基于柔性形态变换的图像边缘检测

由于自然界中的噪声影响和图像模糊的边缘,这给图像的边缘检测和目标分割带来了一定的困难。柔性形态变换作为一种数学形态学的方法,既保留了标准形态变换的许多优良特性,又具有较好稳健性,为进行目标特征分析提供了可能。使用柔性形态变换构造边缘检测算子,对图像进行边缘检测。实验结果表明,与其他常用的边缘检测算子相比,基于柔性形态变换的边缘检测算子在有效去噪的同时,能较好地保留图像的细节信息,具有很强的实用性。     

基于形态梯度运算的遥感图像边缘检测

针对常规线性边缘检测器处理遥感图象时细节丢失严重的缺点,介绍了数学形态学基本理论,讨论了数学形态学在边缘检测中的应用.形态学的灰度梯度运算是在经典形态变换基础上提出的一类非线性算子.对于结构元素的选取作了一定的说明.另外,还与传统线性算子的处理结果进行了比较.通过计算机对遥感图像的模拟实验表明：基于形态灰度梯度运算的遥感图像边缘检测方法,不但几何意义明确,易于构造,而且性能也优于传统检测算子,证实了该方法的可行性.     

基于多结构元顺序形态变换的灰度图像边缘检测

在简要介绍顺序形态变换的基本概念及相关性质和对顺序形态变换进行边缘检测的原理进行阐述,以及对结构元素和百分位对边缘检测的影响进行讨论的基础上,根据图像形态学多刻度形态滤波的思想,从抑制噪声的角度对基本边缘检测算子进行推广和扩展,首先构造了3种边缘检测算子,并从理论上分析了算子的特性;然后将多结构元与图像边缘进行匹配,提出了3种广义顺序形态边缘检测算子并给出了一般表达形式;最后着重探讨了多结构元素及二重混合顺序形态变换百分位值p、q的选取原则.实验结果表明,该边缘检测算子在抑制噪声对图像边缘的影响和保持图像细节方面,优于传统的边缘检测算子和普通的形态边缘检测器.     

基于多尺度形态学梯度的医学图像边缘检测

边缘检测是数字图像处理的一个重要内容,经典的边缘检测算子算法主要采用Prewitt算子、LOG算子、Canny算子等在空域中进行.数学形态学利用结构元素去探测图像,在讨论形态腐蚀和形态膨胀的基础上,提出了一种基于多尺度形态学梯度的医学图像边缘检测算法.单尺度形态学基元随着尺度的增大形成新的更大尺寸的结构元素,从而检测不同的边缘信息,最终重建较理想的图像边缘.仿真结果表明,该算法在含噪图像中能得到较为理想的图像边缘信息,其抗噪声性能明显优于经典的算子检测算法,检测精度较经典的单一梯度算子检测方法亦有一定的改善.     

基于多结构元素的数学形态学的遥感图像边缘检测方法

提出了一种边缘检测的有效算法。该算法在数学形态学的基础上，针对图像中噪声和边缘形态的不同建立了多结构元素，利用灰度形态变换原理进行边缘提取。实验表明，与经典的边缘检测算子相比，该算法具有很好的边缘提取能力，但其抗噪能力较差。为此，探讨性地提出了基于小波变换和数学形态学相结合的边缘提取方法。     

基于形态学梯度的图像边缘检测算法

边缘检测是数字图像处理的一个重要内容,讨论了经典的边缘检测算子算法,该算法更多地采用Prewitt算子、LOG算子、Canny算子等在空域中进行。数学形态学在图像处理中有广泛的应用,其基本原理是基于利用结构元素去探测图像;在讨论常见数学形态学梯度的基础上,提出了一种基于形态学梯度的图像边缘检测算法,应用定义的形态学梯度结构检测出较理想的图像边缘信息。仿真结果表明,该算法在含噪图像中能得到较为理想的图像边缘信息,其抗噪声性能明显地优于经典的算子检测算法,在检测精度方面较经典的单一算子检测方法亦有一定的改善。     

