检索结果-内蒙古大学图书馆

13th International Conference on Wireless communications and Signal processing, WCSP 2021

作者： Yang, Qian Liu, Feng Zhao, Zhenglai Nanjing University of Posts and Telecommunications Nanjing China Nanjing University of Posts and Telecommunications Jiangsu Key Lab of Image Processing Image Communications Nanjing China

ISBN: (纸本)9781665407854

In view of the fact that the proportion of face in the whole image is small and the face posture is skew, which leads to the low accuracy of facial expression recognition, this paper proposes a two-branch neural network based on attention mechanism and length feature of facial landmark. The first branch is based on the modified VGG19 and the integration of the convolutional block attention module (CBAM), which focuses on the extraction of important features of expression. The second branch extracts 68 feature points from the face image, and calculates the Euler distance between these feature points to acquire the length information of 2278 dimensions, and is finally normalized and fed into the full connection layer. The network composed of the first branch and the second branch is trained by joint fine-tuning, where L2 regularization is added to prevent overfitting. The proposed method is tested and verified on Jaffe, CK + and FER +, and the highest accuracy is 93.48%,96.12% and 84.73% respectively. The performance of the proposed method is more advance than many existing algorithms, which shows that the proposed model has good accuracy and robustness. © 2021 IEEE.

关键词： Face recognition

来源：评论

学校读者我要写书评

暂无评论

A novel ant colony based cross-layer QoS routing algorithm for wireless mesh networks

A novel ant colony based cross-layer QoS routing algorithm f...

引用

2008 11th IEEE International Conference on Communication Technology, ICCT 2008

作者： Hui, Zhang Yu-Ning, Dong Long-Xiang, Yang Hong-Bo, Zhu Jiangsu Provincial Key Lab. of Wireless Communications College of Communication and Information Engineering Nanjing University of Posts and Telecommunications Nanjing 210003 China Jiangsu Provincial Key Lab. of Image Processing and Image Communication College of Communication and Information Engineering Nanjing University of Posts and Telecommunications Nanjing 210003 China

ISBN: (纸本)9781424422517

According to the heterogeneous characteristics of wireless mesh networks and the QoS requirements of multimedia applications, we design a novel QoS adaptive architecture for WMNs that is cross-domain, cross-layer and cross-node. Furthermore, this architecture is mathematically described by using a bi-level programming model. This model uses the optimization results of subnets as the optimization parameters or optimization constraints of backbone networks, and combines the features of different network domains. Based on this bi-level programming model, we propose an ant colony optimization based routing algorithm. Simulation results show that the bi-level programming model, which fully optimizes various QoS parameters of paths, can effectively adapt to the heterogeneous characteristics of WMNs so as to obtain the optimal path;the proposed routing algorithm, which has both advantages of low complexity and fast convergence speed, can converge to the theoretical optimal solution of bi-level programming model. © 2008 IEEE.

关键词： Routing algorithms

来源：评论

学校读者我要写书评

暂无评论

Optimal approximation of head-related transfor function based on adaptive genetic algorithm

Optimal approximation of head-related transfor function base...

引用

2008 IEEE International Conference Neural Networks and Signal processing, ICNNSP

作者： Xuelong, Hu Yan, Tang Jun, Cai School of Information Engineering Yangzhou University Yangzhou Jiangsu 225009 China Jiangsu Province Key Lab. for Image Processing and Image Communication Nanjing University of Posts and Communications Nanjing Jiangsu 210003 China

ISBN: (纸本)9781424423118

Head-related Transfer Functions (HRTFs) refer to the spectral filtering from sound sources to listeners' eardrums or ear canals. As an effective model structure, the degree of the IIR filter approximation of the HRTFs, whose design and implementation is a specific spectrum function approximation process, is much lower than that of the FIR. Based on the assessment of HRTFs different importance for sound sources recognition in different spectrum bands, and associated with some perspectives of psychoacoustics in spatial hearing, adaptive and revalued coding genetic algorithm (GA) is applied to the approximation of the HRTFs zero-pole model. The results show that, on an average, the performance of adaptive GA is better than that of the traditional GA. ©2008 IEEE.

