角点检测

针对X射线机标定过程中的角点检测问题，该文设计了一套实用的处理方法。

This paper proposes a set of practical methods for corner detection used for X ray device calibration .

图像质量对Harris角点检测的影响研究

Research into the effects of image quality on Harris corner detection

基于SUSAN角点检测的动态目标识别

Moving object Recognition Based on the SUSAN Corner Detector

针对SUSAN算子阐值固定、对于X型角点检测能力弱和珑c算子对噪声敏感的不足提出了改进。

SUSAN operator Threshold for fixed X-type corner detection for weak and Long c operator less sensitive to noise is improved .

基于小波的多尺度SUSAN角点检测

SUSAN Multi-scale Corner Detection Based on Wavelet Transform

作者将一般图象配准中常用的角点检测技术运用到指纹识别中，提出基于SUSAN的指纹细节点提取新算法。

A new algorithm based on SUSAN in corner detection is proposed for fingerprint identification .

采用Hough变换和灰度变化的图像角点检测法

Corner Detecting Method Based on Hough Transform and Intensity Gradient

基于视频图像Harris角点检测的车辆测速

Measurement of Vehicle Speed Based on Harris Corner Detector

Harris角点检测在彩色图像中的应用

The Application of Harris Corner Detection in Color Imagine

基于直方图均衡化的Harris角点检测算法

Harris Corner Detection Algorithm Based on Image Histogram Equalization

基于尺度空间理论的Harris角点检测

Harris corner detection based on theory of scale-space

一种改进型的Harris角点检测算法

An Improved Detection Algorithm Based on Harris Corner

本文详细讨论了特征点的提取算法，主要采用了Susan角点检测算法。

This paper detailedly discusses the feature point extraction algorithm . It mainly uses the Susan-corner-detecting algorithm .

详细介绍了SUSAN算子在边缘检测和角点检测方面的应用。

The applications of SUSAN operator used in edge-detection and corner – detection are introduced in detail .

通过实验表明，Susan角点检测算法有良好的角点检测性能。

Through experiments , it shows that the Susan-corner-detection algorithm has a good performance of corner detection .

并根据识别出的V型坡口接头采用SUSAN角点检测算法对其进行特征参数提取。

And SUSAN corner detection algorithm is used to obtain its feature extraction in accordance with the identification of the V-joints .

基于小波变换多尺度Harris角点检测算法

A wavelet-based multi-scale Harris corner detection algorithm

本文在Harris角点检测的基础上，提出了一种新的角点检测方法。

Based on the Harris corner detector , a new corner detection method is proposed .

基于角点检测、Zernike矩和神经网络的人脸特征点提取方法

Extracting Face Features Using Corner Detection , Zernike Moments and Neural Network

首先改进Harris角点检测算法，有效提高所提取特征点的速度和精度。

Firstly , corners are extracted using improved Harris operator which improves the precision and speed .

在利用改进的SUSAN算子进行亚像素角点检测时，综合应用了索贝尔边缘算子、灰度平方重心法等方法。

Sobel operator and gray square centrobaric arithmetic were synthesized with the improved SUSAN operator in subpixel corner detection .

自适应的Harris棋盘格角点检测算法

Adaptive Harris X-corner detection algorithm

针对Harris算法定位精度不高的缺点，采用B样条对局部图像进行插值，对插值后的图像进行二次角点检测，得到角点的亚像素级坐标。

By using b-spline interpolation on local image of the image interpolation and the second corner detection the flaw of Harris ' algorithm can be solved .

本文主要研究工作如下：①深入研究了LoG（LaplacianofGaussian）角点检测方法，并针对该方法存在抗噪性能不足的问题，提出了一种LoG角点检测的改进方法。

The work in this thesis is as follows : ① This paper deeply analysis the LoG ( Laplacian of Gaussian ) corner detection method .

本文在图像增强技术条件下采用一种改进的多尺度Harris角点检测算法。

In this paper , image enhancement technologies to the use of an improved multi-scale Harris corner detection algorithm .

其中对Harris角点检测算法介绍最为详细，它是一种稳定的也较成熟的算法。

Harris corner detection algorithm , which describes the most detailed , it is astable and more mature algorithms .

角点检测在光流计算、运动估计、形状分析、相机标定和3D重建、视觉的定位和测量等方面都有重要的应用；

Corner detection have been used in optical flow computation , motion estimate , object tracking , shape analysis , camera calibration , 3D reconstruction , location and measure of machine vision .

对传统的特征点提取算法做了介绍，并且详细分析了Harris角点检测算法，以及特征点的匹配方法。

It gave a brief introduction to traditional feature point matching algorithms and provided a detailed analysis of Harris corner detection .

然后对由Harris角点检测得到的凸包计算前景和背景的观测似然概率。

Then we compute the observation likelihood of foreground and background by convex hull which is obtained by Harris point detection .

针对具体的算法（预处理、模板匹配、Hough变换、光流计算、角点检测），设计了其相应的GPU软件实现。

Realize some algorithm like preprocessing , sample match , Hough transform , optic flow computation , corner detect based on GPU .