检索结果-内蒙古大学图书馆

infrared image segmentation method based on 2D histogram shape modification and optimal objective function

Journal of Systems Engineering and Electronics 2013年第3期24卷 528-536页

作者： Songtao Liu Donghua Gao Fuliang Yin Faculty of Electronic Information&Electrical Engineering Dalian University of Technology Department of Information&Communication Engineering Dalian Naval Academy

In the methods of image thresholding segmentation, such methods based on two-dimensional （2D） histogram and optimal objective functions are important. However, when they are used for infrared image segmentation, they are weak in suppressing background noises and worse in segmenting targets with non-uniform gray level. The concept of 2D histogram shape modification is proposed, which is realized by target information prior restraint after enhancing target information using plateau histogram equalization. The formula of 2D minimum Renyi entropy is deduced for image segmentation, then the shape-modified 2D histogram is combined wfth four optimal objective functions （i.e., maximum between-class variance, maximum entropy, maximum correlation and minimum Renyi entropy） respectively for the appli- cation of infrared image segmentation. Simultaneously, F-measure is introduced to evaluate the segmentation effects objectively. The experimental results show that F-measure is an effective evaluation index for image segmentation since its value is fully consistent with the subjective evaluation, and after 2D histogram shape modification, the methods of optimal objective functions can overcome their original forms＇ deficiency and their segmentation effects are more or less improvements, where the best one is the maximum entropy method based on 2D histogram shape modification.

关键词： infrared image segmentation 2D histogram Otsu maximum entropy maximum correlation minimum Renyi entropy.

来源：评论

学校读者我要写书评

暂无评论

infrared image segmentation based on gray-scale adaptive fuzzy clustering algorithm

引用

MULTIMEDIA TOOLS AND APPLICATIONS 2017年第8期76卷 11111-11125页

作者： Liu, Jin Liu, Yanli Ge, Qianqian Xidian Univ Sch Elect Engn Xian 710071 Peoples R China

Since the infrared detector itself is subject to various external disturbances when collecting information, infrared images are characterized by of low SNR, low contrast and blur edge, which greatly increases the difficulty of detection and recognition. Contraposing the problems that a fuzzy clustering algorithm cannot find the reasonable clustering number adaptively, it will have a low infrared image segmentation rate when the gray-scale between object region and background region are of great difference. A gray-scale adaptive fuzzy clustering algorithm (GAFC) is proposed in this work. The methodology uses a coarse-fine concept to reduce the computational burden required for the fuzzy clustering and to improve the accuracy of segmentation that a single fuzzy clustering cannot reach. The coarse segmentation attempts to segment coarsely based on gray level histogram. Firstly, the pseudo peaks in the gray level histogram are removed by introducing a control factor of peak areas and a control factor of peak widths, then in order to find a finer segmentation result, the coarse segmentation result is clustered by an improved fuzzy clustering algorithm that introduces an adaptive function to get the most reasonable cluster number and that defines a logarithmic function as a measurement of distance. The results of experimental data show that not only the GAFC mentioned in this paper preserves the advantages in multi-threshold segmentation method which is fast and easy, and behaves well in segmenting infrared images in complex environments.

关键词： Adaptive fuzzy clustering infrared image segmentation Multi-threshold segmentation Gray level histogram Pseudo-peak removal

来源：评论

学校读者我要写书评

暂无评论

infrared image segmentation based on Region of Interest Extraction with Gaussian Mixture Modeling 27

Infrared Image Segmentation based on Region of Interest Extr...

引用

Conference on Automatic Target Recognition XXVII

作者： Yeom, Seokwon Daegu Univ Sch Comp & Commun Engn Gyongsan 38453 Gyungbuk South Korea

ISBN: (纸本)9781510609051;9781510609068

infrared (IR) imaging has the capability to detect thermal characteristics of objects under low-light conditions. This paper addresses IR image segmentation with Gaussian mixture modeling. An IR image is segmented with Expectation Maximization (EM) method assuming the image histogram follows the Gaussian mixture distribution. Multi-level segmentation is applied to extract the region of interest (ROI). Each level of the multi-level segmentation is composed of the k-means clustering, the EM algorithm, and a decision process. The foreground objects are individually segmented from the ROI windows. In the experiments, various methods are applied to the IR image capturing several humans at night.

关键词： infrared image segmentation region of interest (ROI) extraction Gaussian mixture modeling multilevel segmentation

来源：评论

学校读者我要写书评

暂无评论

infrared image segmentation with 2D OTSU method based on particle swarm optimization

Infrared image segmentation with 2D OTSU method based on par...