关键词： Transfer functions

来源：评论

学校读者我要写书评

暂无评论

Appearance model based moving object matching across disjoint camera views

引用

2nd International Conference on Opto-Electronics Engineering and Materials Research, OEMR 2013

作者： Yu, Kong Shuai Hu, Dong Education Ministry's Key Lab of Broadband Wireless Communication and Sensor Network Technology The key lab of image processing and image communications of Jiangsu Province Nanjing University of Posts and Telecom Nanjing 210003 China

ISBN: (纸本)9783037857731

A new object tracking scheme for multi-camera surveillance with non-overlapping views is proposed in this paper. Brightness transfer function (BTF) is used to establish relative appearance correspondence between different views. Mixtures of probabilistic principal component analysis (MPPCA) is incooperated to learn the subspace of brightness transfer function with the concern to deal with multiple different brightness areas in a scene. The incremental major color spectrum histogram (IMCSH) is used as similarity measure for reliable matching. Experimental results with real world videos show the effectiveness of the proposed algorithm. © (2013) Trans Tech Publications, Switzerland.

关键词： Luminance

来源：评论

学校读者我要写书评

暂无评论

A NOVEL METHOD TO REALIZE COMPRESSED VIDEO SUPER-RESOLUTION RECONSTRUCTION

引用

Journal of Electronics(China) 2006年第2期23卷 310-313页

作者： Zhou Liang Liu Feng Zhu Xiuchang Information Industry Ministry and Jiangsu Province Key Lab of lmage Processing and Image Communication Nanjing University of Posts and Communications Nanjing 210003 China

This letter proposes a novel method of compressed video super-resolution reconstruction based on MAP-POCS (Maximum Posterior Probability-Projection Onto Convex Set). At first assuming the high-resolution model subject to Poisson-Markov distribution, then constructing the projecting convex based on MAP. According to the characteristics of compressed video, two different convexes are constructed based on integrating the inter-frame and intra-frame information in the wavelet-domain. The results of the experiment demonstrate that the new method not only outperforms the traditional algorithms on the aspects of PSNR (Peak Signal-to-Noise Ratio), MSE (Mean Square Error) and reconstruction vision effect, but also has the advantages of rapid convergence and easy extension.

关键词： Super-resolution Compressed video image reconstruction MAP-POCS

来源：评论

学校读者我要写书评

暂无评论

Mixed image de-noising method of Bayesian estimation and wavelet based on alpha-stable distribution

Mixed image de-noising method of Bayesian estimation and wav...

引用

2008 IEEE International Conference Neural Networks and Signal processing, ICNNSP

作者： Zhijian, Wang Xuelong, Hu Cheng, Li Liping, Wang School of Information Engineering Yangzhou University Yangzhou Jiangsu 225009 China Jiangsu Province Key Lab. for Image Processing and Image Communication Nanjing University of Posts and Communications Nanjing Jiangsu 210003 China Yangzhou Jiangsu 225001 China

ISBN: (纸本)9781424423118

This paper introduces a new kind of recovery method which is the combination of Bayesian estimation and wavelet threshold. Wavelet coefficients of signals show strong characteristics of the non-Gauss statistics, its probability density function can be modeled by alpha-stable priori distribution. This paper uses Bayesian estimation to obtain the low frequency coefficients, and deals with high frequency coefficients with the wavelet soft threshold, then restore signal by wavelet inverse transform. Bayesian estimation well retains the marginal information of signals, but the signal is still not very smooth recovery and wavelet soft threshold can maintain smooth characteristic. The mixed noise elimination methods of Bayesian estimation and wavelet enhance the peak SNR much greater than wavelet threshold, which has better recovery effect. ©2008 IEEE.

关键词： Probability density function

来源：评论

学校读者我要写书评

暂无评论

A Novel Method to Get Super-Resolution images from Low-Resolution Compressed Video

引用

The Journal of China Universities of Posts and Telecommunications 2005年第2期12卷 50-54页

作者： ZHOU Liang ZHU Xiu-chang Information Industry Ministry and Jiangsu Province Key Lab of Image Processing and Image Communication Nanjing University of Posts and Communications Nanjing 210003 P. R. China

In order to resolve the problems of discontented restoration effect and confined applying scope which exist in the current compressed video restoration algorithms, a novel method to get super-resolution images from low-resolution compressed video is proposed in this paper. At first, a uniform model is presented and the restoration problem in the Bayesian framework is formulated under the MAP criterion, then the focus is put on the hybrid motion-compensation and transform coding schemes, at last the methods of getting the parameters are provided. The results of the simulation clearly demonstrate that our method not only has the properties of finer vision effect and wider applying scope, but also performs better than those of current classical algorithms in the aspects of Peak Signal Noise Ratio （PSNR） under the basis of the same condition.

