检索结果-内蒙古大学图书馆

作者： Hu, Lei Wang, Yizhou Jiang, Shuqiang Huang, Qingming Gao, Wen Key Lab of Intelligent Information Processing Chinese Academy of Sciences Beijing 100080 China Institute of Computing Technology Chinese Academy of Sciences Beijing 100080 China Graduate University Chinese Academy of Sciences Beijing 100049 China Institute of Digital Media Peking University Beijing 100871 China Key Lab of Machine Perception Peking University MOE China

ISBN: (纸本)9781424421756

Many video surveillance applications require detecting human reappearances in a scene monitored by a camera or over a network of cameras. This is the human reappearance detection (HRD) problem. Studying this problem is important for analyzing a surveillance scenario at semantic level. In this paper, we propose a novel online learning frameworkfor solving HRD problem. Both generative model and discriminative model are employed in this framework and a voting scheme is presented to fuse the decisions ofboth models for determining whether a just entered person is one of those who have shown up, i.e. whether a reappearance happens. Both models will be updated based on mistake-driven online learning strategy. Our experimental results show that the adopted online learning framework not only improves the reappearance detection accuracy but also achieves high robustness in various surveillance scenes. © 2008 IEEE.

关键词： Cameras

来源：评论

学校读者我要写书评

暂无评论

Enhancing Training Set for Face Detection Based on SVM

引用

Ruan Jian Xue Bao/Journal of Software 2008年第11期19卷 2921-2931页

作者： Wang, Rui-Ping Chen, Jie Shan, Shi-Guang Chen, Xi-Lin Gao, Wen Key Laboratory of Intelligent Information Processing The Chinese Academy of Sciences Beijing 100190 China Institute of Computing Technology The Chinese Academy of Sciences Beijing 100190 China Graduate University The Chinese Academy of Sciences Beijing 100049 China School of Computer Science and Technology Harbin Institute of Technology Harbin 150001 China School of Electronics Engineering and Computer Science Peking University Beijing 100871 China

According to support vector machines (SVMs), for those geometric approach based classification methods, examples close to the class boundary usually are more informative than others. Taking face detection as an example, this paper addresses the problem of enhancing given training set and presents a nonlinear method to tackle the problem effectively. Based on SVM and improved reduced set algorithm (IRS), the method generates new examples lying close to the face/non-face class boundary to enlarge the original dataset and hence improve its sample distribution. The new IRS algorithm has greatly improved the approximation performance of the original reduced set (RS) method by embedding a new distance metric called image Euclidean distance (IMED) into the kernel function. To verify the generalization capability of the proposed method, the enhanced dataset is used to train an AdaBoost-based face detector and test it on the MIT+CMU frontal face test set. The experimental results show that the original collected database can be enhanced effectively by the proposed method to learn a face detector with improved generalization performance.

关键词： Support vector machines

来源：评论

学校读者我要写书评

暂无评论

Face reconstruction using fixation positions and foveated imaging

Face reconstruction using fixation positions and foveated im...

引用

International Conference on Automatic Face and Gesture Recognition

作者： Fang Fang Zhiguo Ma Laiyun Qing Jun Miao Xilin Chen Wen Gao Harbin Institute of Technology School of Computer Science and Technology China Institute of Computing Technology CASKey Laboratory of Intelligent Information Processing Chinese Academy and Sciences Beijing China Graduate School of Chinese Academy of Sciences Beijing China Institute for Digital Media Peking University China

Face representation is important for face recognition system. Though most popular face representations are based on uniform grid sampling, some recent face recognition systems adopt weighted sampling on the different regions of a face. Psychological analysis of visual attention or human eye fixations on human face images may suggest some cues for face representation. human visual system (HVS) gives different weight to different region of human face via space-variant sampling on fovea and non-uniform distribution of fixations. This paper focuses on the problem of simulation of the foveated imaging phenomenon in HVS, and introduction of foveated imaging method into reconstruction of face in region of interest (ROI) using different fixation sources. We compare the effectiveness of actual fixation on reconstruction of face in ROI with uniform, random distribution fixation as well as fixation generated by artificial model. The experimental results on 100 face images from FRGC [7] data set show that actual fixation positions and model-generated fixation positions reconstruct the face in ROI with considerably better quality. A further analysis on the statistics of fixation positions also shows that the distribution of the fixation points is consistent with the weights of different regions on face images used in some other face recognition systems.

