检索结果-内蒙古大学图书馆

An extended speech de-noising method using GGM-based ICA feature extraction

9th Iberoamerican Congress on pattern recognition, CIARP 2004

作者： Kong, Wei Zhou, Yue Yang, Jie Institute of Image Processing and Pattern Recognition Shanghai Jiaotong University Shanghai200030 China

ISBN: (纸本)3540235272

ICA (independent component analysis) feature extraction is an efficient sparse coding method for noise reduction. In many ICA-based de-noising processing, however, they need noise-free source data to train the basis vectors as a priori knowledge. The noise-free data is always not acquirable in practice. In this paper, the generalized Gaussian model (GGM) is proposed as the p.d.f. estimator in ICA to extract the basis vectors directly from the noisy observation, since GGM can easily characterize a wide class of non-Gaussian statistical distributions. Simultaneously, the distribution of the coefficients learned by GGM is benefit for obtaining the shrinkage functions. The de-nosing experiments of noisy speech signals show that the proposed method is more efficient than conventional methods in the environment of additive white Gaussian noise. It demonstrates that the proposed method offer an efficient approach for detecting weak signals from the noise environment. © Springer-Verlag Berlin Heidelberg 2004.

关键词： Independent component analysis

来源：评论

学校读者我要写书评

暂无评论

AMCF-Net: A Novel Adaptive Multi-Channel Fusion Network for Computer-Aided Diagnosis of Lung Nodules in Chest Computed Tomography

引用

IET Communications 2025年第1期19卷

作者： Nan Wang Yu Gu Lidong Yang Baohua Zhang Jing Wang Xiaoqi Lu Jianjun Li Dahua Yu Ying Zhao Xin Liu Siyuan Tang Qun He Inner Mongolia Key Laboratory of Pattern Recognition and Intelligent Image Processing School of Digital and Intelligent Industry Inner Mongolia University of Science and Technology Baotou China School of Information and Electronics Beijing Institute of Technology Beijing China College of Information Engineering Inner Mongolia University of Technology Hohhot China School of Computer Science and Technology Baotou Medical College Inner Mongolia University of Science and Technology Baotou China

Malignant lung nodules can significantly affect patients' normal lives and, in severe cases, threaten their survival. Owing to the heterogeneity of computed tomography scans and the varying sizes of nodules, physicians often face challenges in diagnosing this condition. Therefore, a novel adaptive multi-channel fusion network (AMCF-Net) is proposed for computer-aided diagnosis of lung nodules. First, a Multi-Channel Fusion Model module is designed, which divides the channels into two parts in specific proportions, effectively extracting multi-scale channel information while reducing network parameters. After the feature maps output at each layer of the AMCF-Net, a novel adaptive depth-wise separable convolution with a squeeze-and-excitation module is designed to adaptively integrate the feature maps of various stages of the AMCF-Net, ensuring that the key lesions of lung nodules are not lost during classification. Finally, a hybrid loss scheme based on an adaptive mixing ratio is proposed to solve the problem of an imbalanced number of positive and negative nodule samples in the dataset. The model achieved the following test results: an accuracy of 90.22%, a specificity of 98.19%, an F1-score of 86.57%, a sensitivity of 86.49%, and a G-mean of 87.72%. Compared with other advanced networks, AMCF-net delivers high-precision lung nodule classification with minimal inference cost. Related codes have been released at: https://***/GuYuIMUST/AMCF-net .

关键词： computer networks convolution health care image processing neural nets

来源：评论

学校读者我要写书评

暂无评论

Robust skeleton extraction of gray images based on level set approach

引用

Journal of Multimedia 2013年第1期8卷 24-31页

作者： Yang, Zhihui Guo, Fangfang Dong, Ping Institute of Image Processing and Pattern Recognition North China University of Technology Beijing China

The skeleton of an image object is a simplified representation, which is of great significance for the image recognition and matching. To obtain a smooth and accurate skeleton of a specified object in the gray image, this paper provides a unified framework by combining the level set idea with the gradient module method. The intrinsic procedure involves three steps. First, an energy function is given by virtue of the statistical intensity disparity between the sample points and the object, and then a novel segmentation model is proposed to extract any specified objects in the gray image by the variational method. Moreover, the segmentation model is further improved to be suited to the texture image. Second, in order to find an accurate position of the skeleton, a searching algorithm for the endpoints of the skeleton is shown based on the segmentation result. Finally, an improved skeleton extraction algorithm is given via the shortest path connection approach. Some examples show the robustness and insensitivity of the presented algorithm to the perturbation and noise, respectively. © 2013 ACADEMY PUBLISHER.

