检索结果-内蒙古大学图书馆

12th Pacific Rim International Conference on Artificial Intelligence, PRICAI 2012

作者： Gou, Gaopeng Huang, Di Wang, Yunhong Laboratory of Intelligent Recognition and Image Processing Beijing Key Laboratory of Digital Media Beihang University Beijing China

ISBN: (纸本)9783642326943

Video-based face clustering is a very important issue in face analysis. In this paper, a framework for video-based face clustering is proposed. The framework contains two steps. First, faces are detected from videos and divided into subgroups using temporal continuity information and SIFT (Scale Invariant Feature Transform) features. Second, the typical samples are selected from these subgroups in order to remove some non-typical faces. A similarity matrix is then constructed using these typical samples in the subgroups. The similarity matrix is further processed by our method to generate the face clustering results of that video. Our algorithm is validated using the SPEVI datasets. The experiments demonstrated promising results from our algorithm. © 2012 Springer-Verlag.

关键词： Clustering algorithms

来源：评论

学校读者我要写书评

暂无评论

A novel DNA computing model based on RecA-mediated triple-stranded DNA structure

引用

Progress in Natural Science:Materials International 2007年第6期17卷 708-711页

作者： Fang Gang1, Zhang Shemin2, Dong Yafei1 and Xu Jin1(1. The key laboratory of image processing and intelligent Control, Department of Control Science & Engineering, Huazhong University of Science and Technology, Wuhan 430074, China 2. Shaanxi University of Technology, Hanzhong 723000, China) [a]The Key Laboratory of Image Processing and Intelligent Control Department of Control Science & Engineering Huazhong University of Science and Technology Wuhan China [b]Shaanxi University of Technology Hanzhong China

The field of DNA computing emerged in 1994 after Adleman’s paper was published. Henceforth,a few scholars solved some noted NP-complete problems in this way. And all these methods of DNA computing are based on conventional Watson-Crick hydrogen bond of doublehelical DNA molecule. In this paper, we show that the triple-stranded DNA structure mediated by RecA protein can be used for solving computational problems. Sequence-specific recognition of double-stranded DNA by oligonucleotide-directed triple helix (triplex) formation is used to carry out the algorithm. We present procedure for the 3-vertex-colorability problems. In our proposed procedure, it is suggested that it is possible to solve more complicated problems with more variables by this model.

关键词： DNA computing 3-vertex-colorability problem.

来源：评论

学校读者我要写书评

暂无评论

Towards independent color space selection for human skin detection

Towards independent color space selection for human skin det...

引用

13th Pacific-Rim Conference on Multimedia, PCM 2012

作者： Xu, Tao Wang, Yunhong Zhang, Zhaoxiang Laboratory of Intelligent Recognition and Image Processing Beijing Key Laboratory of Digital Media Beihang University Beijing China

ISBN: (纸本)9783642347771

Skin color detection plays an important role in video based applications. Without considering the selection of suitable color space, a novel skin color detection method is proposed based on the flexible neural tree, which can identify the important components of color spaces automatically. With large training data sets, our method builds a flexible neural tree structure and optimizes its parameters using Genetic Programming and Particle Swarm Optimization algorithms. In experiments, features comprised of all channels extracted from RGB, YCbCr and HSV color spaces are used for the constructing and evaluating of the novel skin color model, in which six most important components, i.e., R, G, B, Y, Cr and S are selected for testing. Furthermore, our method achieves higher accuracy and lower false positive rate than state of the art methods on Compaq and ECU data set. © 2012 Springer-Verlag.

关键词： Genetic programming

来源：评论

学校读者我要写书评

暂无评论

Semi-supervised segmentation of multispectral remote sensing image based on spectral clustering

Semi-supervised segmentation of multispectral remote sensing...

引用

MIPPR 2009 - Multispectral image Acquisition and processing: 6th International Symposium on Multispectral image processing and Pattern Recognition

作者： Zhang, Xiangrong Wang, Ting Jiao, Licheng Yang, Chun Key Laboratory of Intelligent Perception and Image Understanding Institute of Intelligent Information Processing Xidian University Xi'an 710071 China

ISBN: (纸本)9780819478054

In this paper, a new multi-spectral remote sensing image segmentation method based on multi-parameter semi-supervised spectral clustering (STS 3C) is proposed. Two types of instance-level constraints: must-link and cannot-link are incorporated into spectral cluster to construct semi-supervised spectral clustering in which the self-tuning parameter is applied to avoid the selection of the scaling parameter. Further, when STS 3C is applied to multi-spectral remote sensing image segmentation, the uniform sampling technique combined with nearest neighbor rule is used to reduce the computation complexity. Segmentation results show that STS 3C outperforms the semi-supervised spectral clustering with fixed parameter and the well-known clustering methods including k-means and FCM in multi-spectral remote sensing image segmentation. © 2009 Copyright SPIE - The International Society for Optical Engineering.

