检索结果-内蒙古大学图书馆

LPQ based static and dynamic modeling of facial expressions in 3D videos

2012 International Conference on Service-Oriented Computing, ICSOC 2012

作者： Zhen, Qingkai Huang, Di Wang, Yunhong Chen, Liming Laboratory of Intelligent Recognition and Image Processing School of Computer Science and Engineering Beihang University Beijing China Ecole Centrale de Lyon LIRIS UMR5205 F-69134 Lyon France

ISBN: (纸本)9783319029603

Automatic Facial Expression recognition (FER) is one of the most active topics in the domain of computer vision and pattern recognition. In this paper, we focus on discrete facial expression recognition by using 4D data (i.e. 3D range image sequences), and present a novel method to address such an issue. The Local Phase Quantisation from Three Orthogonal Planes (LPQ-TOP) descriptor is applied to extract both the static and dynamic clues conveyed in facial expressions. On the one hand, it locally captures the shape attributes in each 3D face model (facial range image). On the other hand, it detects the latent temporal information and represents dynamic changes occurred in facial muscle actions. The SVM classifier is finally used to predict the expression type. The experiments are carried out on the BU-4DFE database, and the achieved results demonstrate the effectiveness of the proposed method. © Springer International Publishing 2013.

关键词： Face recognition

来源：评论

学校读者我要写书评

暂无评论

Support value based fusing images with different focuses

Support value based fusing images with different focuses

引用

International Conference on Machine Learning and Cybernetics, ICMLC 2005

作者： Zheng, Sheng Sun, Yu-Qiu Tian, Jin-Wen Liu, Jian China Three Gorges University Yichang 443002 China Key Laboratory for Image Processing and Intelligent Control Institute of Pattern Recognition and Artificial Intelligence Huazhong University of Science and Technology Wuhan 430074 China

ISBN: (纸本)078039092X

Many vision-related processing tasks, including edge detection and image segmentation, can be performed more easily when all objects in the scene are in good focus. However, in practice, this may not be always feasible as optical lenses, especially those with long focal lengths, only have a limited depth of field. One classical approach to recover an everywhere-in-focus image is to use Laplacian pyramid image fusion. First, several source images with different focuses of the same scene are taken and decomposed into the low/high-frequency components image sequences. Within these decompositions, the high-frequency components image sequences with the largest magnitude are selected at each pixel location. Finally, the fused image can be recovered from the decomposed components image sequences. In the support vector machine (SVM), the pixels with larger support values have a physical meaning in the sense that they reveal relative more importance of the data points for contributing to the SVM model. In this paper, we use Laplacian pyramid for the multiresolution decomposition, and then replace the traditional salient features by support values of the mapped least squares (LS)-SVM for fusing image. Experimental results illustrate that the proposed method outperforms the traditional approach. ©2005 IEEE.

关键词： image segmentation

来源：评论

学校读者我要写书评

暂无评论

A DSP/FPGA -based parallel architecture for real-time image processing

A DSP/FPGA -based parallel architecture for real-time image ...

引用

6th World Congress on intelligent Control and Automation, WCICA 2006

作者： Luxin, Yan Tianxu, Zhang Sheng, Zhong Institute of Pattern Recognition and Artificial Intelligence Huazhong University of Science and Technology Wuhan 430074 China Key Laboratory for Image Processing and Intelligent Control Huazhong University of Science and Technology Wuhan 430074 China

ISBN: (纸本)1424403324

DSP/FPGA-based parallel architecture oriented to real-time image processing applications is presented. The architecture is structured with high performance DSPs interconnected by FPGA. Within FPGA a FIFO interconnection network and the specific data communication protocol are implemented, which interconnect 3 DSPs (TMS320C6414) effectively. The measured performances in the prototype with the proposed parallel architecture, including inter-DSP data communication performance and system computing capacity, show high data transfer bandwidth (up to 400 Mbytes/s) with low latency as well as high image processing performance, which achieve a good balance for parallel image processing. © 2006 IEEE.

关键词： Digital signal processing

来源：评论

学校读者我要写书评

暂无评论

A FAST ADAPTIVE SPATIO-TEMPORAL 3D FEATURE FOR VIDEO-BASED PERSON RE-IDENTIFICATION

A FAST ADAPTIVE SPATIO-TEMPORAL 3D FEATURE FOR VIDEO-BASED P...

