基于最大类间方差图象分割和ROI区域的数字水印

姚潇 朱世交 李儒耘

提出一种利用图象分割而划分图像ROI区域，从而进行水印的自适应嵌入的新方法。图像分割是图像处理中的基本操作，通过基于内容的图像分割，可以将图像中的感兴趣区域（ROI）提取出来，图像分块后，将在感兴趣区域的块中进行水印的嵌入，水印嵌入到各子块DCT域的中频部分，从而充分提高水印的鲁棒性。[著者文摘]

高分辨率SAR图像分割及目标特征提取

High-Resolution SAR Image Segmentation and Target＇s Feature Extraction

高贵[1] 匡纲要[1] 李德仁[2]

提出了一种非监督SAR图像快速分割算法,对分割得到的目标区域进行特征提取.分割方法利用固体热扩散模型与图像尺度空间的等价性,在SAR图像初始分割的基础上,引入最大后验概率矩阵的各向异性多尺度平滑,在保持图像结构信息的同时滤除斑点噪声对于分割的影响.然后提取目标区域6个特征以详细描述目标,实验结果表明：该方法计算速度快,能够从获得的目标区域得到大量有用的信息.[著者文摘]

An unsupervised fast segmentation method for SAR image is proposed in this paper, and features are extracted from the target region gained from segmentation. According to the equivalence between the solid heat diffusion model and image scale-space, and on the basis of initial segmentation of SAR image, This method includes the multi-scale anisotropic smoothing of the posterior probability matrixs to get rid of the effect of speckle and preserve the important structure information of image. Then 6 features of target area are extracted to describe target in detail. The experiment results show that this algorithm is fast and can get lots of information from target areas.[著者文摘]

遥感图像分形特征提取与分割

Fractal Feature Extraction and Segmentation of Remote Sensing Imagery

郑桂香 蔺启忠

分形理论由B．B．Mandelbrot于20世纪70年代中期创立，现已被广泛地应用于自然科学和社会科学的几乎所有领域。本文在前人研究的基础上，利用双毯法（Double Blanket Method）提取出图像的分形特征并用于图像分割，进一步证实了分形在此领域的可行性和有效性。首先，通过比较局部分形维数偏移全局分形维数的标准差来确定适合该方法的最优滑动窗口。其次，考虑到单尺度分维特征的局限性，提取出多尺度的特征值并建立分形维数谱。然后，以模拟图像为例，分析图像中各区域的分维谱，选择适当尺度的分形特征，利用最大似然法对图像进行分割。最后，将分形理论应用于遥感图像中，与传统的基于灰度值特征的图像分割方法相比，加入图像的空间分形纹理特征后分割精度明显提高。研究结果表明：分维值的大小和变化趋势可以表示不同地物的空间复杂度，结合地物的光谱以及灰度信息能有效地识别目标地物。[著者文摘]

Fractal method is a new subject which was founded by American scientist B. B. Mandelbrot in the middle of 1970s, which is widely applied to almost all the fields of physical and social sciences. Based on previous studies, this paper extracted the fractal features of images by using the Double Blanket Method and applied them to image segmentation which showed the validity and feasibility of fractal in this field further. Firstly, an optimum window was selected by comparing the standard error between local and global fractal dimensions. Secondly, multi-scale fractal features were extracted and fractal dimension spectrums were established with regard to single-scale＇s limitation. Then, by analyzing object fractal dimension spectrum, appro- priate features were utilized to simulative image segmentation based on the maximum likelihood method. At last, fractal theory was bestowed to remote sensing image. Relative to the traditional method consisted of only gray level features, the overall seg- mentation accuracy was obviously improved when considered the spatial fractal texture features. The results showed that fractal dimension and its change trend could display spatial complexity of different objects. Combined with the spectrum and gray level information, the objects can be discriminated easily.[著者文摘]

