检索结果-内蒙古大学图书馆

International Conference on Machine Learning and Cybernetics, ICMLC 2005

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

ISBN: (纸本)078039092X

Many vision-related processing tasks, including edge detection and image segmentation, can be performed more easily when all objects in the scene are in good focus. However, in practice, this may not be always feasible as optical lenses, especially those with long focal lengths, only have a limited depth of field. One classical approach to recover an everywhere-in-focus image is to use Laplacian pyramid image fusion. First, several source images with different focuses of the same scene are taken and decomposed into the low/high-frequency components image sequences. Within these decompositions, the high-frequency components image sequences with the largest magnitude are selected at each pixel location. Finally, the fused image can be recovered from the decomposed components image sequences. In the support vector machine (SVM), the pixels with larger support values have a physical meaning in the sense that they reveal relative more importance of the data points for contributing to the SVM model. In this paper, we use Laplacian pyramid for the multiresolution decomposition, and then replace the traditional salient features by support values of the mapped least squares (LS)-SVM for fusing image. Experimental results illustrate that the proposed method outperforms the traditional approach. ©2005 IEEE.

关键词： image segmentation

来源：评论

学校读者我要写书评

暂无评论

3D TRUS image segmentation in prostate brachytherapy

3D TRUS image segmentation in prostate brachytherapy

引用

2005 27th Annual International Conference of the Engineering in Medicine and Biology Society, IEEE-EMBS 2005

作者： Ding, Mingyue Gardi, Lori Wei, Zhouping Fenster, Aaron Key Laboratory Education Ministry for Image Processing and Intelligent Control Huazhong University of Science and Technology Wuhan 430074 China Imaging Research Laboratories Robarts Research Institute London Ont. N6A 5K8 Canada

ISBN: (纸本)0780387406

Brachytherapy is a minimally invasive interventional surgery used to treat prostate cancer. It is composed of three steps: dose pre-planning, implantation of radioactive seeds, and dose post-planning. In these procedures, it is crucial to determine the positions of needles and seeds, measure the volume of the prostate gland. Three-dimensional transrectal ultrasound (TRUS) imaging has been demonstrated to be a useful technique to perform such tasks. Compared to CT, MRI or X-ray imaging, US image suffers from low contrast, image speckle and shadows, making it challenging for segmentation of needles, the prostates and seeds in the 3D TRUS images. In this paper, we reviewed 3D TRUS image segmentation methods used in prostate brachytherapy including the segmentations of the needles, the prostate, as well as the seeds. Furthermore, some experimental results with agar phantom, turkey and chicken phantom, as well as the patient data are reported. © 2005 IEEE.

关键词： image segmentation

来源：评论

学校读者我要写书评

暂无评论

Speckle reduction of SAR images using support vector machine in wavelet domain

Speckle reduction of SAR images using support vector machine...

引用

MIPPR 2005: SAR and Multispectral image processing

作者： Cheng, Hui Yu, Qiuze Tian, Jinwen Liu, Jian Key Laboratory of Education Huazhong University of Science and Technology Ministry for Image Processing and Intelligence Control Wuhan 430074 China College of Information Science and Engineering Jianghan University Wuhan 430034 China

The granular appearance of speckle noise in synthetic aperture radar (SAR) imagery makes it very difficult to visually and automatically interpret SAR data. Therefore, speckle reduction is a prerequisite for many SAR image processing tasks. We develop a speckle reduction algorithm by fusing the wavelet denoising technique with support vector machine (SVM). Based on the least squares support vector machine (LS-SVM) with Gaussian radial basis function kernel, a new denoising operators used in the wavelet domain are obtained. Simulated SAR images and real SAR images are used to evaluate the denoising performance of our proposed algorithm along with another wavelet-based denoising algorithm, as well as the refined Lee speckle filter. Experimental results show that the that the proposed filter method outperforms standard wavelet denoising techniques in terms of the ratio images and the equivalent-number-of-looks measures in most cases. It also achieves better performance than the refined Lee filter.