引用

IEEE International Conference on image processing

作者： Zheng Liu Jiaxin Chen Yunhong Wang Laboratory of Intelligent Recognition and Image Processing School of Computer Science and Engineering Beihang University

ISBN: (纸本)9781467399623

Video-based person re-identification has become a hot topic in the field of research on computer vision and intelligent surveillance, which is more robust to the variations in a person's appearance than single-shot based methods and involves space-time information. However, the most existing spatiotemporal features have been proposed for action recognition that they mainly focus on the exact spatial changes over time. Unlike action recognition, pedestrians captured in person re-identification problem show similar and cyclic walking activities. The essential spatio-temporal information for person re-identification is the statistical information over time. In this paper, we propose a novel spatio-temporal feature, namely Fast Adaptive Spatio-Temporal 3D feature (FAST3D), for video-based person re-identification. The feature is able to extract the statistical motion information based on densely computed multi-direction gradients and an adaptive fusion process. We evaluate our method on two challenging datasets and the experimental results show the effectiveness and efficiency of the proposed feature.

关键词： Person re-identification Spatio-temporal feature Efficient computation Relevance metric learning

来源：评论

学校读者我要写书评

暂无评论

ACTION recognition BASED ON KINEMATIC REPRESENTATION OF VIDEO DATA

ACTION RECOGNITION BASED ON KINEMATIC REPRESENTATION OF VIDE...

引用

IEEE International Conference on image processing

作者： Xin Sun Di Huang Yunhong Wang Jie Qin Laboratory of Intelligent Recognition and Image Processing School of Computer Science and Engineering Beihang University

ISBN: (纸本)9781479957521

The local space-time feature is an effective way to represent video data and achieves state-of-the-art performance in action recognition. However, in majority of cases, it only captures the static or dynamic cues of the image sequence. In this paper, we propose a novel kinematic descriptor, namely Static and Dynamic fEature Velocity (SDEV), which models the changes of both static and dynamic information with time for action recognition. It is not only discriminative itself, but also complementary to the existing descriptors, thus leading to more comprehensive representation of actions by their combination. Evaluated on two public databases, i.e. UCF sports and Olympic Sports, the results clearly illustrate the competency of SDEV.

关键词： Action recognition Kinematic description Motion feature

来源：评论

学校读者我要写书评

暂无评论

Feature Selection Based on Adaptive Fuzzy Membership Functions

引用

自动化学报 2006年第4期32卷 496-503页

作者： XIE Yan-Tao SANG Nong ZHANG Tian-Xu Institute for Pattern Recognition and Artificial Intelligence Huazhong University of Science and Technology Wuhan 430074 Key Laboratory of Ministry of Education for Image Processing and Intelligent Control Huazhong University of Science and Technology Wuhan 430074

Neuro-fuzzy(NF)networks are adaptive fuzzy inference systems(FIS)and have been applied to feature selection by some ***,their rule number will grow exponentially as the data dimension *** the other hand,feature selection algorithms with artificial neural networks(ANN)usually require normalization of input data,which will probably change some characteristics of original data that are important for *** overcome the problems mentioned above,this paper combines the fuzzification layer of the neuro-fuzzy system with the multi-layer perceptron(MLP)to form a new artificial neural ***,fuzzification strategy and feature measurement based on membership space are proposed for feature selection. Finally,experiments with both natural and artificial data are carried out to compare with other methods,and the results approve the validity of the algorithm.

关键词： Membership function feature selection architecture pruning artificial neural networks

来源：评论

学校读者我要写书评

暂无评论

Background suppression based-on wavelet transformation to detect infrared target

Background suppression based-on wavelet transformation to de...

引用

International Conference on Machine Learning and Cybernetics, ICMLC 2005

作者： Sun, Y.U.-Qiu Tian, Jin-Wen Liu, Jian School of Information and Mathematics Yangtze University Jingzhou 434023 China State Education Commission Key Laboratory for Image Processing and Intelligent Control Institute for Pattern Recognition and Artificial Intelligence Huazhong University of Science and Technology Wuhan 430074 China State Education Commission Key Laboratory for Image Processing and Intelligent Control Dept. of Electronic Information and Enginery Huazhong University of Science and Technology Wuhan China

ISBN: (纸本)078039092X

Target detection and location in infrared clutter background is very important to infrared search and track system. Especially for small target detection in infrared image in background of sea and sky, there are no geometric and structure character to use. When targets such as ship and naval vessel sailing at long distance, they always appear around the sea-level line, and it is mixed with cloud and sea-wave clutter. It is difficult to segment and locate precisely. Background suppression based-on wavelet transformation is proposed in the paper. Wavelet decomposition makes it possible to analyze a signal both in time and frequency domains. In the paper infrared sea and key background images are processed. For their SNR is low and background is complex, using wavelet transformation decomposes an original image and extract approximate feature to reconstruct an image, which mainly includes background information. A new image will be obtained using background image subtracted from original image. There are mainly target and noise points left in the new image. By setting proper threshold, the target can be detected perfectly. At last, experiment results are given and show the method is practical. © 2005 IEEE.

