基于均值漂移滤波及谱分类的海面舰船红外目标分割

提出了一种有效的海面舰船红外目标分割方法.利用均值漂移方法的不连续保持性滤波特性,滤除海面的强杂波干扰,同时又不损失舰船目标的信息.根据滤波得到的区域构建区域邻接图,采用基于最大最小SST图划分算法对区域邻接图的节点进行划分.划分结果最终将图像分为天空背景、海面背景以及舰船目标3个部分.由于采用区域节点来表征图像,较之采用原始图像象素节点表示,其节点个数大大减少,从而使算法的计算效率得到很大提高.实验结果也表明提出两步算法具有优越的性能,能够在海面强杂波干扰的情况下有效提取舰船红外目标.     

An evolutionary algorithm for broadcast scheduling in wireless multihop networks

A technical challenge in successful deployment and utilization of wireless multihop networks (WMN) are to make effective use of the limited channel bandwidth. One method to solve this challenge is broadcast scheduling of channel usage by the way of time division multiple access (TDMA). Three evolutionary algorithms, namely genetic algorithm (GA), immune genetic algorithm (IGA) and memetic algorithm (MA) are used in this study to solve broadcast scheduling for TDMA in WMN. The aim is to minimize the TDMA cycle length and maximize the node transmissions with reduced computation time. In comparison to GA and IGA, MA actively aim on improving the solutions and is explicitly concerned in exploiting all available knowledge about the problem. The simulation results on numerous problem instances confirm that MA significantly outperforms several heuristic and evolutionary algorithms by solving well-known benchmark problem in terms of solution quality, which also demonstrates the effectiveness of MA in efficient use of channel bandwidth.     

区域信息驱动的多目标进化半监督模糊聚类图像分割算法

现有的多目标进化聚类算法应用于图像分割时,往往是在图像像素层面上进行聚类,运行时间过长,而且忽略了图像区域信息使得图像分割效果不太理想。为了提高多目标进化聚类算法的分割效果和时间效率,该文将图像区域信息与部分监督信息引入多目标进化聚类,提出图像区域信息驱动的多目标进化半监督模糊聚类图像分割算法。该算法首先利用超像素策略获得图像的区域信息,然后结合部分监督信息,设计融合区域信息和监督信息的适应度函数,接着通过多目标进化策略对多个适应度函数进行优化得到最优解集。最后构造融合区域信息与监督信息的最优解评价指标,实现从最优解集中选取一个最优解。实验结果表明:与已有多目标进化聚类算法相比,该算法不但分割效果有所提升,而且运行效率得以提高。     

基于互补空间信息的多目标进化聚类图像分割

现有的多目标进化聚类算法应用于图像分割时,没有考虑图像的任何空间信息,使得该类算法在含噪图像上的分割性能不理想。该文鉴于图像的局部空间信息和非局部空间信息的互补性,试图将这两种空间信息同时引入到聚类有效性函数中,构造了融合互补空间信息的目标函数,进而提出了应用于图像分割的基于互补空间信息的多目标进化聚类算法。该算法采用染色体可变长编码策略在进化过程中自动确定图像分割数目,减少了人为干预。自然图像的分割实验表明,该算法不但能在含噪图像上取得较为满意的分割性能,而且适用于多种类型的含噪图像。     

Automatic segmentation of color images with transitive closure

In this paper, a mask based automatic segmentation algorithm for color images which uses pixel similarity has been presented. Main concept of the algorithm relies on spatial mask for course segmentation and the Warshall's transitive closure (TC) computation algorithm for region merging. Although the proposed spatial mask approach reduces the computational burden required for segmentation or clustering techniques such as seeded region growing (SRG) or fuzzy c-means (FCM) in which user supplied parameters are essential, it has over segmentation drawback. Therefore, the transitive closure algorithm, which uses adjacency and similarity matrix associated to undirected graph of the over segmented image, has been employed to merge the regions. After comparing to existing methods, the obtained experimental results confirmed that the color images as well as gray level images could be segmented with considerable accuracy. Also computational complexity of image segmentation is significantly reduced. Furthermore, there is no need any user supplied parameter such as the number of clusters or seed points.     

快速分形图象压缩算法的研究

分形编码是一种非常有潜力的图象压缩技术，但因其与具很高的时间复杂度，故至今未能获得广泛的应用，本文提出了旨在降低分形编码复杂度，缩短编码时间的分形图像压缩改进算法，该算法采取递归四树分块结构，将多种块分类技术相结合，并通过预计算，旋转与翻转标准化等方法降低计算复杂度，采取高效的存储方案来提高压缩化，力求在图像质量，压缩比和编码时间上取得了良好的折Ｚｏｎｇ使分形编码更加实用化。实验结果表明，采用这种     

