检索结果-内蒙古大学图书馆

A novel method of aerial image classification based on attention-based local descriptors

Procedia Earth and Planetary Science 2009年第1期1卷 1133-1139页

作者： Xu, Sheng Fang, Tao Huo, Hong Li, Deren Institute of Image Processing and Pattern Recognition Shanghai Jiaotong University Shanghai 200240 China The State Key Laboratory for Information Engineering in Surveying Mapping and Remote Sensing Wuhan University Wuhan 430072 China

This paper proposes a novel method for object-based classification in very high spatial resolution aerial image. It combines the saliency maps very closely to extract the conspicuous local regions for better description of object and classification. Unlike the previous work on detection of the local regions, a biologically motivated selective attention model is presented in this paper, since not all the local regions are important for describing the objects. In order to model the attention region, we propose a new attention-based local descriptor using the saliency map and relative local features to reflect the region of interest (ROI). The experimental results on the VHR aerial image dataset show that the proposed approach can obtain the state-of-the-art classifica-tion performance. © 2009.

关键词： Object recognition image analysis image classification image segmentation Aerial images Bag of visual words Local descriptors Local feature Local region Novel methods Object based Region of interest Saliency map Selective attention model Very high spatial resolutions

来源：评论

学校读者我要写书评

暂无评论

Efficient word-level sequential coding scheme of bit plane coding for EBCOT in JPEG2000

Efficient word-level sequential coding scheme of bit plane c...

引用

9th International Symposium on Consumer Electronics 2005, ISCE 2005

作者： Xiong, Cheng-Yi Tian, Jin-Wen Liu, Jian Institute of Pattern Recognition and Artificial Intelligence South-Center University for Nationalities Huazhong University of Science and Technology Wuhan China Key Laboratory of Education Ministry for Image Processing and Intelligent Control Institute of Pattern Recognition and Artificial Intelligence Huazhong University of Science and Technology Wuhan China HUST

The embedded block coding with optimized truncation (EBCOT) is the state-of-the-art coding technique for image compression, which is the heart of the latest still image compression standard JPEG2000. EBCOT can be partitioned into three steps: bit plane coding (BPC), context adaptive binary arithmetic coding (CABAC) and postcompression rate-distortion (PCRD) optimization. The bit plane coding in JPEG2000 is a fractional bit-plane coding method, in which the transformed coefficients of a code block are coded bit plane by bit plane with 3 passes in each bit-plane, and context-decision (CX-D) pair of the coded symbol is generated for CABAC. In this paper, a new word-level sequential (WLS) coding scheme for BPC is presented, which makes all the passes coding be completed in one scan, with the context formation in all bit-planes being performed in parallel and all the samples being coded in sequential. The status variables used in context formation are produced on-the-fly. This new algorithm can efficiently implement both the regular mode and vertical causal one recommended by JPEG2000. The proposed algorithm reduces efficiently the size of memory and the amount of memory accessing, and increases significantly the speed of coding. It is well suited for both software and hardware implementation.1 © IEEE.

关键词： image coding

来源：评论

学校读者我要写书评

暂无评论

Universal Adversarial Perturbation Generated by Attacking Layer-wise Relevance Propagation 10

Universal Adversarial Perturbation Generated by Attacking La...

引用

10th IEEE International Conference on Intelligent Systems, IS 2020

作者： Wang, Zifei Huang, Xiaolin Yang, Jie Kasabov, Nikola Shanghai Jiao Tong University Institute of Image Processing and Pattern Recognition Shanghai China Auckland University of Technology Knowledge Engineering and Discovery Research Institute Auckland New Zealand

ISBN: (纸本)9781728154565

The vulnerability of Deep Neural Networks (DNNs) to adversarial attacks has become an important research area of machine learning. It has been known that many state-of-the-art DNNs suffer the risk of universal adversarial perturbations, which are image-agnostic and able to lead misclassifications with high probability. In this paper, we propose a novel method to create such universal adversarial perturbations. Our approach is the first to generate universal perturbations by attacking the attention heat maps with the interpretation method, Layer-wise Relevance Propagation. It is demonstrated that our method achieves high fooling ratios on image classification DNNs pre-trained by imageNet dataset. Moreover, our attack shows good transferability across different DNNs. © 2020 IEEE.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