关键词： image analysis

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

A Smart Mathematic Morphology Method for Recognition and Understanding of Airfield

引用

Wuhan University Journal of Natural Sciences 2005年第5期10卷 867-872页

作者： WANG Zhi-cheng TIAN Yan TIAN Jin-wen LIU Jian LIANG Chao-sheng TAO Wen-bin State Education Commission Key Laboratory for Image Processing and Intelligence Control Huazhong University of Science and Technology Wuhan430074 Hubei China Department of Electronics and Information Engineering Huazhong University of Science and Technology Wuhan 430074 Hubei China Institute for Pattern Recognition and Artificial Intelligence Huazhong University of Science and Technology Wuhan 430074 Hubei China

A method used for recognition and understanding of airfield based on mathematical morphology is proposed in this paper. The new approach can he divided into three steps. First, to extract the typical geometric structure features of airfield, a segmentation method called recursive Otsu algorithm is employed on an airfield image. Second, thinning and shrinking algorithms are utilized to obtain the contour of airfield with single pixel and to remove diffused small particles. Finally, Radon transform is adopted to extract two typical and important components, primary and secondary runways of airfield exactly. At the same time, region growing algorithm is exploited to get the other components such as parking apron and garages. The experimental results demonstrate that the proposed method gives good performance.

关键词： mathematical morphology shrinking algorithm Radon transform Region growing

来源：评论

学校读者我要写书评

暂无评论

Study on the detection of infrared small dim targets based on DMMFs

Study on the detection of infrared small dim targets based o...

引用

International Conference on Space Information Technology

作者： Li, Tao Zhang, Jian Zhang, Caifang Xie, Yubo Key Laboratory of Education Huazhong University of Science and Technology Ministry for Image Processing and Intelligent Control 430074Hubei China School of Information and Electrical Engineering Hunan University of Science and Technology Xiangtan Hunan 411201 China Dept. of Electronic and Information Engineering Huazhong University of Science and Technology Wuhan 430074Hubei China

ISBN: (纸本)0819460079

This paper presents an effective method to detect small and dim infrared image target under complex background, which is performed in spatial domain. Roughly speaking, the new method contains two steps. The first step is further divided into two steps (called difference between maximum and minimum filters, DMMFs): firstly, an original image is filtered by maximum (max) and minimum (min) filters based on the considering max filter can enhance the target and preserve the background while min filter can eliminate the target and also preserve the background;and then the difference between these two results is obtained, therefore the target is enhanced and its background is suppressed at the same time. To obtain an accurate location of the target, the second step called post processing involves local feature mapping and projecting techniques. This DMMF method focuses on reducing the cost of computation, tracking the target in real-time, enhancing the SNR, and suppressing its background clutter. The simulation results show that the proposed algorithm is effective and practical.

关键词： Infrared imaging

来源：评论

学校读者我要写书评

暂无评论

Background suppression based-on wavelet transformation to detect infrared target

Background suppression based-on wavelet transformation to de...

引用

International Conference on Machine Learning and Cybernetics (ICMLC)

作者： Yu-Qiu Sun Jin-Wen Tian Jian Liu State Education Commission Key Laboratory for Image Processing and Intelligent Control Institute for Pattern Recognition and Artificial Intelligence Huazhong University of Science and Technology Wuhan China School of Information and Mathematics Yangtze University Jinzhou China State Education Commission Key Laboratory for Image Processing and Intelligent Control Department of Electronic Information and Enginery Huazhong University of Science and Technology Wuhan China

Target detection and location in infrared clutter background is very important to infrared search and track system. Especially for small target detection in infrared image in background of sea and sky, there are no geometric and structure character to use. When targets such as ship and naval vessel sailing at long distance, they always appear around the sea-level line, and it is mixed with cloud and sea-wave clutter. It is difficult to segment and locate precisely. Background suppression based-on wavelet transformation is proposed in the paper. Wavelet decomposition makes it possible to analyze a signal both in time and frequency domains. In the paper infrared sea and key background images are processed. For their SNR is low and background is complex, using wavelet transformation decomposes an original image and extract approximate feature to reconstruct an image, which mainly includes background information. A new image would be obtained using background image subtracted from original image. There are mainly target and noise points left in the new image. By setting proper threshold, the target can be detected perfectly. At last, experiment results are given and show the method is practical.

