键词： computer vision

来源：评论

学校读者我要写书评

暂无评论

Face recognition with decision tree-based local binary patterns

Face recognition with decision tree-based local binary patte...

引用

Lecture Notes in computer Science

作者： Maturana, Daniel Mery, Domingo Soto, Álvaro Department of Computer Science Pontificia Universidad Católica Chile Chile

ISBN: (纸本)9783642192814

Many state-of-the-art face recognition algorithms use image descriptors based on features known as Local Binary patterns (LBPs). While many variations of LBP exist, so far none of them can automatically adapt to the training data. We introduce and analyze a novel generalization of LBP that learns the most discriminative LBP-like features for each facial region in a supervised manner. Since the proposed method is based on Decision Trees, we call it Decision Tree Local Binary patterns or DT-LBPs. Tests on standard face recognition datasets show the superiority of DT-LBP with respect of several state-of-the-art feature descriptors regularly used in face recognition applications. © 2011 Springer-Verlag Berlin Heidelberg.

关键词： Local binary pattern

来源：评论

学校读者我要写书评

暂无评论

Boosted Exemplar Learning for Action recognition and Annotation

引用

IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY 2011年第7期21卷 853-866页

作者： Zhang, Tianzhu Liu, Jing Liu, Si Xu, Changsheng Lu, Hanqing Chinese Acad Sci Natl Lab Pattern Recognit Inst Automat Beijing 100190 Peoples R China China Singapore Inst Digital Media Singapore 119613 Singapore

Human action recognition and annotation is an active research topic in computer vision. How to model various actions, varying with time resolution, visual appearance, and others, is a challenging task. In this paper, we propose a boosted exemplar learning (BEL) approach to model various actions in a weakly supervised manner, i.e., only action bag-level labels are provided but action instance level ones are not. The proposed BEL method can be summarized as three steps. First, for each action category, amount of class-specific candidate exemplars are learned through an optimization formulation considering their discrimination and co-occurrence. Second, each action bag is described as a set of similarities between its instances and candidate exemplars. Instead of simply using a heuristic distance measure, the similarities are decided by the exemplar-based classifiers through the multiple instance learning, in which a positive (or negative) video or image set is deemed as a positive (or negative) action bag and those frames similar to the given exemplar in Euclidean Space as action instances. Third, we formulate the selection of the most discriminative exemplars into a boosted feature selection framework and simultaneously obtain an action bag-based detector. Experimental results on two publicly available datasets: the KTH dataset and Weizmann dataset, demonstrate the validity and effectiveness of the proposed approach for action recognition. We also apply BEL to learn representations of actions by using images collected from the Web and use this knowledge to automatically annotate action in YouTube videos. Results are very impressive, which proves that the proposed algorithm is also practical in unconstraint environments.

关键词： Action annotation action recognition AdaBoost mi-SVM multiple instance learning (MIL)

来源：评论

学校读者我要写书评

暂无评论

Embedded microscope vision based mechanical platform for LED wafer automatic inspection

Embedded microscope vision based mechanical platform for LED...

引用

2011 3rd International Asia Conference on Informatics in Control, Automation and Robotics, CAR 2011

作者： Gao, Xinyan Zhou, Ning Li, Dakui Yue, Yuan School of Software Dalian University of Technology Dalian China School of Computer and Information Technology Beijing Jiaotong University Beijing China School of Mathematics Computer Science Institute Northwest University for Nationalities Lanzhou China

ISBN: (纸本)9783642259913

In this paper, we propose a novel technique solution towards LED wafer defects automatic full inspection using neural network chip array to assure defect-free outgoing dies. Our research intends to develop an automatic inspection system for defect pattern recognition in order to substitute human visual judgement. This solution mainly includes a three degree-of-freedom precise mechanical positioning stage and an automatic robot arm working with an embedded microscope vision system. A built-in parallel neural network chip array acts as the recognition engine instead of traditional software approach. Meanwhile, the mechanical motion control is also based on neural network method. This solution will benefit greatly from hardware engine acceleration as for performance improvement. © 2011 Springer-Verlag.