关键词： image segmentation

来源：评论

学校读者我要写书评

暂无评论

SAR image classification based on correlation of directional features in frequency domain

SAR image classification based on correlation of directional...

引用

MIPPR 2009 - Pattern Recognition and Computer Vision: 6th International Symposium on Multispectral image processing and Pattern Recognition

作者： Zhong, Hua Yang, Xiaoming Jiao, Licheng Institution of Intelligent Information Processing Key Laboratory of Intelligent Perception and Image Understanding Xidian University Xi'an 710071 China

ISBN: (纸本)9780819478078

A new SAR image classification method is proposed based on the remarkable correlation of feature channels, which are obtained by dividing the Fourier plane into sectors according to the frequency and direction. Compared with other feature correlation based methods in wavelet and Contourlet domain, our method operates directly in the Fourier plane, which is more robust with regard to images size and more flexible in the capture of frequency and directional information. Moreover, the use of FFT transform is computationally more attractive. Experimental results on the Brodatz textures and SAR images demonstrate the effectiveness and efficiency of the proposed method. © 2009 Copyright SPIE - The International Society for Optical Engineering.

关键词： Classification (of information)

来源：评论

学校读者我要写书评

暂无评论

A traffic flow detection system combining optical flow and shadow removal

A traffic flow detection system combining optical flow and s...

引用

2011 3rd Chinese Conference on intelligent Visual Surveillance, IVS 2011

作者： Zhang, Zhaoxiang Hou, Yuqing Wang, Yunhong Qin, Jie Laboratory of Intelligent Recognition and Image Processing Beijing Key Laboratory of Digital Media Beihang University Beijing China

ISBN: (纸本)9781457718311

Traffic flow detection plays an important role in intelligent Transportation Systems(ITS). Video based traffic flow detection system is the most widely used strategy in ITS. Under this circumstance, we design and implement a video based traffic flow detection system which is called MyTD in this paper. MyTD takes advantages of both shadow removal and optical flow algorithms. Firstly, we introduce the current development of ITS and focus on the video based traffic detection technology, which is the key to ITS. Secondly, a shadow removal algorithm combining information in both RGB and HSV color spaces is proposed. Thirdly, based on the Iterative Pyramidal LK Optical Flow Algorithm, a vehicle tracking function is realized by OpenCV, as well as a Connected Components Labeling function and the vehicle counting function. Finally, MyTD is implemented and tested based on the algorithm presented above. Experimental results show the outstanding performance of our method comparing with traditional optical flow algorithms. © 2011 IEEE.

关键词： Optical flows

来源：评论

学校读者我要写书评

暂无评论

Low-complexity bandelet for SAR image compression

Low-complexity bandelet for SAR image compression

引用

MIPPR 2009 - Multispectral image Acquisition and processing: 6th International Symposium on Multispectral image processing and Pattern Recognition

作者： Yang, Shuyuan Wang, Zhaoxia Qi, Weidong Jiao, Licheng Key Laboratory of Intelligent Perception and Image Understanding Institute of Intelligent Information Processing Xidian University Xi'an 710071 China

ISBN: (纸本)9780819478054

Synthetic aperture radar (SAR) images compression is very important in reducing the burden of data storage and transmission. Finding efficient geometric representations of images is a central issue in improving the efficiency of image compression. Bandelet provides an efficient way for image representation based on geometric regularity. In the second generation Bandelet, the multiscale decomposition of image is completed by 2D wavelet transform (WT) and the obtained subbands images are squared partitioned. Then a bottom to top CART algorithm is used to prune the quadtree, and finally an exhaustive searching algorithm is used to obtain the optimal direction in each square. This process is of high complexity in time and space though it can provide an efficient representation of images than WT. Considering this, we proposed a rapid implementation of Bandelet transform based on fixed size image partition, and then applied it to SAR image compression. Experiments results show that in relative to the second generation Bandelets, our proposed method has rapid implementation and comparable performance with chinalake and abq-apt in 0.5-2.0bpp. An improvement of PSNR(Peak Signal to Noise Ratio) and the preservation of edges and texture over JPEG2000 are obtained. © 2009 Copyright SPIE - The International Society for Optical Engineering.