A fast quantum mechanics based contour extraction algorithm

A fast quantum mechanics based contour extraction algorithm

引用

Medical Imaging 2009 - image processing

作者： Lan, Tian Sun, Yangguang Ding, Mingyue Institute for Pattern Recognition and Artificial Intelligence Key Laboratory of Education Ministry for Image Processing and Intelligent Control Huazhong University of Science and Technology Wuhan 430074 China

ISBN: (纸本)9780819475107

A fast algorithm was proposed to decrease the computational cost of the contour extraction approach based on quantum mechanics. The contour extraction approach based on quantum mechanics is a novel method proposed recently by us, which will be presented on the same conference by another paper of us titled "a statistical approach to contour extraction based on quantum mechanics". In our approach, contour extraction was modeled as the locus of a moving particle described by quantum mechanics, which is obtained by the most probable locus of the particle simulated in a large number of iterations. In quantum mechanics, the probability that a particle appears at a point is equivalent to the square amplitude of the wave function. Furthermore, the expression of the wave function can be derived from digital images, making the probability of the locus of a particle available. We employed the Markov Chain Monte Carlo (MCMC) method to estimate the square amplitude of the wave function. Finally, our fast quantum mechanics based contour extraction algorithm (referred as our fast algorithm hereafter) was evaluated by a number of different images including synthetic and medical images. It was demonstrated that our fast algorithm can achieve significant improvements in accuracy and robustness compared with the well-known state-of-the-art contour extraction techniques and dramatic reduction of time complexity compared to the statistical approach to contour extraction based on quantum mechanics. © 2009 Copyright SPIE - The International Society for Optical Engineering.

关键词： Wave functions

来源：评论

学校读者我要写书评

暂无评论

A new method for optimizing the combinational kernels

A new method for optimizing the combinational kernels

引用

2010 International Conference on Computer Application and System Modeling, ICCASM 2010

作者： Tian, Xue Yang, Xu Institute of Electrical and Mechanical Engineering Jiaxing University Jiaxing 314001 China Institute of Image Processing and Pattern Recognition Shanghai Jiaotong University Shanghai 200240 China

ISBN: (纸本)9781424472369

The optimal kernel selection is a critical problem for the kernel-based learning algorithm. In order to obtain good results, the kernel function must be chosen in a data-dependent manner. To this end, we propose a new feature space based class separability measure to evaluate the conformation of kernels to the data. The optimal combination coefficients of multiple Gaussian functions are obtained by optimizing this measure. Experimental results show that our algorithm outperforms the cross-validation method and the radius margin bound method, and moreover, can further improve the performances of SVM classifiers. © 2010 IEEE.

关键词： pattern recognition

来源：评论

学校读者我要写书评

暂无评论

A fake iris detection method based on FFT and quality assessment

A fake iris detection method based on FFT and quality assess...

引用

2008 Chinese Conference on pattern recognition, CCPR 2008

作者： He, Xiaofu Lu, Yue Shi, Pengfei Department of Computer Science and Technology East China Normal University Shanghai 200241 China Institute of Image Processing and Pattern Recognition Shanghai Jiao Tong University Shanghai 200240 China

ISBN: (纸本)9781424423163

In recent years, iris recognition is becoming a very active topic in both research and practical applications. However, fake iris is a potential threat there are potential threats for iris-based systems. This paper presents a novel fake iris detection method based on the analysis of 2-D Fourier spectra together with iris image quality assessment. First, image quality assessment method is used to exclude the defocused, motion blurred fake iris. Then statistical properties of Fourier spectra for fake iris are used for clear fake iris detection. Experimental results show that the proposed method can detect photo iris and printed iris effectively. ©2008 IEEE.

