检索结果-内蒙古大学图书馆

IEEE International Conference on Biometrics: Theory, Applications and Systems

作者： Choi, Hyun-Cheol Park, Unsang Jain, Anil K. Department of Brain and Cognitive Engineering Korea University Seoul Korea Republic of Department of Computer Science and Engineering Michigan State University E. Lansing MI 48824 United States

ISBN: (纸本)9781424475803

Face recognition systems typically have a rather short operating distance with standoff (distance between the camera and the subject) limited to 1∼2 meters. When these systems are used to capture face images at a larger distance (5∼10 m), the resulting images contain only a small number of pixels on the face region, resulting in a degradation in face recognition performance. To address this problem, we propose a camera system consisting of one PTZ camera and two static cameras to acquire high resolution face images up to a distance of 10 meters. We propose a novel camera calibration method based on the coaxial configuration between the static and PTZ cameras. We also use a linear prediction model and camera control to mitigate delays in image processing and mechanical camera motion. The proposed system has a larger standoff in face image acquisition and effectiveness in face recognition test. Experimental results on video data collected at a distance ranging from 5 to 10 meters of 20 different subjects as probe and 10,020 subjects as gallery shows 96.4% rank-1 identification accuracy of the proposed method compared to 0.1% rank-1 accuracy of the conventional camera system using a state-of-the-art matcher. © 2010 IEEE.

关键词： Face recognition

来源：评论

学校读者我要写书评

暂无评论

PILL-ID: Matching and retrieval of drug pill imprint images

PILL-ID: Matching and retrieval of drug pill imprint images

引用

International Conference on Pattern Recognition

作者： Lee, Young-Beom Park, Unsang Jain, Anil K. Dept. of Brain and Cognitive Engineering Korea University Seoul Korea Republic of Dept. of Computer Science and Engineering Michigan State University E. Lansing MI 48824 United States

ISBN: (纸本)9780769541099

Automatic illicit drug pill matching and retrieval is becoming an important problem due to an increase in the number of tablet type illicit drugs being circulated in our society. We propose an automatic method to match drug pill images based on the imprints appearing on the tablet. This will help identify the source and manufacturer of the illicit drugs. The feature vector extracted from tablet images is based on edge localization and invariant moments. Instead of storing a single template for each pill type, we generate multiple templates during the edge detection process. This circumvents the difficulties during matching due to variations in illumination and viewpoint. Experimental results using a set of real drug pill images (822 illicit drug pill images and 1,294 legal drug pill images) showed 76.74% (93.02%) rank-one (rank-20) matching accuracy. © 2010 IEEE.

关键词： Edge detection

来源：评论

学校读者我要写书评

暂无评论

Function over form: An identity-free dynamic facial avatar 10

Function over form: An identity-free dynamic facial avatar

引用

Proceedings of the SSPNET 2nd International Symposium on Facial Analysis and Animation

作者： Griffin, Harry J. McOwan, Peter W. Johnston, Alan Cognitive Perceptual and Brain Sciences University College London United Kingdom School of Electronic Engineering and Computer Science Queen Mary University of London United Kingdom CoMPLEX University College London United Kingdom

ISBN: (纸本)9781450305228

The degree to which facial motion is used for facial categorisation and identification is an ongoing question of great interest to psychologists. The development and choice of appropriate tools for displaying facial motion to investigate this question is a major challenge. A facial avatar in which static cues to category and identity have been removed is required. Previous solutions include point light displays or projection of motion onto a pre-formed computer-generated head or mask. These solutions may offer only sparse sampling of the rich field of facial motion or be perceived as synthetic due to unrealistic skin tone or unusual avatar shape.

关键词： Interactive computer graphics

来源：评论

学校读者我要写书评

暂无评论

View Invariant Body Pose Estimation Based on Biased Manifold Learning

View Invariant Body Pose Estimation Based on Biased Manifold...

引用

International Conference on Pattern Recognition

作者： Dongcheol Hur Christian Wallraven Seong-Whan Lee Dept. of Computer Science and Engineering Korea University Korea Dept. of Brain and Cognitive Engineering Korea University Korea

ISBN: (纸本)9781424475421

In human body pose estimation, manifold learning is a popular technique for reducing the dimension of 2D images and 3D body configuration data. This technique, however, is especially vulnerable to silhouette variation such as caused by viewpoint changes. In this paper, we propose a novel approach that combines three separate manifolds for representing variations in viewpoint, pose and 3D body configuration. We use biased manifold learning to learn these manifolds with appropriately weighted distances. A set of four mapping functions are then learned by a generalized regression neural network for added robustness. Despite using only three manifolds, we show that this method can reliably estimate 3D body poses from 2D images with all learned viewpoints.