关键词： image recognition

来源：评论

学校读者我要写书评

暂无评论

Reeb graphs through local binary patterns 10

Reeb graphs through local binary patterns

引用

10th IAPR-TC-15 International Workshop on Graph-Based Representations in pattern recognition, GbRPR 2015

作者： Janusch, Ines Kropatsch, Walter G. Pattern Recognition and Image Processing Group Institute of Computer Graphics and Algorithms Vienna University of Technology Vienna Austria

ISBN: (纸本)9783319182230

This paper presents an approach to derive critical points of a shape, the basis of a Reeb graph, using a combination of a medial axis skeleton and features along this skeleton. A Reeb graph captures the topology of a shape. The nodes in the graph represent critical points (positions of change in the topology), while edges represent topological persistence. We present an approach to compute such critical points using Local Binary patterns. For one pixel the Local Binary pattern feature vector is derived comparing this pixel to its neighbouring pixels in an environment of a certain radius. We start with an initial segmentation and a medial axis representation. Along this axis critical points are computed using Local Binary patterns with the radius, defining the neighbouring pixels, set a bit larger than the radius according to the medial axis transformation. Critical points obtained in this way form the node set in a Reeb graph, edges are given through the connectivity of the skeleton. This approach aims at improving the representation of flawed segmented data. In the same way segmentation artefacts, as for example single pixels representing noise, may be corrected based on this analysis. © Springer International Publishing Switzerland 2015.

关键词： image segmentation

来源：评论

学校读者我要写书评

暂无评论

Fast DCT-I, DCT-III, and DCT-IV via Moments

引用

Eurasip Journal on Applied Signal processing 2005年第12期2005卷 1902-1909页

作者： Liu, J.G. Liu, Y.Z. Wang, G.Y. Key Laboratory of Education Huazhong University of Science and Technology Ministry for Image Processing and Intelligence Control Wuhan 430074 China Department of Computer Science and Engineering China University of Geosciences Wuhan 430074 China Key Laboratory of State Education Ministry for Image Processing and Intelligent Control Huazhong University of Science and Technology China Institute of Pattern Recognition and Artificial Intelligence Huazhong University of Science and Technology China

This paper presents a novel approach to compute DCT-I, DCT-III, and DCT-IV. By using a modular mapping and truncating, DCTs are approximated by linear sums of discrete moments computed fast only through additions. This enables us to use computational techniques developed for computing moments to compute DCTs efficiently. We demonstrate this by applying our earlier systolic solution to this problem. The method can also be applied to multidimensional DCTs as well as their inverses. © 2005 Hindawi Publishing Corporation.

关键词： Method of moments

来源：评论

学校读者我要写书评

暂无评论

P4P Pastry: A novel P4P-based pastry routing algorithm in peer to peer network

P4P Pastry: A novel P4P-based pastry routing algorithm in pe...

引用

2010 2nd IEEE International Conference on Information Management and Engineering, ICIME 2010

作者： Guo, Zhengwei Yang, Shuai Yang, Huaipo College of Computer and Information Engineering Institute of Image Processing and Pattern Recognition Henan University Kaifeng Henan China

ISBN: (纸本)9781424452644

Aiming at the cu rrent structured P2P system's locality of physical location and accessing resources, in the context of P4P technology, this paper takes the Pastry algorithm as a foundation, proposes a P4P routing algorithm, in which peers performed clustering to the same resources and the proximity of physical location of nodes. When routing, the node routes to the nodes which are physical adjacent to it and have the lowest cost of communication. Theory analysis and the experimental results show that the algorithm proposed in this paper has realized localization download and greatly raised the data transfer rate, reduced the load in backbone network and enhanced the network performance. © 2010 IEEE.