关键词： Biometrics

来源：评论

学校读者我要写书评

暂无评论

Integer Haar wavelet for romote sensing image compression 6

Integer Haar wavelet for romote sensing image compression

引用

6th International Conference on Signal processing, ICSP 2002

作者： Zhenhua, Wang Hongbo, Xu Yan, Tian Jinwen, Tian Jian, Liu State Key Lab. for Image Processing and Intelligent Control Institute for Pattern Recognition and Artificial Intelligence Huazhong University of Science and Technology Wuhan430074 China

ISBN: (纸本)0780374886

With the development of remote sensing technique, onboard data compression has become an urgent need and a lot of study has been directed toward the development of efficient techniques. In this paper, the construction approach of integer Haar is discussed briefly, and a'simple image compression scheme based on integer Haar Wavelet Transform and block DPCM is proposed. The scheme can be easily designed for data processing in real-time system of remote sensing with parellel algorithm. Simulation experimental results demonstrate that the proposed approach is a efficient image compression method. © 2002 IEEE.

关键词： image compression

来源：评论

学校读者我要写书评

暂无评论

A novel fast full frame video stabilization via three-layer model 21

A novel fast full frame video stabilization via three-layer ...

引用

21st International Conference on MultiMedia Modeling, MMM 2015

作者： Long, Wei Yang, Jie Song, Dacheng Chen, Xiaogang He, Xiangjian Institute of Image Processing and Pattern Recognition Shanghai Jiao Tong University Shanghai China University of Shanghai for Science and Technology Shanghai China School of Computing and Communications University of Technology Sydney Australia

ISBN: (纸本)9783319144443

Video stabilization is an important video enhancement technology which aims at removing undesired shaking from input videos. A challenging task in stabilization is to inpaint the missing pixels of undefined areas in the motion-compensated frames. This paper describes a new video stabilization method. It adopts a multi-layer model to improve the efficiency of the video stabilization. The undefined areas can be inpainted in real-time. Compared with traditional methods, our proposed algorithm only need maintain a single updated mosaic image for video completion, while previous methods require to store all neighboring frames and then registered with the current frame. The experimental results demonstrated the effectiveness of the proposed approach. © Springer International Publishing Switzerland 2015.

关键词： Motion compensation

来源：评论

学校读者我要写书评

暂无评论

Follicular Unit Registration Based on Binocular Stereo Vision for Hair Transplantation Surgery Robot 6

Follicular Unit Registration Based on Binocular Stereo Visio...

引用

6th International Conference on Data Science and Information technology, DSIT 2023

作者： Wang, Weiduo Liu, Jinfeng Yang, Jie Shanghai Jiao Tong University Institute of Image Processing and Pattern Recognition Department of Automation China Shanghai Jiao Tong University Institute of Medical Robotics China

ISBN: (纸本)9798350304442

In this paper, we focus on the follicular unit registration problem for hair transplantation surgery robots based on binocular stereo vision system. The follicular units in both images are detected with YOLO V5 network. Because of the dull and similar pattern of the follicular units, previous regular methods which are pixel-based are reported with misalignment and poor accuracy. To solve this problem, we propose the context shape to describe the feature of the follicular unit. The distribution of units surrounding the target unit is estimated as the context shape. Then, Otsu's method is used to segment hairs and Hungarian algorithm is used to match the hairs in the matched follicular unit. Then, the hairs are projected to 3D coordinate system and reconstructed. The experiments on the generated hair dataset demonstrate that the proposed method achieves both high accuracy and speed. © 2023 IEEE.

关键词： Stereo vision

来源：评论

学校读者我要写书评

暂无评论

Scale-dependent spatial data mining

Scale-dependent spatial data mining

引用

MIPPR 2005: Geospatial Information, Data Mining, and Applications

作者： Sun, Qingxian Fang, Tao Guo, Dazhi Department of Surveying and Land Science China University of Mining and Technology Beijing 100083 China Institute of Image Processing and Pattern Recognition Shanghai Jiao Tong University Shanghai 200030 China

Scale is a major concept in many sciences concerned with human activities and physical processes occurring in the world, and directly related to many investigations of spatial objects, including the procedure of spatial data mining. In this paper, we attempt to apply the spatial data mining to the field of coal mining, and the technical notion is to generate patterns or rules by means of different scale databases that depict the same subject. The whole research procedure gives readers an understanding of how processes operate at different scales and how they can be linked across scales. At the same time, our study actually presents a new method of image mining as well.

关键词： Data mining

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：