蝙蝠优化的二维Tsallis熵多阈值SAR图像分割

针对智能优化SAR图像分割算法存在计算量大、易陷入局部最优、分割精度不够等问题,融合蝙蝠算法和二维Tsallis熵多阈值,提出了一种蝙蝠优化的二维Tsallis熵多阈值SAR图像分割算法。算法利用立方映射均匀化初始蝙蝠种群,引入Levy飞行特征加强算法跳出局部最优能力,使用Powell局部搜索加快算法收敛等3方面改进蝙蝠算法;同时将二维Tsallis熵单阈值分割方法扩展到多阈值分割,建立基于多阈值的选取方法,并结合改进的蝙蝠算法,将二维Tsallis熵多阈值应用于SAR图像分割中。仿真结果表明,与其他智能优化分割算法相比,本分割算法在边缘处理和分割精度上都有明显优势。     

Efficient morphological segmentation using a new connected operator

An efficient segmentation algorithm for region-based coding is proposed. A new connected operator based on both size and contrast is presented and an efficient region merging algorithm which preserves high quality in terms of the number of regions is proposed. Experimental results show that the proposed algorithm achieves a good performance in terms of the image quality and the number of regions     

Interpolated histogram method for area optimised median computation

The article describes an area efficient algorithm for real-time approximate median computation on VLSI platforms. The improvement in performance and area optimisation are achieved through linear interpolation within a reduced number of histogram bins. In order to reduce the hardware utilisation further, an approximation technique for interpolation is also proposed. This approach extends the utility of the histogram method to data sets having a large dynamic range. The performance of the proposed algorithm in terms of mean squared error (MSE) and resource utilisation is provided and compared to that of the existing algorithms. This comparison indicates that more than 60% optimisation in resources is achieved with marginal compromise in the accuracy of the median. The proposed algorithm finds applications in the areas of image processing, time series analysis and median absolute deviation (MAD) computation.     

基于分水岭变换和蚁群聚类的图像分割

针对传统分水岭分割算法对噪声敏感和易于产生过分割问题,提出一种新的基于分水岭和蚁群智能聚类的图像分割方法(CWAC,Combining watersheds and ant colony clustering).CWAC方法首先用分水岭变换对图像做初分割,然后用蚁群方法在区域之间进行聚类合并,获得最终的分割结果.CWAC不但成功地解决了分水岭存在的过分割问题,还大大提高了蚁群聚类算法的搜索效率;本文利用分水岭变换后的灰度信息和空间信息,定义了一种新的引导函数,可更准确有效引导蚁群聚类.实验结果表明CWAC可以快速准确地分割出目标,是一种有效的图像分割方法.     

一种从视频压缩码流中精确提取运动对象的快速算法

针对目前大部分视频对象分割方法相当复杂而且计算量大的问题,提出了一种在压缩域粗分割,在空域精细分割的方法。该方法利用压缩域中运动向量进行聚类,得到运动对象的初始分割。将分割模板通过运动参数映射到参考帧I帧,,解码初始分割区域进行Canny边缘俭测和边缘跟踪,即可得到精确的对象轮廓。该方法使得处理的数据量保持最小,节约了处理时间并得到了像素级精度的分割对象。     

Towards multi-stage texture-based active contour image segmentation

In this paper, we present a three-stage approach to incorporation of texture analysis into a two-dimensional active contour segmentation framework. This approach allows to utilise texture information alongside other image features. The proposed method starts with an initial unsupervised feature computation and selection, then moves to a fast contour evolution process and ends with a final refinement stage. The algorithm is designed to be general in its nature and not restricted to any particular texture feature extraction method. In this paper, the initial stage generates a set of feature maps consisting of grey-level co-occurrence matrix and Gabor features. The implementation makes an extensive use of hardware acceleration for efficient calculation of a relatively large number of features. The performance of the method was tested on various synthetic and natural images and compared with results of other algorithms.     

基于新遗传算法的Otsu图像阈值分割方法

最大类间方差（Otsu）图像分割法是常用的一种基于统计原理的图像阈值分割方法。为了改善Otsu耗时较多、分割的精度低、易产生图像误分割等不足,将猴王遗传算法与Otsu算法结合,运用猴王遗传算法的原理,寻找图像灰度的最大类间方差,即最佳阈值。结果表明,结合后的方法不仅提高了图像的分割质量、缩短了运算时间,而且非常适合图像的实时处理。     

结合光谱相似性与相位一致模型的高分辨率遥感图像分割方法

提出一种结合高分辨率遥感图像的光谱相似性与相位一致边缘检测模型的分水岭分割方法。分水岭分割算法的性能依赖于图像边缘梯度图。利用同类地物的光谱相似性特点,可有效抑制相位一致模型边缘检测中产生的伪边缘和噪声信息,从而获得更好的遥感图像分割结果。本文首先基于目标像元与其邻域像元之间的光谱曲线距离之和定义光谱相似性模型,结合相位一致模型获得边缘响应强度;然后利用自动标记分水岭变换方法实现高分辨率遥感图像分割。使用本文方法和其它方法对遥感图像进行了分割实验,并利用基于多光谱信息熵方法对分割结果进行了非监督评价和比较,同时对计算耗时进行了对比分析。结果表明本文所提方法可以有效地抑制遥感图像的过分割现象,并取得较好的分割结果。     

