检索结果-内蒙古大学图书馆

International Conference on Intelligent Systems Design and Applications (ISDA)

作者： Zhihong Xu Xin Zheng Ping Guo Mage Processing and Pattern Recognition Laboratory Beijing Normal University Beijing China

The software systems which are related to national projects are always very crucial. This kind of systems always involves hi-tech factors and has to spend a large amount of money, so the quality and reliability of the software deserve to be further studied. Hence, we propose to apply three classification techniques most used in data mining fields: Bayesian belief networks (BBN), nearest neighbor (NN) and decision tree (DT), to validate the usefulness of software metrics for risk prediction. Results show that comparing with metrics such as Lines of code (LOQ and Cyclomatic complexity (V(G)) which are traditionally used for risk prediction, Halstead program difficulty (D), Number of executable statements (EXEC) and Halstead program volume (V) are the more effective metrics as risk predictors. By analyzing we also found that BBN was more effective than the other two methods in risk prediction

关键词： Software metrics Software systems Software quality Classification tree analysis Data mining Bayesian methods Nearest neighbor searches Neural networks Decision trees Risk analysis

来源：评论

学校读者我要写书评

暂无评论

Large Scale Terrain Compression and Real-Time Rendering Based on Wavelet Transform

Large Scale Terrain Compression and Real-Time Rendering Base...

引用

International Conference on Computational Intelligence and Security

作者： Xiaodong Wang Xin Zheng Qian Yin Image Processing and Pattern Recognition Laboratory Beijing Normal University Beijing China

ISBN: (纸本)9781424441969

By taking advantage of 3 attributes of integer wavelet transform (IWT): efficient computing, multi-resolution and partially reconstruction, we propose one lossless large scale terrain compression method with high compression rate in this paper. By this way, we can decompress terrain data with multi-resolution efficiently at any viewpoint and render the terrain in real time by fast updating strategy. Experiments prove that by our method we can compress the data efficiently and render the terrain scene smoothly in real time.

关键词： Large-scale systems Wavelet transforms Image coding Rendering (computer graphics) Image reconstruction Discrete wavelet transforms Image resolution Multiresolution analysis Virtual reality Computational intelligence

来源：评论

学校读者我要写书评

暂无评论

Classification Fusion in Wireless Sensor Networks

引用

自动化学报 2006年第6期32卷 947-955页

作者： LIU Chun-Ting HUO Hong FANG Tao LI De-Ren SHEN Xiao Institute of Image Processing ＆ Pattern Recognition Shanghai Jiaotong University Shanghai 200240 State Key Laboratory of Information Engineering in Surveying Mapping and Remote Sensing Wuhan University Wuhan 430079

In wireless sensor networks, target classification differs from that in centralized sensing systems because of the distributed detection, wireless communication and limited resources. We study the classification problem of moving vehicles in wireless sensor networks using acoustic signals emitted from vehicles. Three algorithms including wavelet decomposition, weighted k-nearest-neighbor and Dempster-Shafer theory are combined in this paper. Finally, we use real world experimental data to validate the classification methods. The result shows that wavelet based feature extraction method can extract stable features from acoustic signals. By fusion with Dempster's rule, the classification performance is improved.

关键词： Wireless sensor networks classification fusion wavelet decomposition weighted k-nearest-neighbor Dempster-Shafer theory

来源：评论

学校读者我要写书评

暂无评论

Real time implementation of an MRF-based motion detection algorithm on a DSP board

Real time implementation of an MRF-based motion detection al...

引用

IEEE Digital Signal processing Workshop

作者： C. Dumontier F. Luthon J.P. Charras Image Processing and Pattern Recognition Laboratory National Polytechnical Institute Grenoble France

ISBN: (纸本)0780336291

The main concern in image processing is computation cost. Markov random fields (MRF) based algorithms particularly require a significant computation cost. Most of implementations of this kind of algorithms are made on parallel machines. This paper investigates an original solution for real time implementation of a robust MRF-based motion detection algorithm. A PC board, based on a pipeline architecture using a single powerfull DSP and FPGA components, is developed. The algorithm and the board are described. A processing rate of 15 images per second is achieved, showing the validity of this approach.

关键词： Motion detection Computational efficiency Image processing Markov random fields Parallel machines Robustness Pipelines Computer architecture Digital signal processing Field programmable gate arrays

来源：评论

学校读者我要写书评

暂无评论

Text-independent Speaker Identification Using Fisher Discrimination Dictionary Learning Method

Text-independent Speaker Identification Using Fisher Discrim...

引用

International Conference on Computational Intelligence and Security

作者： Xia Wang Qian Yin Ping Guo Image Processing and Pattern Recognition Laboratory Beijing Normal University Beijing China

In last decades, text-independent speaker recognition is a hot research topic attracted many researchers. In this paper, we proposed to apply the Fisher discrimination dictionary learning method to identify the text-independent speaker recognition. The feature used in classification is the Gaussian Mixture Model super vector. The proposed method is evaluated with public ally available dataset TIMIT. Experimental results show that the proposed method outperforms the Sparse Representation Classifier used for text-independent speaker recognition in both clean and noisy condition.

关键词： Dictionaries Mathematical model Equations Speaker recognition Noise measurement Learning systems pattern recognition

来源：评论

学校读者我要写书评

暂无评论

An Evolutionary Real-Time 3D Route Planner for Aircraft

引用

Journal of Systems Engineering and Electronics 2003年第1期14卷 47-53页

作者：郑昌文丁明跃周成平 Institute of Pattern Recognition and Artificial Intelligence State Education Commission Key Laboratory for Image Processing and Intelligent Control Huazhong University of Science and Technology Wuhan 430074 P. R. China

A novel evolutionary route planner for aircraft is proposed in this paper. In the new planner, individual candidates are evaluated with respect to the workspace, thus the computation of the configuration space is not required. By using problem-specific chromosome structure and genetic operators, the routes are generated in real time, with different mission constraints such as minimum route leg length and flying altitude, maximum turning angle, maximum climbing/diving angle and route distance constraint taken into account.