引用

5th International Symposium on Multispectral image Processing and Pattern Recognition

作者： Zhao, Guangzhou Zhu, Guangxi Zeng, Yurong Zhang, Tianxu Xu, Huazhong Huazhong Univ Sci & Technol Wuhan Natl Lab Optoelect Dept Elect & Informat Wuhan 430074 Peoples R China Wuhan Univ Technol Sch Automat Wuhan 430070 Peoples R China Hubei Univ Econ Sch Comp Wuhan 430205 Peoples R China Huazhong Univ Sci & Technol Inst Pattern Recognit & Artificial Intelligence Wuhan 430074 Peoples R China

ISBN: (纸本)9780819469519

This paper proposes a global threshold selection method to do infrared image segmentation, which uses both gray-level distribution and spatial information, namely, two-dimensional OTSU method (2D OTSU). It often gets better anti-noise performance. What's more, taking consideration of the complexity of its computation, we introduce a new heuristic optimization algorithm, called the particle swarm optimization (PSO) algorithm to search the result. So an algorithm for PSO-based 2D Otsu segmentation is proposed. The experiments of segmentation the infrared images are illustrated to show that the proposed method can get ideal segmentation result with less computation cost.

关键词： infrared image segmentation 2D OTSU PSO algorithm threshold technique real time processing

来源：评论

学校读者我要写书评

暂无评论

infrared image segmentation using HOG feature and kernel extreme learning machine

Infrared image segmentation using HOG feature and kernel ext...

引用

Conference on Applied Optics and Photonics (AOPC) - image Processing and Analysis

作者： Liang, Ying Wang, Luping Zhang, Luping Natl Univ Def Technol Sch Elect Sci & Engn Changsha 410073 Hunan Peoples R China

ISBN: (纸本)9781628419009

image segmentation is an important application in computer vision. Nowadays, image segmentation of infrared image has not gain as much attention as image segmentation of visible light image. But this application is very useful. For example, searching and tracking targets with infrared search and track system (IRST) has been widely used these days due to its special passive mode. So it can be used as a kind of supplementary equipment for radar. infrared image segmentation can help computers identify backgrounds of the image, and help it automatically adjust the related parameters for the next work, such as targets recognition or targets detection. Our work proposed a new image segmentation method for infrared image using histogram of oriented gradients (HOG) feature and kernel extreme learning machine (kernel ELM). HOG are feature descriptors which can be used in computer vision and image processing for the purpose of object detection. In this paper, we extract HOG feature of infrared image, and use this feature as the basis for classification. After having feature, we use kernel extreme learning machine to do the segmentation. Kernel extreme learning machine has shown many excellent characteristics in classification. By testing our algorithm proposed in our paper, we demonstrated that our algorithm is effective and feasible.

关键词： HOG feature kernel extreme learning machine infrared image segmentation

来源：评论

学校读者我要写书评

暂无评论

infrared image segmentation via intelligent genetic algorithm based on maximum entropy

Infrared image segmentation via intelligent genetic algorith...

引用

7th International Conference on Signal Processing

作者： Wu, J Qiu, Y Liu, J Tian, JW Huazhong Univ Sci & Technol State Key Lab Image Proc & Intelligene Control Wuhan 430074 Peoples R China

ISBN: (纸本)7121002159

This paper presents a fast and effective segmentation method for infrared image, based on fuzzy filtering, the criteria of maximum entropy and intelligent genetic algorithm. A fuzzy filter is applied to depress the Gaussian(-like) noise. Then we use the theory of maximum entropy to select the optimum threshold. A new intelligent genetic algorithm (IGA), which applies an intelligent crossover (IC) based on orthogonal arrays (OAS) is proposed to solve this optimal problem. Experiment results show that the proposed method can depress the Gaussian(-like) noise effectively, segment the infrared image properly, and is faster than the conventional genetic algorithm and Exhaustive search, also is easier to implement on hardware.

关键词： infrared image segmentation fuzzy filtering maximum entropy intelligent genetic algorithm thresholding

来源：评论

学校读者我要写书评

暂无评论

infrared image segmentation via fast fuzzy c-means with spatial information

Infrared image segmentation via fast fuzzy c-means with spat...