基于形态学梯度的图像边缘检测算法

边缘检测是数字图像处理的一个重要内容，讨论了经典的边缘检测算子算法，该算法更多地采用Prewitt算子、LOG算子、Canny算子等在空域中进行。数学形态学在图像处理中有广泛的应用，其基本原理是基于利用结构元素去探测图像；在讨论常见数学形态学梯度的基础上，提出了一种基于形态学梯度的图像边缘检测算法，应用定义的形态学梯度结构检测出较理想的图像边缘信息。仿真结果表明，该算法在含噪图像中能得到较为理想的图像边缘信息，其抗噪声性能明显地优于经典的算子检测算法，在检测精度方面较经典的单一算子检测方法亦有一定的改善。     

噪声污染图象中的广义形态边缘检测器

在深入地探讨数学形态学在边缘检测领域中的应用的基础上,系统地给出了普通形态差分算子,并提出了一类广义形态差分算子。同时,把提出的广义形态差分算子应用于受噪声污染的图象,以提取图象的边缘。通过实验表明,广义形态边缘检测算子能较好地提取边缘,在抑制噪声对边缘的影响和保持图象的边缘细节上,效果优于经典的边缘检测器和普通形态边缘检测器。     

基于Tsallis熵差的遥感图像边缘检测方法

基于Tsallis熵差和百分位形态变换,提出了一种改进的遥感图像边缘检测方法。该方法通过构造基于百分位形态变换的边缘检测算子和选择不同方向结构元素进行变换来增加图像的边缘信息,并且该方法在百分位形态变换的基础上还改进了百分位变换的评价准则。它利用图像Tsallis熵差来选择边缘检测算子的百位变换值,将选择Tsallis熵差最大的百分位变换作为变换结果。实验结果表明,与传统的基于数学形态学的边缘检测方法相比,该方法可以最大程度上抑制噪声,有效地提高图像的边缘检测效果。     

基于柔性形态学的梯度边缘检测算法

在深入研究柔性数学形态学边缘检测算法的基础上,提出比传统柔性形态学膨胀和腐蚀算子具有更强鲁棒性的柔性形态学膨胀和腐蚀算子,在此基础上提出柔性形态学梯度边缘检测算法,实验证明了该算法对噪声特别是脉冲噪声有很强的抑制作用,并能很好地检测出图像的边缘信息。     

Soft Morphological Filtering Using a Fuzzy Model and its Application to Colour Image Processing

Abstract Soft morphological filters form a class of filters with many desirable properties. They were introduced to improve the behaviour of standard morphological filters in detail preservation and noise elimination. In this paper, a framework for soft morphological colour image processing using a fuzzy model is introduced. This extends the standard colour morphological operators in the same way that soft greyscale morphology extends the standard greyscale morphology theory. The primary and secondary operations of the new soft morphological approach are defined. The proposed operators are less sensitive to image distortion and to small variations in the shape of the objects, and perform significantly better in impulse noise removal problems, compared to standard morphological operators. Experimental results of the application to real colour images demonstrate these advantageous characteristics of the new operators. Additionally, illustrative examples that exhibit the applicability of the proposed methodology to edge detection problems are also included.An erratum to this article can be found at     

Fuzzy mathematical morphology for biological image segmentation

Due to the imaging devices, real-world images such as biological images may have poor contrast and be corrupted by noise, so that regions in the images present soft edges and their segmentation turns out to be quite difficult. Fuzzy mathematical morphology can be successfully applied to segment biological images having such characteristics of vagueness and imprecision. In this work we introduce an approach based on fuzzy mathematical morphology to segment images of human oocytes in order to extract the oocyte region from the entire image. The approach applies fuzzy morphological operators to detect soft edges in the oocyte images, followed by morphological reconstruction operators to isolate the oocyte region. The main concepts from fuzzy mathematical morphology are briefly introduced and the results of applying fuzzy morphological operators are reported in low-contrast images of human oocytes.     