关键词： Image reconstruction Humans Face recognition Layout Content addressable storage Image sampling Psychology Image analysis Statistical analysis Video compression

来源：评论

学校读者我要写书评

暂无评论

A Novel Fuzzy Likelihood Measure Algorithm

A Novel Fuzzy Likelihood Measure Algorithm

引用

International Conference on Computer Science and Software Engineering

作者： Shifei Ding Fengxiang Jin School of Computer Science and Technology China China University of Mining and Technology Xuzhou China Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy and Sciences Beijing China College of Geoinformation Science and Engineering Shandong University of Science and Technology Qingdao China

ISBN: (纸本)9781424439027

Similarity measure (PSM) is a kind of measurement that measure the size of similarity between two patterns, it plays a key role in the analysis and research of pattern recognition, machine learning, clustering analysis. This article will firstly study the current PSM theory, point out its application range; secondly, discuss the axiomatic theory of fuzzy likelihood measure, give the frequently-used algorithms of fuzzy likelihood measure that based on axiomatic theory; finally, advance a new kind of fuzzy likelihood function, then establish the fuzzy likelihood measure(FLM) between two fuzzy sets, so as to describe the similar degree between two fuzzy sets. FLM theory not only enriches and improves the PLS theory, and also provides new research methods for the theory research such as pattern recognition, machine learning, clustering analysis and so on.

关键词： Fuzzy sets Pattern recognition Fuzzy set theory Pattern analysis Size measurement Software measurement Fuzzy systems Current measurement Computer science information processing

来源：评论

学校读者我要写书评

暂无评论

Hierarchical background subtraction using local pixel clustering

Hierarchical background subtraction using local pixel cluste...

引用

International Conference on Pattern Recognition

作者： Bineng Zhong Hongxun Yao Shiguang Shan Xilin Chen Wen Gao Department of Computer Science and Engineering Harbin Institute of Technology Digital Media Research Center Institute of Computing Technology Chinese Academy of Sciences Beijing China Key Laboratory of Intelligent Information Processing Chinese Academy and Sciences Beijing China Digital Media Institute Peking University Beijing China

ISBN: (纸本)9781424421749

We propose a robust hierarchical background subtraction technique which takes the spatial relations of neighboring pixels in a local region into account to detect objects in difficult conditions. Our algorithm combines a per-pixel with a per-region background model in a hierarchical manner, which accentuates the advantages of each. This is a natural combination because the two models have complementary strengths. The per-pixel background model is achieved by mixture of Gaussians models (GMM) with RGB feature. Although precisely describing background change in high resolution, it suffers from the sensitivity to quick variations in dynamic environment. To tolerate these quick variations, we further develop a novel GMM based per-region background model, which is updated by the cluster centers obtained from a k-means clustering of the pixelspsila RGB feature in the region. Numerical and qualitative experimental results on challenging videos demonstrate the robustness of the proposed method.

关键词： Autoregressive processes Robustness Object detection Videos Layout Smart pixels Content addressable storage Gaussian processes Lighting Cameras

来源：评论

学校读者我要写书评

暂无评论

Parzen Discriminant Analysis

Parzen Discriminant Analysis

引用

International Conference on Pattern Recognition

作者： Youhan Fang Shiguang Shan Hong Chang Xilin Chen Wen Gao Chinese Academy of Sciences Beijing China Digital Media Research Center Institute of Computing Technology Chinese Academy of Sciences Beijing China Key Laboratory of Intelligent Information Processing CAS Beijing China Digital Media Institute Peking University Beijing China

ISBN: (纸本)9781424421749

In this paper, we propose a non-parametric discriminant analysis method (no assumption on the distributions of classes), called Parzen discriminant analysis (PDA). Through a deep investigation on the non-parametric density estimation, we find that minimizing/maximizing the distances between each data sample and its nearby similar/dissimilar samples is equivalent to minimizing an upper bound of the Bayesian error rate. Based on this theoretical analysis, we define our criterion as maximizing the average local dissimilarity scatter with respect to a fixed average local similarity scatter. All local scatters are calculated in fixed size local regions, resembling the idea of Parzen estimation. Experiments in UCI machine learning database show that our method impressively outperforms other related neighbor based non-parametric methods.

关键词： Error analysis Scattering Upper bound Linear discriminant analysis information analysis Bayesian methods Gaussian distribution Personal digital assistants Content addressable storage Performance analysis

来源：评论

学校读者我要写书评

暂无评论

Hallucinating facial images and features

Hallucinating facial images and features

引用

International Conference on Pattern Recognition

作者： Bo Li Hong Chang Shiguang Shan Xilin Chen Wen Gao Harbin Institute of Technology Harbin China Institute of Computing Tech. CAS Digital Media Research and Development Center Beijing China Key Laboratory of Intelligent Information Processing Chinese Academy and Sciences Beijing China Digital Media Institute Peking University Beijing China

ISBN: (纸本)9781424421749

In facial image analysis, image resolution is an important factor which has great influence on the performance of face recognition systems. As for low-resolution face recognition problem, traditional methods usually carry out super-resolution firstly before passing the super-resolved image to a face recognition system. In this paper, we propose a new method which predicts high-resolution images and the corresponding features simultaneously. More specifically, we propose ldquofeature hallucinationrdquo to project facial images with low-resolution into an expected feature space. As a result, the proposed method does not require super-resolution as an explicit preprocessing step. In addition, we explore a constrained hallucination that considers the local consistency in the image grid. In our method, we use the index of local visual primitives as features and a block-based histogram distance to measure the similarity for the face recognition. Experimental results on FERET face database verify that the proposed method can improve both visual quality and recognition rate for low-resolution facial images.