引用

IEEE International Conference on Robotics and Biomimetics (ROBIO 2004)

作者： Wu, J Li, J Liu, J Tian, JW Wuhan Univ Sci & Technol Coll Informat Sci & Engn Wuhan 430081 Peoples R China

ISBN: (纸本)0780386418

Forward Looking Infra-Red (FLIR) image segmentation is crucial for Automatic Target Recognition (ATR). This paper presents a new clustering algorithm for FUR image segmentation. We combine the standard fuzzy means algorithm (FCM) with two-dimensional histogram of the image, and modify the membership function of the FCM for taking into account the spatial information of image data. Since the FCM is computationally cumbersome, we also present a fast and efficient implementation of the proposed method. Experiments show that the proposed method can segment the infrared image properly and fast, also has the better robust performance to noise.

关键词： infrared image segmentation clustering fuzzy c-means membership function robust

来源：评论

学校读者我要写书评

暂无评论

infrared image segmentation based on 2-D maximum fuzzy entropy and intelligent genetic algorithm

Infrared image segmentation based on 2-D maximum fuzzy entro...

引用

International Conference on Intelligent Mechatronics and Automation

作者： Wu, J Li, J Liu, J Tian, JW Wuhan Univ Sci & Technol Coll Informat Sci & Engn Wuhan 430081 Hubei Province Peoples R China

ISBN: (纸本)0780387481

This paper presents a fast and effective segmtentation method for Forward Looking infra-Red (FLIR) image, based on fuzzy filtering, the principle of 2-D maximum fuzzy a entropy and intelligent genetic algorithm. A new fuzzy operator is applied to the enhancement of noisy images. Basing on fuzzy relation and maximum fuzzy entropy principle, we perform fuzzy partition on a 2-D histogram. A new intelligent genetic algorithm (IGA), which applies an intelligent crossover (IC) based on orthogonal arrays (OAS), is proposed to search the optimal combination of the fuzzy parameters finally used to segment the image. Experiment results show that the proposed method can depress the Gaussian (-like) noise effectively, segment the infrared image automatically and properly, and is faster than the conventional genetic algorithm and exhaustive search.

关键词： infrared image segmentation fuzzy filtering fuzzy entropy membership function intelligent genetic algorithm

来源：评论

学校读者我要写书评

暂无评论

infrared image segmentation of Aircraft Skin Damage Based on the Game between MRF and Improved GVF Snake 29

Infrared Image Segmentation of Aircraft Skin Damage Based on...

引用

第29届中国控制与决策会议

作者： Kun Wang Momo Guo Yanxiao Lee Li Wang Jingchang Zhuge School of Electronic Information and Automation Civil Aviation University of China School of Vocational and technical Civil Aviation University of China

ISBN: (纸本)9781509046584

infrared image possess the characteristics of large noises, concentrated intensity, blurring target edge, and poor contrast between target and background, which causing the segmentation of damage targets in aircraft skin infrared thermal image become difficult. Aiming at this problem, a method of infrared image segmentation based on the game between Markov Random Field(MRF) and improved Gradient Vector Flow(GVF) Snake is proposed in this paper. On the basis of wavelet transform denoising, the infrared image is firstly classified into target and background domain by Maximum Between-Class Variance. Secondly, region-based MRF image segmentation model and edge-based improved GVF Snake image segmentation model are established, respectively. These two algorithms are executed in parallel and independently, and the iteration stops when convergence condition is reached. Finally, Game theory is applied to fuse the segmentation results of the above two models. When the game reaches the Nash equilibrium, the optimal solution of segmentation is acquired. The experimental results show that the proposed method can successfully segment the defect targets from the infrared images of aircraft aluminum skin specimens and effectively improve the accuracy of infrared image segmentation.

关键词： infrared image segmentation Game Theory MRF GVF Snake OTSU

来源：评论

学校读者我要写书评

暂无评论

infrared image segmentation method based on spatial coherence histogram and maximum entropy 3

Infrared image segmentation method based on spatial coherenc...

引用

Conference on infrared, Millimeter-Wave, and Terahertz Technologies III

作者： Liu, Songtao Shen, Tongsheng Dai, Yao Dalian Naval Acad Dept Informat Operat Dalian 116018 Peoples R China China Def Sci & Technol Informat Ctr Beijing 100142 Peoples R China

ISBN: (纸本)9781628413489

In order to segment the target well and suppress background noises effectively, an infrared image segmentation method based on spatial coherence histogram and maximum entropy is proposed. First, spatial coherence histogram is presented by weighting the importance of the different position of these pixels with the same gray-level, which is obtained by computing their local density. Then, after enhancing the image by spatial coherence histogram, 1D maximum entropy method is used to segment the image. The novel method can not only get better segmentation results, but also have a faster computation time than traditional 2D histogram-based segmentation methods.

关键词： infrared image segmentation image enhancement spatial coherence histogram maximum entropy

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：