关键词： Infrared detectors Object detection Infrared imaging Target tracking Marine vehicles Clouds image segmentation Wavelet analysis Wavelet domain Signal analysis

来源：评论

学校读者我要写书评

暂无评论

High Performance Reconfigurable Hardware System for real-time image processing

引用

Journal of Systems Engineering and Electronics 2005年第3期000卷 502-509页

作者： Zhao Guangzhou Zhang Tianxu Wang Yuehuan Cao Zhiguo Zuo Zhengrong State Key Laboratory for Image Processing and Intelligent Control，Inst.for Pattern Recognition and Artificial Intelligence，Huazhong Univ.of Science and Technology，Wuhan 430074，P.R.China

A novel reconfigurable hardware system which uses both multi-DSP and FPGA to attain high performance and real-time image processing are presented. The system structure and working principle of mainly processing multi-DSP board, extended multi-DSP board are analysed. The outstanding advantage is that the communication among different board components of this system is supported by high speed link ports & serial ports for increasing the system performance and computational power. Then the implementation of embedded real-time operating systems (RTOS) by us is discussed in detail. In this system, we adopt two kinds of parallel structures controlled by RTOS for parallel processing of algorithms. The experimental results show that exploitive period of the system is short, and maintenance *** it is suitable for real-time image processing and can get satisfactory effect of image recognition.

关键词： rmulti-DSP field programmable gate arrays real-time image processing real time operating systems paralld structure

来源：评论

学校读者我要写书评

暂无评论

Fast algorithm of discrete Walsta-Haar transformation

Fast algorithm of discrete Walsta-Haar transformation

引用

International Conference on Space Information Technology

作者： Lu, Li Shi, Baochang Tian, Jinwen Liu, Jian State Education Commission Key Lab for Image Processing and Intelligent Control Huazhong University of Science and Technology Wuhan Hubei 430074 China Inst. for Pattern Recognition and Artificial Intelligence Huazhong University of Science and Technology Wuhan Hubei 430074 China Department of Mathematics Huazhong University of Science and Technology Wuhan Hubei 430074 China

Walsh-Haar function system that was first intruoduced by us is a new kind of function systems, and has a good global/local property. This function system is called Walsh ordering function system since its generation kernel functions belong to Walsh ordering Walsh function system. We worked out a recursive property of the matrix WHKRm+1 corresponding to the first KR m+1 Walsh-Haar functions in Walsh-Haar function system, and we also proved that Walsh-Haar function system is perfect and orthogonal similar to Walsh function system and Haar function system. Thus, discrete Walsh-Haar transformation (DW-HT) is an orthogonal transformation that can be widely used in signal processing. In this paper, using the recursive property of the matrix WHKRm+1 and the fast algorithm of discrete Walsh transformation (DWT) in Walsh ordering, we have designed a fast algorithm of Walsh ordering DW-HT based on the bisection technique. The idea and method used in this paper can be used for designing fast algorithms of other ordering DW-HTs and other discrete orthogonal transformations.

关键词： Mathematical transformations

来源：评论

学校读者我要写书评

暂无评论

Support value based fusing images with different focuses

Support value based fusing images with different focuses

引用

International Conference on Machine Learning and Cybernetics (ICMLC)

作者： Sheng Zheng Yu-Qiu Sun Jin-Wen Tian Jian Liu State Education Commission Key Laboratory for Image Processing and Intelligent Control Institute of Pattern Recognition and Artificial Intelligence Huazhong University of Science and Technology Wuhan China China Three Gorges University Yichang China

Many vision-related processing tasks, including edge detection and image segmentation, can be performed more easily when all objects in the scene are in good focus. However, in practice, this may not be always feasible as optical lenses, especially those with long focal lengths, only have a limited depth of field. One classical approach to recover an everywhere-in-focus image is to use Laplacian pyramid image fusion. First, several source images with different focuses of the same scene are taken and decomposed into the low/high-frequency components image sequences. Within these decompositions, the high-frequency components image sequences with the largest magnitude are selected at each pixel location. Finally, the fused image can be recovered from the decomposed components image sequences. In the support vector machine (SVM), the pixels with larger support values have a physical meaning in the sense that they reveal relative more importance of the data points for contributing to the SVM model. In this paper, we use Laplacian pyramid for the multi resolution decomposition, and then replace the traditional salient features by support values of the mapped least squares (LS)-SVM for fusing image. Experimental results illustrate that the proposed method outperforms the traditional approach.

关键词： Focusing image sequences Support vector machines Layout Laplace equations image edge detection image segmentation Optical sensors Lenses image fusion

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：