关键词： Light emitting diodes

来源：评论

学校读者我要写书评

暂无评论

Supervised local subspace learning for continuous head pose estimation

Supervised local subspace learning for continuous head pose ...

引用

作者： Huang, Dong Storer, Markus De La Torre, Fernando Bischof, Horst Robotics Institute Carnegie Mellon University United States Institute for Computer Graphics and Vision Graz University of Technology Austria University of Electronic Science and Technology of China China

ISBN: (纸本)9781457703942

Head pose estimation from images has recently attracted much attention in computer vision due to its diverse applications in face recognition, driver monitoring and human computer interaction. Most successful approaches to head pose estimation formulate the problem as a nonlinear regression between image features and continuous 3D angles (i.e. yaw, pitch and roll). However, regression-like methods suffer from three main drawbacks: (1) They typically lack generalization and overfit when trained using a few samples. (2) They fail to get reliable estimates over some regions of the output space (angles) when the training set is not uniformly sampled. For instance, if the training data contains under-sampled areas for some angles. (3) They are not robust to image noise or occlusion. To address these problems, this paper presents Supervised Local Subspace Learning (SL2), a method that learns a local linear model from a sparse and non-uniformly sampled training set. SL2 learns a mixture of local tangent spaces that is robust to under-sampled regions, and due to its regularization properties it is also robust to over-fitting. Moreover, because SL2 is a generative model, it can deal with image noise. Experimental results on the CMU Multi-PIE and BU-3DFE database show the effectiveness of our approach in terms of accuracy and computational complexity. © 2011 IEEE.

关键词： Face recognition

来源：评论

学校读者我要写书评

暂无评论

Tracking planes with time of flight cameras and J-linkage

Tracking planes with time of flight cameras and J-linkage

引用

2011 IEEE Workshop on Applications of computer vision, WACV 2011

作者： Schwarz, Loren Arthur Mateus, Diana Lallemand, Joé Navab, Nassir Technische Universität München 85748 Garching Germany

ISBN: (纸本)9781424494965

In this paper, we propose a method for detection and tracking of multiple planes in sequences of Time of Flight (ToF) depth images. Our approach extends the recent J-linkage algorithm for estimation of multiple model instances in noisy data to tracking. Instead of randomly selecting plane hypotheses in every image, we propagate plane hypotheses through the sequence of images, resulting in a significant reduction of computational load in every frame. We also introduce a multi-pass scheme that allows detecting and tracking planes of varying spatial extent along with their boundaries. Our qualitative and quantitative evaluation shows that the proposed method can robustly detect planes and consistently track the hypotheses through sequences of ToF images. © 2010 IEEE.

关键词： pattern recognition

来源：评论

学校读者我要写书评

暂无评论

Enhanced Biologically Inspired Model for Object recognition

引用

IEEE TRANSACTIONS ON SYSTEMS MAN AND CYBERNETICS PART B-CYBERNETICS 2011年第6期41卷 1668-1680页

作者： Huang, Yongzhen Huang, Kaiqi Tao, Dacheng Tan, Tieniu Li, Xuelong Chinese Acad Sci Natl Lab Pattern Recognit Inst Automat Beijing 100190 Peoples R China Univ Technol Sydney Ctr Quantum Computat & Informat Syst Sydney NSW 2007 Australia Chinese Acad Sci Ctr Opt IMagery Anal & Learning OPTIMAL State Key Lab Transient Opt & Photon Xian Inst Opt & Precis Mech Xian 710119 Peoples R China