Fast Algorithms for Area Morphology

Acton, S. T., Fast Algorithms for Area Morphology, Digital Signal Processing11 (2001) 187–203Efficient algorithms are developed for area morphology. As opposed to traditional morphological operations that alter grayscale images via a concatenation of order statistic filters, the area morphological operators manipulate connected components within the image level sets. Essentially, the area morphology filters are capable of removing objects based on the object area solely. These operators can then be effectively used in important multiscale and scale space tasks such as object-based coding and hierarchical image searches. Unfortunately, the traditional implementation of these filters based on level set theory precludes real-time implementation. This paper reviews previous fast algorithms and introduces a pyramidal approach. The full pyramidal algorithm is over 1000 times faster than the standard algorithm for typical image sizes. The paper provides supporting simulation results in terms of computational complexity and solution quality.     

Soft morphological filtering

Stack filters are widely used nonlinear filters based on threshold decomposition and positive Boolean functions. They have shown to form a very large class of filters which includes rank-order operations as well as standard morphological operations. The stack filter representation of an order statistic filter provides an efficient tool for the theoretical analysis of the filter.Soft morphological filters form a large subclass of stack filters. They were introduced to improve the behavior of standard morphological filters in noisy conditions. In this paper, different properties of soft morphological filters are analysed and illustrated. Their connection to stack filters is established, and that connection is used in the statistical analysis of soft morphological filters. Soft morphological filters are less sensitive to additive noise than standard morphological filters. The deterministic properties of soft morphological filters are also analysed and it is shown that soft morphological filters form a class of filters with many desirable properties. For example, they preserve well details of images.     

基于形态学重构的多结构元细胞图像边缘检测

细胞图像边缘检测结果为细胞形态学分析提供依据.针对传统边缘检测算法在细胞图像边缘检测中存在的问题.为了改善图像细节丢失的缺点,提出一种基于形态学重构的边缘检测算法.利用形态学重构运算保持边缘的良好特性,采用多结构元方案,设计形态学重构滤波器对细胞图像进行去噪处理,利用形态学梯度检测算子获取重构后的细胞图像边缘,对获得的多路细胞图像边缘进行加权处理,最终检测出细胞图像边缘.仿真结果表明算法检测效果优于传统边缘检测算子检测效果,检测出的细胞图像边缘连续且一致.     

调节形态学运算及其神经网络实现

数学形态学是一门建立在集合论基础上的学科,为数字图像处理和分析提供了一种有效的工具.在分析传统的数学形态学基本运算的基础上,引入调节数学形态学运算的概念,然后讨论了调节形态学运算的神经网络实现,并给出了用于图像滤波的计算机仿真结果.该方法较之传统的数学形态学基本运算更为灵活.     

Chamfer metrics in mathematical morphology

This paper presents an integration of chamfer metrics into mathematical morphology. Because chamfer metrics can approximate the Euclidean metric accurately, morphological operations based on chamfer metrics give a good approximation to morphological operations that use Euclidean discs as structuring elements. First, a formal definition of chamfer metrics is presented and some properties are discussed. Then, a number of morphological operations based on chamfer metrics are defined. These include the medial axis, the medial line, size and antisize distributions, and the opening transform. A theoretical analysis of some properties of these operators is provided. This analysis concentrates on the relation between distance transformations and reconstructions and the morphological operators just mentioned. This leads to a number of efficient algorithms for the computation of the morphological operators. All algorithms (except for the opening transform) require a fixed number of image scans and are based on local operations only. An algorithm for the opening transform that is 50–100 times as fast as the brute-force algorithm is presented.This research was supported by the Foundation for Computer Science in the Netherlands (SION), with financial support from the Netherlands Organization for Scientific Research (NWO). This research was part of a project in which the TNO Human Factors Research Institute, CWI, and the University of Amsterdam cooperated.     

结合小波滤波和形态学的图像边缘检测方法

针对传统的边缘检测方法对含噪图像检测效果不理想,提出了一种小波滤波和多结构元素的数学形态学相结合的图像边缘检测方法。用广义交叉验证准则进行小波阈值的自适应选取,用此阈值的广义阈值函数的小波滤波方法对含噪图像去噪;构造4种具有代表性的结构元素,根据边缘方向自动选择相应方向的结构元素,用改进的形态学边缘检测算子对图像进行边缘检测,得到在噪声存在条件下较为理想的图像边缘。实验结果表明,该算法能够有效地抑制噪声,检测的边缘较清晰、连续,其检测效果优于传统边缘检测算法。