自适应阈值分割的图像边缘检测方法研究

Adaptive Thresholds Edge Detection for Image Based on Segmentation

高岚 廖云良 朱波华 李俊 周金勇

边缘是图像视觉中的一种重要信息,是图像最基本的特征之一。在边缘检测过程中为了消除传统分水线算法引起的过分割现象,给出了一种新的过分割区域合并算法,该方法能把复杂的目标图像分割成为一系列反映目标基本结构特征的简单区域。然后利用轮廓提取算法去除图像内部的像素点,经最后处理得到的部分即是图像的边缘。[著者文摘]

The edge is an important feature that human vision recognizes image target. Edge is also one of the most fundamental character of a image. In order to eliminate the over-segmentation of traditional watershed, a new merge algorithm of over segment regions was proposed in edge detection. This method could effectively segment the target with the complicated nature background to a series of simple domain, which constructed the fundamental structure of the object. Then, an contour extraction algorithm was used to remove the inner pixel of image, and the last part was image edge.[著者文摘]

高分辨率遥感影像特征分割及算法评价分析

Research on High Resolution Remote Sensing Image Segmentation. Methods Based on Features and Evaluation of Algorithms

明冬萍[1] 骆剑承[1] 周成虎[1] 王晶[2]

图像分割一直是图像处理和计算机视觉领域中的一项关键技术。本文首先从遥感影像地学处理与应用的角度阐述了影像分割技术对于遥感信息提取和目标识别的重要性．然后提出了基于特征的高分辨率遥感影像信息提取技术框架．建立了一套基于特征的遥感影像分割方法及分类体系。同时，鉴于遥感影像分割方法评价的重要性，阐述了一种高分辨率遥感影像分割方法评价的思路．并对几种典型的基于特征的遥感影像分割方法进行定性和定量的试验和评价．对其各自的性能和适用面进行对比分析。最后．指出了遥感影像特征分割方法所存在的问题及其发展趋势。[著者文摘]

Image segmentation is a key technique ＂in image processing and computer vision field. From the point of view of geo-processing and application of remote sensing images, this paper emphasizes the importance of image segmentation for information extraction and targets recognition from remote sensing images and sets a classification system of common remote sensing image segmentation methods. In addition, this paper states the thoughts of high resolution RS image segmentation methods evaluation and tests it by evaluating four typical image segmentation algorithms based on features with six images qualitatively and quantitatively. The four typical image segmentation algorithms are Max-Entropy （ME）, Split＆Merge （SM）, improved Gauss Markov Random Field（GMRF） and Orientation＆Phase（OP）. In the qualitative evaluation, this paper analyses these algorithms in terms of their rationale and gets a rough evaluation. In the quantitative evaluation, image complexity is taken into account firstly and five measures are employed. The five measures are removed region rumber, nonuniformity within region measure, contrast across region measure, variance contrast across region measure and edge gradient measure. The qualitatively and quantitatively evaluation results are important to perform the optimal selection of segmentation algorithm in practical work. In the end, this paper draws some conclusions about high resolution remote sensing image segmentation and enumerates the flaws of image segmentation methods evaluation, especially it concludes the application prospect of high resolution RS image segmentation.[著者文摘]

基于局部模糊方差的过渡区提取及图像分割

EXTRACTION OF TRANSITION REGION AND IMAGE SEGMENTATION BASED ON LOCAL FUZZY VARIANCE

田岩[1] 刘继军[1] 谢玉波[1] 史文中[2]

为取得良好的图像分割效果，利用局部模糊方差区分过渡区与背景区的差异，提出了一种基于局部模糊方差的图像过渡区提取方法并用于图像的分割．首先将利用模糊集构造模糊方差的方法拓展到二维图像的情形，进而利用局部模糊方差构造过渡区．在此基础上通过多阈值的选择方法在过渡区上确定阈值，最后将其用于图像分割．实验结果表明所提方法具有较强的鲁棒性，并能取得良好的分割效果．[著者文摘]

To obtain a favorable segmented result of an image, a transition region method, based on the difference of local fuzzy variance between transition region and background, was proposed and used for image segmentation. First, the method to construct fuzzy variance based on fuzzy set was extended to the case of two dimensional image; second, a transition region was obtained by the local fuzzy variance; and at last the final segmented result was acquired by a multi-threshold selecting method. Experimental results show that the proposed method is robust and it can provide satisfactory segmented result.[著者文摘]