关键词： image compression

来源：评论

学校读者我要写书评

暂无评论

MCIF-Transformer Mask RCNN:Multi-Branch Cross-Scale Interactive Feature Fusion Transformer Model for PET/CT Lung Tumor Instance Segmentation

引用

Computers, Materials & Continua 2024年第6期79卷 4371-4393页

作者： Huiling Lu Tao Zhou School of Medical Information&Engineering Ningxia Medical UniversityYinchuan750004China School of Computer Science and Engineering North Minzu UniversityYinchuan750021China Key Laboratory of Image and Graphics Intelligent Processing of State Ethnic Affairs Commission NorthMinzu UniversityYinchuan750021China

The precise detection and segmentation of tumor lesions are very important for lung cancer computer-aided ***,in PET/CT(Positron Emission Tomography/Computed Tomography)lung images,the lesion shapes are complex,the edges are blurred,and the sample numbers are *** solve these problems,this paper proposes a Multi-branch Cross-scale Interactive Feature fusion Transformer model(MCIF-Transformer Mask RCNN)for PET/CT lung tumor instance segmentation,The main innovative works of this paper are as follows:Firstly,the ResNet-Transformer backbone network is used to extract global feature and local feature in lung *** pixel dependence relationship is established in local and non-local fields to improve the model perception ***,the Cross-scale Interactive Feature Enhancement auxiliary network is designed to provide the shallow features to the deep features,and the cross-scale interactive feature enhancement module(CIFEM)is used to enhance the attention ability of the fine-grained ***,the Cross-scale Interactive Feature fusion FPN network(CIF-FPN)is constructed to realize bidirectional interactive fusion between deep features and shallow features,and the low-level features are enhanced in deep semantic ***,4 ablation experiments,3 comparison experiments of detection,3 comparison experiments of segmentation and 6 comparison experiments with two-stage and single-stage instance segmentation networks are done on PET/CT lung medical image *** results showed that APdet,APseg,ARdet and ARseg indexes are improved by 5.5%,5.15%,3.11%and 6.79%compared with Mask RCNN(resnet50).Based on the above research,the precise detection and segmentation of the lesion region are realized in this *** method has positive significance for the detection of lung tumors.

关键词： PET/CT images instance segmentation mask RCNN interactive fusion transformer

来源：评论

学校读者我要写书评

暂无评论

Active learning for transferrable object classification in cross-view traffic scene surveillance

Active learning for transferrable object classification in c...

引用

13th Pacific-Rim Conference on Multimedia, PCM 2012

作者： Zhang, Zhaoxiang Tang, Jun Zhao, Yuhang Wang, Yunhong Liu, Jianyun Laboratory of Intelligent Recognition and Image Processing Beijing Key Laboratory of Digital Media Beihang University Beijing China

ISBN: (纸本)9783642347771

We discuss the problem of object classification in cross-view traffic scene surveillance videos in this paper. To classify moving objects in traffic scene videos into pedestrian, bicycle and variety of vehicles, an effective intelligent classification framework has been proposed which takes advantage of a transfer machine learning method to bridge the gap between source scene data and target scene data. The transfer learning algorithm makes one classifier adaptive to perspective changes instead of training two different classifiers for corresponding perspectives. The samples transferred from source scene database have saved much manual labeling work on target scene database. In this paper, we propose an active transfer learning method to decrease manual labeling work further for target scene traffic object classification. Redundant experiments are conducted and experimental results demonstrate the effectiveness and convenience of our approach. © 2012 Springer-Verlag.

关键词： Learning algorithms

来源：评论

学校读者我要写书评

暂无评论

image denoising with non-local means in the shearlet domain

Image denoising with non-local means in the shearlet domain

引用

International Workshop on Multi-Platform/Multi-Sensor Remote Sensing and Mapping

作者： Zhang, Xiaohua Zhang, Qiang Jiao, L.C. Key Laboratory of Intelligent Perception and Image Understanding Institute of Intelligent Information Processing Xidian University Xi'an 710071 China

ISBN: (纸本)9781424494040

In this paper, a novel method for image denoising is proposed which adopts multiscale geometry tool. Firstly the image is decomposed by discrete shearlet transform. The shearlet coefficients of each direction approach the generalized Gaussian distribution. We use the principal component analysis (PCA) for every similarity window of shearlet coefficients. Then we use Generalized Gaussian model of non-local means method to handle the shearlet coefficients. Finally, we reconstruct image with the new shearlet coefficients to obtain the result. Numerical results show that our algorithm competes favorably with nonlocal means algorithms in the case of high noise. ©2011 IEEE.

关键词： Principal component analysis

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：