边界分割

算法上采用了平滑滤波技术，边界分割技术和交遇区方法设计Fisher线性分类器。

In the project we process the data with the methods of smooth filter , boundary division technique and Fisher linear sorting method .

结合区域分割与边界分割技术，提出了基于BP分割评价的多层次双阈值迭代分割算法和多层次自适应边缘检测算法。

In order to achieve multi-level segmentation , the thises proposed two new methods , one of which is the multi-level double value iteration segmentation algorithm based on BP evaluation and the other is multi-level adaptive edge detecting algorithm based on improved canny operator .

在基于边界分割方法中，用动态规划来寻找图像里的真边界。

In edge-based method , we use the dynamic programming to find the true boundary .

然后，基于目标轮廓提取和串行边界分割技术，解决了变背景下斑点状散布目标自动识别的难题。

Thus determines fleck discrete targets ' precision dimensions by feature extraction and serial borderline segmentation technologies .

本文提出一种基于格网的等值线跟踪，适用于任意边界分割的快速充填算法，实现充填的矢量化效果。

Based on contour tracing for grid data , a fast algorithm of color fill is proposed to cope with random boundaries surrounding data gaps and to realize the vector effect of color fill graph .

用实验系统完成了对基本图像的线、圆、椭圆、不规则元件和边界分割等进行测量，对存在的问题和产生的误差进行了理论分析。

The basic image elements of line , circle , ellipse , non-normal device and border segmentation are measured by our experimental system , and the existed problems and error derived from experiments are analyzed in theory .

提出散乱点云的特征智能识别理论，主要包括三步：恢复散乱点云的微分几何属性、点云分割及特征识别，其中恢复点云微分几何属性是边界分割和特征识别的基础。

A theory of intelligent feature-detection for unorganized point-cloud is provided . It includes three steps : recovery of differential geometry property for unorganized points , data segmentation and feature detection . The first step is the base of the other two steps .

通过激光雷达采集反映深度信息的程距数据，采用边探测方法，对探测交叉节点或极值进行边界分割，并采用几何模型匹配算法处理简单环境。

Gather the range data which can reflect the depth information through the laser radar . Adopt the border survey method , we can cut border through survey the cross-nodes or extremums , and adopt the geometry model matching algorithm to deal with the simple environment .

利用边界分割控制策略离散参数域边界，利用推进波前法对参数域进行剖分，然后利用逆映射生成曲面网格，以得到高品质的有限元网格。

Boundary division and control strategy dispersed the boundaries of parameter region . Mesh was generated on parameter region by advancing front technique and on 3-D surfaces by inverse mapping . With the help of the multiple mapping and mesh control strategy , high-quality mesh can be generated efficiently .

用边界条件分割法求解分层介质物体的稳定温度场

Use of boundary condition dissection in solving steady-state heat conduction problems of composite medium

该算法在无需预先设定阈值的情况下，可高速地获得单像素、连续轮廓边界的分割图像，并通过调节温度系数，实现图像由概略到细节的分割，因此避免了过分割现象。

Simultaneously , the segmentation from rough to detail can be realized by adjusting the temperature parameter to avoid the over-segmentation .

事实是，语言和方言并不能像地图上的边界一样分割的那么清楚。

It turns out that languages and dialects do not divide neatly , as if they were following the borders drawn on a map .

分层介质物体的稳定温度场，目前常用数值方法来求解.本文指出，对某类区域上的上述问题，可以用一种新的方法&边界条件分割法求出其近似解析解。

In this paper , a new method-Boundary Condition Dissection is introduced to obtain the solution to steady-state heat conduction problems of composite medium .

本文是一篇综述文章，主要介绍关于单色图像的分割方法：基于边界的分割方法、基于区域的分割方法、综合边界和区域信息的分割方法，并提供这些方法的一些实验结果。

This paper is a review . It mainly introduces monochrome images segmentation approaches including edge-based methods , region-based methods and integrating edge-based with region-based approaches , and offers the experiment results by utilizing the methods .

基于模拟退火的简化Snake弱边界医学图像分割

Simulated Annealing Based Simplified Snakes for Weak Edge Medical Image Segmentation

在以下各节中，将介绍如何通过修改跑步小人的边界框和分割游戏的空间，细化SnailBait的碰撞检测。

In the sections that follow , see how to refine Snail Bait 's collision detection by modifying the runner 's bounding box and partitioning the game 's space .

传统的基于可变模型的分割方法是一种只基于边界信息的分割方法，就充分利用图像信息的角度来说有其局限性。

Traditional deformable model based segmentation is a method merely based on edge information , which does not make full use of image information .

自然背景复杂的纹理特征和红外图像中的噪声影响，以及红外目标模糊的边缘，给红外目标的边界检测和分割带来一定的困难。

The effect of natural background and noise in infrared image , fuzzy edge of infrared object , make it difficult to segment and label artificial object in natural background .

本文主要利用levelset函数隐式地追踪图像的边界来实现图像分割。

In this paper , image segmentation was realized by level set function for tracking image boundary implicitly .

在分割算法中，我们选择了基于边界的活动轮廓分割算法。

The active contour is chosen to be the method for segmentation .

一种利用多参数进行实时语音边界检测与音节分割算法

A Real-time Border Detection and Syllable Segmentation of Voice Based on Multi-Parameter

启发式边界跟踪道路图象分割方法

Road image segmentation method based on heuristic edge tracing

首先从采集到的人眼图像中定位虹膜的内外边界，并对分割出的虹膜进行归一化处理和图像增强处理。

The normalization and image enhancement is used to process the iris position which was located in the eye images .

利用边界信息最后确定分割线来对字符进行形状分割。

Combined with the edge information , we can define how to segment the character images based on segmentation lines .

本文介绍了一些可用来提高性能的简单技术，比如细化边界框和空间分割。

This article has shown you some simple techniques that you can use to improve performance , such as refining bounding boxes and spatial partitioning .

在复杂背景情况下，采用固定的阈值边界模型进行肤色分割将导致较大的漏检或误检。

As a result , for images with complex backgrounds , a fixed decision boundary skin-color model may lead to high false rejection rate and false detection rate .

分析了多种图像分割的方法后，本文提出了一种新的阈值图像的图像分割的方法，该算法中将图像中的每一点都设定一个阈值，结合边界来对进行分割的。

It is proposed that a method in image segmentation base on threshold graph , whose algorithm set threshold on every pixel of the picture and then split together with the border .

针对边界中存在的分割噪声使用圆形形态算子对边界进行完整化，最终获得了完整的刀具磨损区图像，为实现通过刀具磨损区大小来评判刀具磨损程度的方法奠定基础。

Aiming at the edge noise of image , mathematical morphology theory is applied to integrate edge . Test results show that the segmentation algorithm is effective in identifying tool wear degree .

在对二值化图像扫描形成目标块的过程中，标记各个目标像素，记录目标的边界点，得出分割目标的面积、周长、质心坐标。

During scanning binary image to form object region , each object pixels will be labeled and object boundary points will be recorded , thus the area , circumference and centroid coordinate of the segmented object can be obtained .

在基于运动变化区域和边界特征的视频分割中，本文提出了一种通过估计相对噪声特征参数对差分图像中的相对噪声进行滤波的运动变化区域自动检测技术。

In the video segmentation process based on the motion-changed region and edge features , an automatic motion changed-region detection algorithm is proposed which detects motion-changed region through filtering relative noise based on the estimated relative noise 's parameters in difference image .