关键词： Face recognition Image resolution Strontium Image reconstruction Image analysis Content addressable storage Image recognition Interpolation Face detection Rendering (computer graphics)

来源：评论

学校读者我要写书评

暂无评论

An Innovative Tempo Model for Movie Content Analysis

An Innovative Tempo Model for Movie Content Analysis

引用

IEEE International Conference on Networking, Sensing and Control

作者： Anan Liu Zhaoxuan Yang Jiapeng Wu Yongdong Zhang Jintao Li School ofElectronic Engineering Tianjin University TJU Tianjin China Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy and Sciences Beijing China Tianjin University TJU China ICT Chinese Academy and Sciences China

The paper presents a novel tempo model for movie content analysis. We originally propose that tempo indicates the rhythm of both movie scenarios and human perception and focus on the low level features extraction to represent both aspects. By thoroughly analyzing them, we classify the factors of tempo into two sorts. The first is based on the film grammar and we use the low level features of shot length and camera motion to describe filmmaking by directors. The second is based on the human perception and the low level features of motion intensity, motion complexity, audio energy and audio pace are integrated for the formulation of information to describe the viewers' emotional changes to continuously developing storyline. With both factors, tempo is defined and tempo flow plot is derived as the clue of storyline. Then we implement the tempo model for Action scene detection and build a system, SmartMovirPlayer, for hierarchical browse and edit with action concept annotation. The large-scale experiments demonstrate the effectiveness of the tempo model for movie content analysis.

关键词： Motion pictures Humans Layout Performance analysis Rhythm Feature extraction Cameras Large-scale systems technology planning Laboratories

来源：评论

学校读者我要写书评

暂无评论

Locally Assembled Binary (LAB) Feature with Feature-centric Cascade for Fast and Accurate Face Detection

Locally Assembled Binary (LAB) Feature with Feature-centric ...

引用

26th IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2008), vol.11

作者： Shengye Yan Shiguang Shan Xilin Chen Wen Gao Key Lab of Intelligent Information Processing Chinese Academy and Sciences Beijing China Key Lab of Intelligent Information Processing Chinese Academy of Sciences (CAS) Beijing China School of EE& Peking University Beijing China Digital Media Research Center Institute of Computing Technology Chinese Academy and Sciences Beijing China

In this paper, we describe a novel type of feature for fast and accurate face detection. The feature is called Locally Assembled Binary (LAB) Haar feature. LAB feature is basically inspired by the success of Haar feature and Local Binary Pattern (LBP) for face detection, but it is far beyond a simple combination. In our method, Haar features are modified to keep only the ordinal relationship (named by binary Haar feature) rather than the difference between the accumulated intensities. Several neighboring binary Haar features are then assembled to capture their co-occurrence with similar idea to LBP. We show that the feature is more efficient than Haar feature and LBP both in discriminating power and computational cost. Furthermore, a novel efficient detection method called feature-centric cascade is proposed to build an efficient detector, which is developed from the feature-centric method. Experimental results on the CMU+MIT frontal face test set and CMU profile test set show that the proposed method can achieve very good results and amazing detection speed.

关键词： Assembly Face detection Computer vision Detectors Content addressable storage Computational efficiency Testing intelligent robots Humans Skin

来源：评论

学校读者我要写书评

暂无评论

RESEARCH OF PATTERN FEATURE EXTRACTION AND SELECTION

RESEARCH OF PATTERN FEATURE EXTRACTION AND SELECTION

引用

2008 International Conference on Machine Learning and Cybernetics(2008机器学习与控制论国际会议)

作者： SHI-FEI DING WEI-KUAN JIA CHUN-YANG SU ZHONG-ZHI SHI School of Computer Science and Technology China University of Mining and Technology Xuzhou 221008 College of Plant Protection Shandong Agricultural University Taian 271018 China School of Computer Science and Technology China University of Mining and Technology Xuzhou 221008 Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Aca

As an important link of pattern recognition, pattern feature extraction and selection has been paid close attention by lots of scholars, and currently become one of the research hot spot in the field of pattern recognition. Its main purpose is "Low Loss Dimensionality Reduction";it is generally divided into two parts, that is, linear pattern feature extraction and selection and nonlinear pattern feature extraction and selection. This article gives a general discussion of pattern feature extraction and selection, and introduces the frontier methods of this field, at last discusses the development tendency of pattern feature extraction and selection.

关键词： Pattern Feature Eztraction information Theory Neural Network Independent Component Analysis Manifold Learning Optimization 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：