基于敏感区域多结构元素形态学边缘检测算法

Edge Detection Algorithm for Sensitive Region Based on Morphology of Multi-Structural Element

伯绍波 闫茂德 贺昱曜

在边缘检测算法的应用中，很难同时兼顾图像处理效果和处理速度，为此，提出了一种新的边缘检测算法，将边缘处理集中在感兴趣的图像区域中。该算法利用梯度算子获得图像中的敏感区域，再构造多种结构元素，结合形态学梯度和OTSU分割法检测敏感区域的边缘。应用于沥青路面裂缝图像检测，实验结果表明，与其它边缘检测算法相比，该算法不仅具有很好的边缘提取能力，而且具有很强的抗噪能力。在保证处理效果的同时，也保证了处理速度，有很高的实用性和推广性。[著者文摘]

In the practical application of edge detection, it is difficult to make a balance between image processing effect and processing speed. In order to solve this problem, a novel edge detection algorithm is presented which the interested regions of the image are processed only. The proposed algorithm employs the gradient operator to gain the sensitive regions in the image. After that, combining the morphology-gradient operator with OTSU segmentation algorithm, it constructs multi-structural element to detect the edges in sensitive regions. The presented algorithm is applied to the asphalt pavement crack detection. The experimental result indicates that compared with other edge detection algorithms, it has not only a good ability to extract the image edge, but also a strong ability to suppress the noise in the image. Moreover, it can provide good image processing effect and processing speed.[著者文摘]

基于灰度形态学的烟叶图像边缘检测

Edge Detection in Tobacco Leaf Image Based on Grayscale Morphology

郭骏[1] 潘申[1] 胡小建[2]

烟叶图像的边缘提取是利用计算机进行烟叶检测与分级的关键步骤。为了能够在提取边缘的同时保留图像的边缘细节信息，该文针对CCD获取的烟叶原始图像，利用灰度形态学的算法，构造了全方位的结构元素进行边缘的提取。实验证明，基于灰度形态学腐蚀变换的边缘检测算法是有效的。[著者文摘]

Edge extraction in tobacco leaf image is the key step in tobacco leaf detecting and grading using computer technology. In order to extract edge and keep detailed edge information, the original tobacco leaf images obtained by CCD camera are studied. Omni-directional structure element is structured to detect edge according to the grayscale morphology arithmetic. Efficiency of edge detection based on the grayscale morphology erode transform is proved by experimental results.[著者文摘]

改进的基于形态学梯度法的车辆图像边缘检测方法

An Improved Vehicle Image Edge Detection Based on Morphology Gradient

刘立程

在分析和比较用于图像边缘检测的多尺度多方位的形态学梯度算法和多级形态学运算合成法的基础上,提出了一种改进的基于形态学梯度法的汽车图像边缘检测方法.经过实验检验,并与其它形态学边缘检测方法进行了比较,证明该方法对汽车图像边缘检测具有较好效果.[著者文摘]

On the analysis and comparison of the multi-scale, multi-direction and multi-grade mathematical morphology gradient algorithm for the image edge detection, an improved vehicle image edge detection method based on the morphology gradient is given in this paper. Experiment results are obtained by applying the edge detector on a truck image , which prove to be more efficient than other existing morphology edge detectors.[著者文摘]

基于形态梯度运算的遥感图像边缘检测

Edge Detection Method of Remote Sensing Images Based on Mathematical Morphology of Gradient

苏波

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.[著者文摘]

In this paper,the basic theory of the morphology is presented and the morphology applied to detecting edge is discussed,in the light of the classical inear edge detector lose RS image details severely.The morphology of Gray Gradient is a non-linear operations based on standard morphological operations.We state the choice of the structuring element and compare with the classical edgede detection operators .The experimental results show the edge detection method of RS Images based on mathematical morphology of gray gradient better than the traditional operators not only the geometrical properties but also the effects of the structuring element and approve the feasibility of this method.[著者文摘]

一种基于形态学的全方位图像边缘检测算法

雷雁[1] 傅德胜[2]

针对图像边缘复杂、易受噪声影响的特点，提出了一种基于形态学的全方位图像边缘检测算法，利用全方位的结构元与多结构元的相结合提取图像的多样的边缘特征，采用多尺度的方法加权合成处理得到最后的边缘图像。实验表明，该方法能检测出更多类型的边缘，同时又能有效的抑制噪音。[著者文摘]

基于多尺度形态学的红外图像边缘检测方法

Edge detection of infrared image based on multi-scale morphology

刘曙 罗予频 杨士元

提出了一种基于数学形态学算子的多尺度边缘检测方法。首先选取几个有代表性的结构元素对灰度图像进行边缘检测得到边缘图像。改变结构元素的尺寸大小可得到多尺度下的边缘图像，根据局部边缘生存期的长短将不同尺度下的边缘图像合成。对噪声大、边缘较模糊的红外图像进行了边缘检测与比较，实验表明该算法抗噪能力强，能得到更精细准确的边缘。[著者文摘]

An edge detection algorithm based on multi-scale morphology was presented. Firstly, image edge was detected by using several typical structure elements. Then, edges in different scale were combined according to the life of local feature, which were detected by changing the size of structure elements. Compared with several conventional edge detectors, the proposed algorithm has better noise immunity and performance on edge detection of infrared image with large noise and blurry edge.[著者文摘]