关键词： Data transfer

来源：评论

学校读者我要写书评

暂无评论

Study on the Medical image Distributed Dynamic processing Method

引用

Journal of Systems Engineering and Electronics 2003年第4期14卷 69-76页

作者： Zhang Quanhai & Shi Pengfeiinstitute of image processing and pattern recognition, Shanghai Jiaotong university, Shanghai 200030, P. R. china Institute of Image Processing and Pattern Recognition Shanghai Jiaotong University Shanghai 200030 P.R. China

To meet the challenge of implementing rapidly advanced, time-consuming medical image processing algorithms, it is necessary to develop a medical image processing technology to process a 2D or 3D medical image dynamically on the web. But in a premier system, only static image processing can be provided with the limitation of web technology. The development of Java and CORBA (common object request broker architecture) overcomes the shortcoming of the web static application and makes the dynamic processing of medical images on the web available. To develop an open solution of distributed computing, we integrate the Java, and web with the CORBA and present a web-based medical image dynamic processing methed, which adopts Java technology as the language to program application and components of the web and utilies the CORBA architecture to cope with heterogeneous property of a complex distributed system. The method also provides a platform-independent, transparent processing architecture to implement the advanced image routines and enable users to access large dataset and resources according to the requirements of medical applications. The experiment in this paper shows that the medical image dynamic processing method implemented on the web by using Java and the CORBA is feasible.

关键词： medical image dynamic processing based on web distributed computing interoperation CORBA.

来源：评论

学校读者我要写书评

暂无评论

Kernel based weighted group sparse representation classifier

Kernel based weighted group sparse representation classifier

引用

15th International Conference on Human-Computer Interaction, HCI International 2013

作者： Xu, Bingxin Guo, Ping Chen, C. L. Philip Image Processing and Pattern Recognition Laboratory Beijing Normal University Beijing China Faculty of Science and Technology University of Macau China

ISBN: (纸本)9783642393419

Sparse representation classification (SRC) is a new framework for classification and has been successfully applied to face recognition. However, SRC can not well classify the data when they are in the overlap feature space. In addition, SRC treats different samples equally and ignores the cooperation among samples belong to the same class. In this paper, a kernel based weighted group sparse classifier (KWGSC) is proposed. Kernel trick is not only used for mapping the original feature space into a high dimensional feature space, but also as a measure to select members of each group. The weight reflects the importance degree of training samples in different group. Substantial experiments on benchmark databases have been conducted to investigate the performance of proposed method in image classification. The experimental results demonstrate that the proposed KWGSC approach has a higher classification accuracy than that of SRC and other modified sparse representation classification. © 2013 Springer-Verlag.

关键词： Classification (of information)

来源：评论

学校读者我要写书评

暂无评论

RETRACTED ARTICLE: P4P Gnutella: A novel P4P-based Gnutella routing algorithm in P2P

RETRACTED ARTICLE: P4P Gnutella: A novel P4P-based Gnutella ...

引用

作者： Guo, Zhengwei Yang, Huaipo Yang, Shuai College of Computer and Information Engineering Institute of Image Processing and Pattern Recognition Henan University Kaifeng Henan China

ISBN: (纸本)9781424451432

Analysis on the basis of the protocol Gnutella0.6, the use P4P technologies for sensing conveniently network topology information, proposes a P4P-based Gnutella routing algorithm, in which nodes join algorithm to consider the network topology and as far as possible to join super-nodes that close to itself. When routing algorithm forwards query packet, it give priority to select the physical proximity of the super-node. Theory analysis and the experimental show that the algorithm proposed in this paper has improved routing efficiency, reduced the routing delay and greatly raising the data transfer rate, enhanced the network performance. ©2010 IEEE.

关键词： Routing algorithms

来源：评论

学校读者我要写书评

暂无评论

Action recognition by multiple features and hyper-sphere multi-class SVM

Action recognition by multiple features and hyper-sphere mul...

引用

2010 20th International Conference on pattern recognition, ICPR 2010

作者： Liu, Jia Yang, Jie Zhang, Yi He, Xiangjian Institute of Image Processing and Pattern Recognition Shanghai Jiaotong University Shanghai China Faculty of Engineering and Information Technology University of Technology Sydney NSW Australia

ISBN: (纸本)9780769541099

In this paper we propose a novel framework for action recognition based on multiple features for improve action recognition in videos. The fusion of multiple features is important for recognizing actions as often a single feature based representation is not enough to capture the imaging variations (view-point, illumination etc.) and attributes of individuals (size, age, gender etc.). Hence, we use two kinds of features: i) a quantized vocabulary of local spatio-temporal (ST) volumes (cuboids and 2-D SIFT), and ii) the higher-order statistical models of interest points, which aims to capture the global information of the actor. We construct video representation in terms of local space-time features and global features and integrate such representations with hyper-sphere multi-class SVM. Experiments on publicly available datasets show that our proposed approach is effective. An additional experiment shows that using both local and global features provides a richer representation of human action when compared to the use of a single feature type. © 2010 IEEE.

关键词： Spheres

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：