关键词： super-resolutlon compressed video restoration

来源：评论

学校读者我要写书评

暂无评论

Approaches to image retrieval using fuzzy set theory

Approaches to image retrieval using fuzzy set theory

引用

2008 IEEE International Conference Neural Networks and Signal processing, ICNNSP

作者： Li, Yang Xuelong, Hu Jun, Pan School of Information Engineering Yangzhou University Yangzhou Jiangsu 225009 China Jiangsu Province Key Lab. for Image Processing and Image Communication Nanjing University of Posts and Communications Nanjing Jiangsu 210003 China Jiangsu Prov. Key Lab. for Computer Information Processing Technology Suzhou University Suzhou Jiangsu 215006 China

ISBN: (纸本)9781424423118

This paper mainly presents two approaches for image retrieval. There is some faintness in color locating in quantification boundary when image color is quantized. The membership function in fuzzy set theory can describe the fuzzy transition preferably. In this paper, the membership function in HSI color space is adopted to solve the problem above. At the same time, spatial information is integrated with color feature to describe the image content more truly. Due to the importance of texture feature, gray concurrence matrix is extracted. In the second part of this paper, retrieval scheme combining four image feature descriptors is presented, and then follows Fuzzy Hamming Distance (FHD) which is used as a fuzzy similarity measure. We have performed an experiment on a 1000 images database and our results show higher retrieval accuracy. © 2008 IEEE.

关键词： Fuzzy sets

来源：评论

学校读者我要写书评

暂无评论

Video object matching based on sift algorithm

Video object matching based on sift algorithm

引用

2008 IEEE International Conference Neural Networks and Signal processing, ICNNSP

作者： Xuelong, Hu Yingcheng, Tang Zhenghua, Zhang School of Information Engineering Yangzhou University Yangzhou Jiangsu 225009 China Jiangsu Prov. Key Lab for Image Processing and Image Communication Nanjing University of Posts and Communications Nanjing Jiangsu 210003 China Jiangsu Prov. Key Lab. for Computer Information Processing Technology Suzhou University Suzhou Jiangsu 215006 China

ISBN: (纸本)9781424423118

SIFT (Scale Invariant Feature Transform) is used to solve visual tracking problem, where the appearances of the tracked object and scene background change during tracking. The implementation of this algorithm has five major stages: scale-space extrema detection;keypoint localization;orientation assignment;keypoint descriptor;keypoint matching. From the beginning frame, object is selected as the template, its SIFT features are computed. Then in the following frames, the SIFT features are computed. Euclidean distance between the object's SIFT features and the frames' SIFT features can be used to compute the accurate position of the matched object. The experimental results on real video sequences demonstrate the effectiveness of this approach and show this algorithm is of higher robustness and real-time performance. It can solve the matching problem with translation, rotation and affine distortion between images. It plays an important role in video object tracking and video object retrieval. © 2008 IEEE.

关键词： Tracking (position)

来源：评论

学校读者我要写书评

暂无评论

Robust blind watermark algorithm of color image based on neural network

Robust blind watermark algorithm of color image based on neu...

引用

2008 IEEE International Conference Neural Networks and Signal processing, ICNNSP

作者： Xuelong, Hu Xu, Lian Lin, Chen Yongai, Zheng School of Information Engineering Yangzhou University Yangzhou Jiangsu 225009 China Jiangsu Province Key Lab. for Image Processing and Image Communication Nanjing University of Posts and Communications Nanjing Jiangsu 210003 China Shanghai University of Electrical Power Shanghai 200090 China

ISBN: (纸本)9781424423118

A new algorithm of color image blind watermarking based on BP neural network and wavelet significant tree is proposed. In YCbCr, the luminance component is decomposed with wavelet, and the wavelet significant tree can be found. Then the correlativity among nodes of wavelet significant tree is described by the nonlinear relationship responded by the trained BP neural network. Based on the relationship, the watermark is embedded into wavelet significant trees. Finally, the embedded watermark can be extracted without original image. The experimental results show that the embedded watermark can be extracted preferably in some common attacks, and this algorithm has better transparency and stronger robustness with some comparisons to other algorithms. © 2008 IEEE.

关键词： Neural networks

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：