边缘检测的形态学算法与传统算法比较

The Comparison Between Morphology Algorithm and Traditional Algorithms for Edge Detection

焦斌亮 胡永刚

由于图像的边缘通常含有大量重要信息，因此，边缘检测成为图像处理的一个重要环节，其检测算法也获得了广泛的研究，已经形成了Roberts、Laplacian、Canny等多种算法。但这些传统算法在边缘检测精度和抗噪声性能方面还存在一定的问题。文章运用数学形态学边缘检测算法的结构元素变换，对无噪声图像检测出多幅边缘图；对噪声图像采用改进的开启运算，先用3×3的结构元素进行腐蚀，后用5×5的结构元素进行膨胀，用边缘检测算子foB-f进行检测，并与传统算法和不变结构元素的形态学开启运算的结果进行了比较。实验结果表明，灵活多变的数学形态学边缘检测算法在检测精度和抗噪声性能上都优于传统算法。[著者文摘]

The edge of a picture generally implies much useful information so the edge detection is important in image processing and the detection algorithm is studied extensively. There have been various algorithms such as Roberts, Laplacian, Canny and so on. But the traditional algorithms have drawbacks in the detection accuracy and the anti -noise performance. In this paper, the mathematical morphology detection algorithm with the construction element transformation is used to detect a noiseless picture. The improved open calculation, that is using 3 x 3 construction element to decay, then using 5 x 5 constructionelement to inflate and finally using operator foB -f to detect, is used to the noise picture. The morphology algorithm with construction element transformation is compared with the traditional algorithms and the constant construction element morphology algorithm. The results show that the flexible mathematicalmorphology edge detection algorithm is better than the traditional algorithms in both detection accuracy and anti - noise performance.[著者文摘]

基于小波增强的改进多尺度形态梯度边缘检测算法

Edge Detection Based on Image Enhancement of Wavelet Transform and Modified Multi-scale Morphological Gradient

费浦生 王文波

在形态学梯度边缘检测算子的基础上，综合多结构元和多尺度算法的特性，提出了一种基于小波增强的多结构元、多尺度边缘检测方法，用不同取向的结构元素对图像进行多尺度检测，并综合各尺度下的边缘，得到了噪声存在下的理想边缘。实验表明，本文方法边缘定位准确、轮廓清晰，保留了更多的图像细节，具有较强的抗噪能力。[著者文摘]

The multi-structure elements and multi-scale edge detection method is proposed based on image enhanced of wavelet transform. Four elements are used to detect multi-directional edges of image at different scales, The more ideal image edges under the environment of existing noise are obtained by integrating the edge characteristics for various scale. During computation the computation is reduced by simplifying the different scales structuring elements. The experiments show that compared with traditional morphological edge detection algorithms, the method possesses better edge locating ability and keeps the more edge details, but also the ability of noise interference restrained is stronger.[著者文摘]

一种改进的形态学梯度边缘检测算法

An Improved Morphological Gradient Edge Detection Algorithm

张立东 毕笃彦

数学形态学边缘检测器能克服线性边缘检测器的一些缺点，但是存在宽边缘，导致边缘分辨率较低。文章依据宽边缘形成机理，提出了一种从相互垂直方向分割形态学梯度图像，提取截面曲线局部极大值的边缘检测算法；给出了算法实现的详细步骤。实验表明该算法能提高形态学梯度边缘检测器的边缘分辨能力，并且能增强形态学边缘检测器的抗噪性能。[著者文摘]

Morphological gradient is a nonlinear edge detector that can overcome the some drawbacks of the linear edge detector. Wide edges detected by morphological gradient cause the low edge resolution. According to the reasons why wide edges produce, an edge detection algorithm is presented that gradient image is segmented in two orthogonal orientations and local maximums are dived from the section curves, The algorithm＇s steps are presented in detail. The experimental results show the algorithm can improve the edge resolution and insensitivity to noise.[著者文摘]

基于形态多结构元和小波变换的边缘检测算法

An Edge Detection Algorithm of Noisy Image Based on Wavelet Transform and Multiple Structuring Elements Morphology

张建国[1] 孙琳[2]

提出了一种小波变换与多结构元形态学相结合的抗噪边缘检测方法。通过改进的小波边缘提取方法选择噪声图像的突变点，同时滤除部分噪声；针对图像中噪声和边缘形态的不同，建立了多个结构元素。采用多结构元形态检测算子对选取的突变点进行形态操作，在抑制噪声的同时，较好地提取了边缘。基于实验结果，指出对舍有不同类型噪声（如椒盐噪声、高斯噪声等）的图像，该方法都可以较好地抑制噪声，提取边缘，且效果优于经典的边缘检测算法。[著者文摘]

This paper puts forward an edge detection method based on wavelet transform and multi-structuring elements morphology, selects the coarse edge points and deleting part of noise by an improved edge detection method of wavelet transform, aiming at the morphology difference of noise and edge, constructs the multiple structuring elements, by using multiple structuring elements morphological operators detects the edge at the selected coarsc edge points, which detects the edge very well and restrain the noise also very well,and based on the experimental results, points out that for different kinds noisy images, such as salt and pepper noise and Gaussian noise and so on, the method can detect edge and restrain noise very well, and the effect of edge detection is better than classical edge detection.[著者文摘]