关键词： Manifolds Three dimensional displays Estimation Image reconstruction Joints Parameter estimation Artificial neural networks

来源：评论

学校读者我要写书评

暂无评论

Two-Layer Hidden Markov Models for Multi-class Motor Imagery Classification

Two-Layer Hidden Markov Models for Multi-class Motor Imagery...

引用

Workshop on brain Decoding: Pattern Recognition Challenges in Neuroimaging (WBD)

作者： Heung-Il Suk Seong-Whan Lee Department of Computer Science and Engineering Korea University Seoul South Korea Department of Brain and Cognitive Engineering Korea University Seoul South Korea

Classifiers in a high dimensional space based on the signals of multiple electrodes in EEG-based BCIs suffer from the curse of dimensionality due to the limited training dataset. In order to tackle this problem, we design a framework of two-layer hidden Markov models (HMMs) for probabilistic classification of EEG signals. We first independently model the characteristics of EEG signals embedded in each channel for different motor imagery tasks in the lower-layer, and then represent the holistic task-related dynamic EEG patterns in the upper-layer by considering the relationships among channels. From the experimental results based on the dataset II-a of BCI Competition IV (2008), we demonstrated that our method achieved high session-to-session transfer results and was superior to previous methods.

关键词： Hidden Markov models Electroencephalography Feature extraction brain modeling Training Time domain analysis Principal component analysis

来源：评论

学校读者我要写书评

暂无评论

Sparse dictionary methods for EEG signal classification in face perception

Sparse dictionary methods for EEG signal classification in f...

引用

2010 IEEE 20th International Workshop on Machine Learning for Signal Processing, MLSP 2010

作者： Shariat, Shahriar Pavlovic, Vladimir Papathomas, Thomas Braun, Ainsley Sinha, Pawan Dept. Computer Science Rutgers University Piscataway NJ United States Dept. of Biomedical Engineering RuCCS/Lab. of Vision Research Rutgers University Piscataway NJ United States Dept. of Brain and Cognitive Sciences MIT Cambridge MA United States

ISBN: (纸本)9781424478774

This paper presents a systematic application of machine learning techniques for classifying high-density EEG signals elicited by face and non-face stimuli. The two stimuli used here are derived from the vase-faces illusion and share the same defining contours, differing only slightly in stimulus space. This emphasizes activity differences related to high-level percepts rather than low-level attributes. This design decision results in a difficult classification task for the ensuing EEG signals. Traditionally, EEG analyses are done on the basis of signal processing techniques involving multiple instance averaging and then a manual examination to detect differentiating components. The present study constitutes an agnostic effort based on purely statistical estimates of three major classifiers: L1-norm logistic regression, group lasso and k Nearest Neighbors (kNN);kNN produced the worst results. L1 regression and group lasso show significantly better performance, while being abl e to identify distinct spatio-temporal signatures. Both L1 regression and group lasso assert the saliency of samples in 170ms, 250ms, 400ms and 600ms after stimulus onset, congruent with the previously reported ERP components associated with face perception. Similarly, spatial locations of salient markers point to the occipital and temporal brain regions, previously implicated in visual object perception. The overall approach presented here can provide a principled way of identifying EEG correlates of other perceptual/cognitive tasks. ©2010 IEEE.

关键词： brain

来源：评论

学校读者我要写书评

暂无评论

PTZ camera assisted face acquisition, tracking & recognition

PTZ camera assisted face acquisition, tracking & recognition

引用

IEEE International Conference on Biometrics: Theory, Applications, and Systems (BTAS)

作者： Hyun-Cheol Choi Unsang Park Anil K. Jain Department of Brain and Cognitive Engineering Korea University Seoul South Korea Department of Computer Science and Engineering Michigan State University East Lansing MI USA