关键词： Pattern recognition

来源：评论

学校读者我要写书评

暂无评论

A cross-domain person re-identification algorithm based on distribution-consistency and multi-label collaborative learning

引用

Multimedia Tools and Applications 2024年第38期83卷 85939-85962页

作者： Zhang, Baohua Hao, Chen Lv, Xiaoqi Gu, Yu Wang, Yueming Liu, Xin Ren, Yan Li, Jianjun School of Information Engineering Inner Mongolia University of Science and Technology Inner Mongolia Baotou014010 China School of Information Engineering Mongolia Industrial University Inner Mongolia Huhehaote010051 China Inner Mongolia Key Laboratory of Pattern Recognition and Intelligent Image Processing Inner Mongolia Baotou014010 China

To decrease domain shift in cross-domain person re-identification, existing methods generate pseudo labels for training models, however, the inherent distribution between source domain data and the hard quantization loss is ignored. Therefore, a cross-domain person re-identification method based on distribution consistency and multi-label collaborative learning is proposed. Firstly, a soft binary cross-entropy loss function is constructed to constrain the inter-sample relationship of cross-domain transformation, which can ensure the consistency of appearance features and sample distribution, and achieving feature cross-domain alignment. On this basis, in order to suppress the noise of hard pseudo labels, a multi-label collaborative learning network is constructed. The soft pseudo labels are generated by using the collaborative foreground features and global features to guide the network training, making the model adapt to the target domain. The experimental results show that the proposed method has better performance than that of recent representative methods. © The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2024.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

Adaptive thresholding of digital subtraction angiography images

Adaptive thresholding of digital subtraction angiography ima...

引用

MIPPR 2005: image Analysis Techniques

作者： Sang, Nong Li, Heng Peng, Weixue Zhang, Tianxu Institute for Pattern Recognition and Artificial Intelligence Huazhong University of Science and Technology Wuhan 430074 China Key Laboratory Ministry of Education for Image Processing and Intelligent Control Huazhong University of Science and Technology Wuhan 430074 China

In clinical practice, digital subtraction angiography (DSA) is a powerful technique for the visualization of blood vessels in the human body. Blood vessel segmentation is a main problem for 3D vascular reconstruction. In this paper, we propose a new adaptive thresholding method for the segmentation of DSA images. Each pixel of the DSA images is declared to be a vessel/background point with regard to a threshold and a few local characteristic limits depending on some information contained in the pixel neighborhood window. The size of the neighborhood window is set according to a priori knowledge of the diameter of vessels to make sure that each window contains the background definitely. Some experiments on cerebral DSA images are given, which show that our proposed method yields better results than global thresholding methods and some other local thresholding methods do.

关键词： image analysis

来源：评论

学校读者我要写书评

暂无评论

3D reconstruction of the coronary tree from two X-ray angiographic views

3D reconstruction of the coronary tree from two X-ray angiog...

引用

Medical Imaging 2006: image processing

作者： Sang, Nong Peng, Weixue Li, Heng Zhang, Zhen Zhang, Tianxu Institute for Pattern Recognition and Artificial Intelligence Huazhong University of Science and Technology Wuhan 430074 China Key Laboratory Ministry of Education for Image Processing and Intelligent Control Huazhong University of Science and Technology Wuhan 430074 China

ISBN: (纸本)0819464236

In this paper, we develop a method for the reconstruction of 3D coronary artery based on two perspective projections acquired on a standard single plane angiographic system in the same systole. Our reconstruction is based on the model of generalized cylinders, which are generated by sweeping a two-dimensional cross section along an axis in three-dimensional space. We restrict the cross section to be circular and always perpendicular to the tangent of the axis. Firstly, the vascular centerlines of the X-ray angiography images on both projections are semiautomatically extracted by multiscale vessel tracking using Gabor filters, and the radius of the coronary are also acquired simultaneously. Secondly, the relative geometry of the two projections is determined by the gantry information and 2D matching is realized through the epipolar geometry and the consistency of the vessels. Thirdly, we determine the three-dimensional (3D) coordinates of the identified object points from the image coordinates of the matched points and the calculated imaging system geometry. Finally, we link the consequent cross sections which are processed according to the radius and the direction information to obtain the 3D structure of the artery. The proposed 3D reconstruction method is validated on real data and is shown to perform robustly and accurately in the presence of noise.

关键词： image reconstruction

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：