本文提出了一种新的自动图象边缘检测方法。
In this paper, an automatic algorithm of edge detection is proposed.
图象边缘检测是计算机图象处理的最基本步骤之一。
Edge detection is one of the fundamental steps on the image processing.
介绍用神经网络实现图象边缘检测的实验研究结果。
A number of experiments were carried out to investigate the application of neural networks for edge detection.
以利普斯指数为特征参数对图象边缘类型进行了分析。
And regarding Lipshitz exponents as feature parameter, it analyses image edge types.
本文提出了一种利用广义似然比检测图象边缘的算法。
In this paper, We present an edge detection algorithm using generalized likelihood ratio.
本文提出了一种基于视觉特性和BTC的图象边缘检测算法。
An edge detection algorithm based on a visual characteristic and BTC is presented in this paper.
广义模糊算子法是一种用于图象边缘检测的全新而有效的方法。
Generalized Fuzzy Operator (GFO) is a new efficient algorithm for edgedetection of an image.
这种方法不仅能够有效地平滑噪声，还能够锐化模糊的图象边缘；
With this method, not only the noise can be smoothed efficiently, but also the blurred edge of an image be sharpened.
本文用数学形态学的理论，提出了一种新的灰度图象边缘检测算法。
This paper applies mathematical morphology theory to present a new algorithm for grey scale image edge detection.
提出了一种基于活动轮廓模型的胃窦B超序列图象边缘轮廓的提取与跟踪方法。
An extraction and tracking of the contour of gastric anthem in the ultrasound sequence images based on active contour models is presented in this paper.
同时，在不灵敏频带内(如图象边缘区)引入一定噪声以达到整个恢复图象的噪声平滑。
Meanwhile, some noises are added into frequency bands where it is less visible in order to achieve noise smooth of overall reconstructing image.
本文提出一个新的图象边缘检测方法，采用扁球面函数的特性，形成一种特殊的滤波器。
This paper suggests a new image edge detection method which is based on properties of prolate spheroidal function and performed with a special filter.
堆栈滤波器是一类能够有效滤除脉冲类噪声，同时能较好地保护图象边缘与细节的非线性滤波器。
As a kind of nonlinear filters, stack filters can suppress impulse noise effectively, and keep edges and details at the same time.
实验证明，通过选取适当的维数范围该方法能得到良好的边缘检测效果，并能突出主要的图象边缘细节信息。
Experiment results show that this method is effective for edge detection by selecting proper range of the dimension, giving the eminent and detailed edge of the original image.
本文提出了一种利用梯度的方向信息，对微分图象进行细化，并确定一测量函数进行边缘点连接，以实现图象边缘检测的方法。
An edge detecting method for digital image is proposed using direction information of the gradient to thin off the differential image and defining a measuring function to link the edge points.
第三部分分别使用小波分析和数学形态学进行了数字图象边缘检测，并将两者的检测结果进行了对比，得出了各自的适应条件和优劣之处。
The third part USES wavelet analysis and Mathematical Morphology to detect the image edge, and contrasts the two results, we have gotten respective apply condition and good or evil.
采用多边形拟合物体图象边缘轮廓线，即实现从图象到图形的转换的方法，与直接记录原图象数据相比可大大减少轮廓线上所需记录的边缘点的个数，即减少数据量。
In this paper, a method about contour extraction of regular targets in images is proposed, which is based on an improved rectangle fitting method and a polygon fitting method.
该方法同时利用图象中的灰度信息和边缘信息，从而克服了只依靠单一信息源的不足。
Since this algorithm utilizes both the intensity information and the edge information of an image, it compensates for the deficiency of depending only on a single information source.
实验结果表明，此方法能够较好地完成红外图象的边缘检测任务，从而为红外目标识别打下良好的基础。
The experimental results show this algorithm can fulfill the task of edge detection of infrared image nicely, which founded a good basis for registering infrared targets.
本文给出一种基于子波变换的图象多尺度边缘提取方法。
In this paper, an image multiscale edges extraction algorithm based on wavelet is presented.
通过数模转换、彩色编码、边缘锐化、透视显示、多元图象迭合等处理，获得常规物探数据处理方法难于获得的某些地球物理信息。
Some new geo-physical informations can be acquired by such as the digital analog conversion, color code, edge sharpening, perspective display and multivariableimage overlapping.
本文提出了一种噪声图象快速边缘提取和分割算法。
An algorithm of fast edge extraction and segmentation in noisy image is described in this paper.
本文介绍了被强噪声干扰的图象的边缘提取问题。
This paper deals with the edge detection for the low SNR image.
讨论了图象的模糊边缘检测问题。
对不同压缩比的压缩结果进行了分析，比较了原始图象和解压图象的边缘信息。
Analyses compression results with different compression ratios, and compares the original images with the marginal information of decoded images.
景物边缘信息是进行图象分析和识别的重要属性，如何有效地从噪声图象中提取边缘是这些领域中的难点。
Edge is an important attribute for image analysis and recognition, but it is difficult to effectively extract edge from noisy image in the domain.
该方法既保留了图象的边缘，避免了以往图象分类中出现的边缘模糊问题，又有效地对图象进行了区域划分。
This method not only preserves the edge of the image, avoids the problem of edge blurring in image classification, but also is effective in region division.
本文阐述了松弛法算法及其在图象匹配、边缘抽取及遥感图象分类等方面的应用。
In this paper the relaxation algorithms and their applications in image matching, edge extraction and remote sensing imagery classification are described.
从基于象素的SAR图象分类和基于邻域的SAR图象分类特点出发，提出了一种基于边缘检测的SAR图象分类融合方法。
From the characteristic of SAR image classifications based on pixel level and region level, this paper provides a fusion method for SAR image classifications based on edge-detection.
噪声图象的快速边缘提取和分割是实时图象处理中的重要问题。
Fast edge extraction and segmentation in noisy image is a difficult problem in real-time image processing.
应用推荐