Face recognition systems typically have a rather short operating distance with standoff (distance between the camera and the subject) limited to 1~2 meters. When these systems are used to capture face images at a larger distance (5~10 m), the resulting images contain only a small number of pixels on the face region, resulting in a degradation in face recognition performance. To address this problem, we propose a camera system consisting of one PTZ camera and two static cameras to acquire high resolution face images up to a distance of 10 meters. We propose a novel camera calibration method based on the coaxial configuration between the static and PTZ cameras. We also use a linear prediction model and camera control to mitigate delays in image processing and mechanical camera motion. The proposed system has a larger standoff in face image acquisition and effectiveness in face recognition test. Experimental results on video data collected at a distance ranging from 5 to 10 meters of 20 different subjects as probe and 10,020 subjects as gallery shows 96.4% rank-1 identification accuracy of the proposed method compared to 0.1% rank-1 accuracy of the conventional camera system using a state-of-the-art matcher.

关键词： Cameras Face Face recognition Image resolution Calibration Accuracy

来源：评论

学校读者我要写书评

暂无评论

Online visual vocabulary pruning using pairwise constraints

Online visual vocabulary pruning using pairwise constraints

引用

Conference on computer Vision and Pattern Recognition (CVPR)

作者： Pavan K. Mallapragada Rong Jin Anil K. Jain Department Computer Science and Engineering Michigan State University East Lansing MI USA Department Brain and Cognitive Engineering Korea University Seoul South Korea

Given a pair of images represented using bag-of-visual-words and a label corresponding to whether the images are “related”(must-link constraint) or “unrelated” (cannot-link constraint), we address the problem of selecting a subset of visual words that are salient in explaining the relation between the image pair. In particular, a subset of features is selected such that the distance computed using these features satisfies the given pairwise constraints. An efficient online feature selection algorithm is presented based on the dual-gradient descent approach. Side information in the form of pair-wise constraints is incorporated into the feature selection stage, providing the user with flexibility to use an unsupervised or semi-supervised algorithm at a later stage. Correlated subsets of visual words, usually resulting from hierarchical quantization process (called groups), are exploited to select a significantly smaller vocabulary. A group-LASSO regularizer is used to drive as many feature weights to zero as possible. We evaluate the quality of the pruned vocabulary by clustering the data using the resulting feature subset. Experiments on PASCAL VOC 2007 dataset using 5000 visual keywords, resulted in around 80% reduction in the number of keywords, with little or no loss in performance.

关键词： Vocabulary Clustering algorithms computer science Quantization Performance loss Prototypes Large-scale systems Image retrieval Scalability Partitioning algorithms

来源：评论

学校读者我要写书评

暂无评论

PILL-ID: Matching and Retrieval of Drug Pill Imprint Images

PILL-ID: Matching and Retrieval of Drug Pill Imprint Images

引用

International Conference on Pattern Recognition

作者： Young-Beom Lee Unsang Park Anil K. Jain Department of Brain and Cognitive Engineering Korea University Seoul South Korea Department of Computer Science & Engineering Michigan State University East Lansing MI USA

ISBN: (纸本)9781424475421

关键词： Drugs Image edge detection Feature extraction Shape Databases Law

来源：评论

学校读者我要写书评

暂无评论

Liu et al. reply.

引用

Nature 2011年第7369期478卷 E4-E5页

作者： Liu, Yang-Yu Slotine, Jean-Jacques Barabási, Albert-László 1 1] Center for Complex Network Research and Departments of Physics Computer Science and Biology Northeastern University Boston Massachusetts 02115 USA Center for Cancer Systems Biology Dana-Farber Cancer Institute Boston Massachusetts 02115 USA 2 1] Nonlinear Systems Laboratory Massachusetts Institute of Technology Cambridge Massachusetts 02139 USA Department of Mechanical Engineering and Department of Brain and Cognitive Sciences Massachusetts Institute of Technology Cambridge Massachusetts 02139 USA 3 1] Center for Complex Network Research and Departments of Physics Computer Science and Biology Northeastern University Boston Massachusetts 02115 USA Department of Medicine Brigham and Women's Hospital Harvard Medical School Boston Massachusetts 02115 USA

Replying to F.-J. Müller & A. Schuppert Nature 478, 10.1038/nature10543 (2011) Müller and Schuppert1 describe an exception to our finding2 that roughly 80% of the nodes must be controlled to gain full control over gene regulatory networks. Yet our result hides subtleties that reveal as much about controllability as about the limits of our current understanding of biological networks.

关键词： Physics Applied physics and engineering

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：