关键词： Evolutionary computation Route planning Route constraints Real time Aircraft.

来源：评论

学校读者我要写书评

暂无评论

OCF-Layout2Img: Object-Wise Constraint Free Layout to Image Generation 23

OCF-Layout2Img: Object-Wise Constraint Free Layout to Image ...

引用

15th International Conference on Digital Image processing, ICDIP 2023

作者： Lin, Xiao Liu, Bin He, Zhifen Wang, Kang Li, Bo School of Mathematics and Information Science Key Laboratory of Jiangxi Province for Image Processing and Pattern Recognition Nanchang Hangkong University China Jiangxi Science and Technology Infrastructure Center Jiangxi Computing Center China

ISBN: (纸本)9798400708237

Complex scene generation is an important and challenging image synthesis task. Though latent space based conditional generative methods get impressive results, the accurate locating of objects for more detailed situation and editable contiguous synthesis are still a snag. In addition, previous methods with spatial awareness are easy to lose the location information after a series fusion operation. Focusing on such kind of problems, in this paper we propose an object-wise constraint free and location-lossless way of layout embedding by combining VAE and recent high performance VQGAN to achieve a location accurate and stable synthesis for layouts of complex scene. Instead of conditioning on layout, we apply a pretrained VQGAN to define the latent space and project every region of layout to image latent space directly by aligning their distribution with a novel light Cross-VAE structure. Then the quantization and decoder of VQGAN are reused for synthesis. This VAE plugged into VQGAN framework, which is called Layout-DVGAN in this paper. Experimental results demonstrate our method has competitive performance compared with the approaches which applied explicit spatial awareness way. © 2023 ACM.

关键词： Location

来源：评论

学校读者我要写书评

暂无评论

A Hierarchical Model with Pseudoinverse Learning Algorithm Optimazation for Pulsar Candidate Selection

A Hierarchical Model with Pseudoinverse Learning Algorithm O...

引用

Congress on Evolutionary Computation

作者： Shijia Li Sibo Feng Ping Guo Qian Yin Image Processing and Pattern Recognition Laboratory Beijing Normal University Beijing China

Pulsars search has always been one of the most concerned problem in the field of astronomy. Nowadays, with the development of astronomical instruments and observation technology, the amount of data is getting bigger and bigger. Radio pulsar surveys have generated and will generate vast amounts of data. To handle big data, developing new technologies and frameworks to efficiently and accurately analyze these data become increasing urgent. The number of positive and negative samples in pulsar candidate data set is very unbalanced, if we only use these a few positive samples to train a deep neural network (DNN), the trained DNN is prone because of the problem of overfitting and will affect the generalization ability. Motivated by the mixtures of experts network architecture, we proposed a hierarchical model for pulsar candidate selection which assembles a set of trained base classifiers. Moreover, training a neural network always takes a lot of time because of using gradient descent (GD) based algorithm. In this work, we utilize the pseudoinverse learning algorithm instead of GD based algorithm to train proposed model. With the designed network architecture and adopted training algorithm, our model has the advantages not only with high steady-state precision but also good generalization performance.

关键词： Matrix decomposition Training Big Data Neural networks Task analysis Decoding Machine learning

来源：评论

学校读者我要写书评

暂无评论

Combining the contrast information with WLD for texture classification

Combining the contrast information with WLD for texture clas...

引用

IEEE International Conference on Computer Science and Automation Engineering (CSAE)

作者： Hussain Dawood Hassan Dawood Ping Guo Image Processing and Pattern Recognition Laboratory Beijing Normal University Beijing China

A considerable amount of research work has been done for texture classification using local or global feature extraction methods. Inspired by Weber's Law, a simple and robust Weber Local Descriptor (WLD) is a recently developed for local feature extraction. This WLD method did not consider the contrast information. In order to improve texture classification accuracy, we propose a hybrid approach that combines the WLD with contrast information in this paper. It utilizes the histogram of two complementary features WLD and the image variance calculated with the Probability Weighted Moments. Support vector machine is used for classification. The comparison of the proposed method with state of art methods like local binary pattern and WLD is experimental investigated on two publically available dataset, named as Brodatz and KTH-TIPS2-a. Results show that our proposed method outperforms over the state of art methods for texture classification.

关键词： Histograms Feature extraction Pulse width modulation Maximum likelihood estimation Standards pattern recognition Robustness

来源：评论

学校读者我要写书评

暂无评论

Weighted MLS-SVM for approximation of directional derivatives

Weighted MLS-SVM for approximation of directional derivative...

引用

MIPPR 2005: Image Analysis Techniques

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

Based on statistical learning theory, support vector machine (SVM) is a novel type of learning machine, and it contains polynomial, neural network and radial basis function (RBF) as special cases. The mapped least squares support vector machine (MLS-SVM) is a special least square SVM (LS-SVM), which extends the application of the SVM to the image processing. Based on the MLS-SVM, a family of filters for the approximation of partial derivatives of the digital image surface is designed. Prior information (e.g., local dominant orientation) are incorporated in a two dimension weighted function. The weighted MLS-SVM with the radial basis function kernel is applied to design the proposed filters. Exemplary application of the proposed filters to fingerprint image segmentation is also presented.

关键词： Learning systems

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：