The biologically inspired model (BIM) proposed by Serre et al. presents a promising solution to object categorization. It emulates the process of object recognition in primates' visual cortex by constructing a set of scale- and position-tolerant features whose properties are similar to those of the cells along the ventral stream of visual cortex. However, BIM has potential to be further improved in two aspects: mismatch by dense input and randomly feature selection due to the feedforward framework. To solve or alleviate these limitations, we develop an enhanced BIM (EBIM) in terms of the following two aspects: 1) removing uninformative inputs by imposing sparsity constraints, 2) apply a feedback loop to middle level feature selection. Each aspect is motivated by relevant psychophysical research findings. To show the effectiveness of the EBIM, we apply it to object categorization and conduct empirical studies on four computer vision data sets. Experimental results demonstrate that the EBIM outperforms the BIM and is comparable to state-of-the-art approaches in terms of accuracy. Moreover, the new system is about 20 times faster than the BIM.

关键词： Biologically inspired model (BIM) feedback object recognition sparseness

来源：评论

学校读者我要写书评

暂无评论

Machine Learning in Medical Imaging 2011

引用

丛书名： Lecture Notes in computer Science

2011年

作者： Kenji Suzuki Fei Wang Dinggang Shen Pingkun Yan

ISBN: (数字)9783642243196

ISBN: (纸本)9783642243189

This book constitutes the refereed proceedings of the Second International Workshop on Machine Learning in Medical Imaging, MLMI 2011, held in conjunction with MICCAI 2011, in Toronto, Canada, in September 2011. The 44 revised full papers presented were carefully reviewed and selected from 74 submissions. The papers focus on major trends in machine learning in medical imaging aiming to identify new cutting-edge techniques and their use in medical imaging.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Analysis of eye gaze pattern of infants at risk of autism spectrum disorder using Markov Models

Analysis of eye gaze pattern of infants at risk of autism sp...

引用

2011 IEEE Workshop on Applications of computer vision, WACV 2011

作者： Alie, David Mahoor, Mohammad H. Mattson, Whitney I. Anderson, Daniel R. Messinger, Daniel S. University of Denver Department of Electrical and Computer Engineering Denver Co 80208 United States University of Miami Department of Psychology Coral Gables FL 33146 United States

ISBN: (纸本)9781424494965

This paper presents the possibility of using pattern recognition algorithms of infant gaze patterns at six months of age among children at high risk for an autism spectrum disorder (ASD). ASDs, which must be diagnosed by 3 years of age, are characterized by communication and interaction impairments which frequently involve disturbances of visual attention and gaze patterning. We used video cameras to record the face-to-face interactions of 32 infant subjects with their parents. The video was manually coded to determine the eye gaze pattern of infants by marking where the infant was looking in each frame (either at their parent's face or away from their parent's face). In order to identify infants ASD diagnosis at three years, we analyzed infant eye gaze patterns at six months. Variable-order Markov Models (VMM) were used to create models for typically developing comparison children as well as children with an ASD. The models correctly classified infants who did and did not develop an ASD diagnosis with an accuracy rate of 93.75 percent. Employing an assessment tool at a very young age offers the hope of early intervention, potentially mitigating the effects of the disorder throughout the rest of the child's life. © 2010 IEEE.

关键词： Video cameras

来源：评论

学校读者我要写书评

暂无评论

Artificial Intelligence and Computational Intelligence 2011

引用

丛书名： Lecture Notes in computer Science

2011年

作者： Hepu Deng Duoqian Miao Jingsheng Lei Fu Lee Wang

ISBN: (数字)9783642238963

ISBN: (纸本)9783642238956

This three-volume proceedings contains revised selected papers from the Second International Conference on Artificial Intelligence and Computational Intelligence, AICI 2011, held in Taiyuan, China, in September 2011. The total of 265 high-quality papers presented were carefully reviewed and selected from 1073 submissions. The topics of Part III covered are: machine vision; natural language processing; nature computation; neural computation; neural networks; particle swarm optimization; pattern recognition; rough set theory; and support vector machine.

关键词：

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：