改进海鸥算法的多阈值图像分割算法北大核心CSCD

为进一步提高图像分割精度,改善传统多阈值图像分割方法计算量大、分割慢的问题,提出了改进海鸥算法(improved seagull optimization algorithm,ISOA)的多阈值图像分割方案。针对原始海鸥算法(seagull optimization algorithm,SOA)存在早熟、寻优精度不足的问题,首先,采用cubic混沌映射优化初始解,提高搜索效率;其次,引入鹰栖息优化算法(eagle perching optmizer,EPO)的缩放因子和疯狂算子进行扰动,并与麻雀搜索算法(sparow search algorithm,SSA)警戒者的位置更新相结合,优化寻优精度和收敛速度,避免陷入局部最优。利用6种基准测试函数对ISOA进行寻优性能测试。最后,将ISOA与图像分割的最优阈值选取相结合,进行基于Otsu的多阈值图像分割,并与现有分割算法进行对比。仿真结果表明,ISOA在基于Otsu的图像分割中,100%取得了最优值,且80.9%的结果优于其余算法,使图像的分割精度和质量均得到了优化。     

Multi-threshold algorithm about image segmentation based on polynomial uniform approximation

Aiming at those shortcomings of previous multi-threshold image segmentation algorithm such as large complexity and instability caused by the image histogram glitch interference,a new multi-threshold image segmentation algorithm was proposed using Bernstein polynomial to uniformly approximate histogram curve.First,according to the approximation theory of Weierstrass to construct Bernstein polynomial for the histogram curve,then more difficult peak value calculating of the histogram was reduced to the Bernstein polynomial extremal generating,that was exported easily by the first and second derivative of Bernstein polynomial function,and finally obtain the actual peak value of the image histogram by picking up these extremes and polar values and filtering through classification algorithm,and finish multi-threshold image segmentation.Experimental results show that the algorithm is insensitive for histogram glitch interference,the overall is stable,the redundant computation and time complexity are smaller,with less time and high efficiency,the approximate performance and segmentation effect are better.     

采用进化规划和最大熵的目标图像分割算法

图像分割是图像处理和计算机视觉中关键技术之一。在分析最大熵法和进化规划算法(EP)基础上,提出一种自动阈值选取的图像分割算法。该算法以图像的最大熵作为适应度值,将图像分割问题看作一个全局数值优化问题,利用进化规划全局寻优和快速计算的特点,搜索一个最佳阈值用于图像分割。仿真结果表明,本方法很好地解决了最大熵法计算量大的缺点,速度快且分割效果好。     

基于Tsallis交叉熵快速迭代的河流遥感图像分割

为了使河流遥感图像分割的精度和速度进一步提高,本文提出了一种基于二维Tsallis交叉熵快速迭代的河流遥感图像分割方法。鉴于现有的Tsallis交叉熵阈值法运算效率不够高,首先提出了一维Tsallis交叉熵阈值选取的快速迭代算法;然后导出了基于灰度级—邻域平均灰度级直方图的Tsallis交叉熵阈值选取公式,以进一步提高分割精度,并采用递推方式计算阈值选取准则函数中的中间变量,避免其重复运算,加快运算速度;最后,提出了二维Tsallis交叉熵阈值选取的快速迭代算法,推导出相应的公式,大大减少了运算量。大量实验结果表明,与近年来提出的4种阈值分割方法相比,本文方法在对河流遥感图像的分割效果及运行时间上均有明显优势,是河流检测与类型识别系统中可选择的一种快速有效的分割方法。      

结合光谱相似性与相位一致模型的高分辨率遥感图像分割方法

提出一种结合高分辨率遥感图像的光谱相似性与相位一致边缘检测模型的分水岭分割方法.分水岭分割算法的性能依赖干图像边缘梯度图.利用同类地物的光谱相似性特点,可有效抑制相位一致模型边缘检测中产生的伪边缘和噪声信息,从而获得更好的遥感图像分割结果.首先基于目标像元与其邻域像元之间的光谱曲线距离之和定义光谱相似性模型,结合相位一致模型获得边缘响应强度;然后利用自动标记分水岭变换方法实现高分辨率遥感图像分割.基于此方法和其它方法进行了分割实验,并利用基于多光谱信息熵方法对分割结果进行了非监督评价和比较,同时对比分析了计算耗时.结果表明此方法可有效抑制遥感图像过分割现象,并取得较好的分割结果.     

Wavelet image coding based on significance extraction usingmorphological operations

An algorithm is proposed for improving Servetto et al.'s (see Proceedings of the International Conference on Image Processing, Washington, DC, p.530-3, 1995) method of morphological representation of wavelet data (MRWD), which is among the most efficient wavelet-based image compression algorithms. In MRWD, morphological dilation is used to capture and encode the arbitrarily shaped clusters of significant coefficients within each subband and high compression is achieved. But there are still several deficiencies for rectification in MRWD. An efficient image compression algorithm is proposed, in which, for each subband, morphological dilation is first used to extract and encode the clustered significant coefficients, and the remaining space is encoded in an efficient way. Instead of encoding the large number of zeros one by one, only the small number of remaining significant coefficients and their positional information are encoded. Experimental results show that this improvement is very effective, especially for images with large and relatively smooth regions