二维图像

基于LBP的二维图像纹理合成技术

2D Image Texture Synthesis Techniques Based on LBP

该算法的实现，可以应用于非线性分类，神经网络分类学习（包括BP，RBF），以及二维图像散乱点的填充。

The quantity of convex hull is as less as possible . This algorithm can be applied to non-linear classification , neural classification algorithm ( including BP and RBF ) and 2D image filling for sample points .

结果用该方法实现了头部CT二维图像的三维体素成像。

Results The three volume rendering of CT two-dimensional images of head has been realized .

利用MATLAB实现二维图像傅立叶变换算法

Algorithm of Fourier-transform in 2-dimension image reconstruction with MATLAB

二维图像Fourier全息谱编码显示研究

Research on Fourier Holo-spectrum Encoding Display of Two-dimensional Image

面阵CCD采集双光栅干涉产生的莫尔条纹二维图像，进行扭转角测量。

Area array CCD grabbed moir é fringe image generated by two gratings interference to measure tortion angle .

基于二维图像矩阵的ICA人脸识别

Independent component analysis for face recognition based on two dimension image matrix

CCD图像跟踪系统广泛应用于图像制导、光电观测等领域，其利用目标的二维图像信息，实现对目标的跟踪，具有跟踪精度高、隐蔽性好、抗干扰能力强等特点。

It is widely used in accurate guidance technology and photoelectric measure field that Array CCD detector image tracking system .

结合线阵CCD扫描二维图像工作原理，分析了玻璃厚度检测图像特点。

Associates with the working principles of scanning two-dimensional image using linear array CCD , characteristics of glass thickness image are analyzed .

设计了一种改进的配准算法，实现基于三维CT血管丛投影所得二维图像与DSA图像的二维配准算法。

An improved registration algorithms were designed , the registration algorithm with DSA image and projection images of three-dimensional CT vessels were realized .

Fourier相位和幅度是二维图像处理中的重要特征，应用于图像压缩编码、信号重构。

Fourier phase and magnitude are two important features of two dimensional image , which have been used for image coding , signal reconstruction .

X树是子孙节点全为零的分级四叉树，用以表示二维图像中的一组零小波系数。

An X-tree is a hierarchical quadtree whose all descendants are insignificant , and it is used to denote 2-D clustered insignificant wavelet coefficients of an image .

鉴于此，本文利用图像处理和计算机辅助设计技术，将股骨的螺旋CT二维图像进行三维重建研究。

Accordingly , on the basis of image processing technique and computer aided design technique , three dimensional ( 3D ) digital model of femur was reconstructed from spiral CT data .

根据线阵CCD对二维图像进行扫描检测的特点，提出一种基于数字同步技术的轴类零件尺寸检测方法。

A method for shaft part size detection based on digital synchronous technique is proposed according to the characteristics of scanning 2-D image with linear CCD .

提出了一种提高THzCT二维图像分辨率的处理算法，该算法结合THzCT成像系统的特点，采用维纳滤波去除噪声。

Introduce a high resolution algorithm for THz two-dimensional CT , which takes advantage of Wiener filtering and fits the imaging system of THz CT .

最后，在MATLAB环境下，完成了基于超空泡二维图像灰度梯度的SFS三维重构算法。

At last , it completes the SFS algorithm for three-dimensional reconstruction on the grayscale gradient image of supercavitation in the environment of MATLAB .

目前在中等规模的掌纹库上的等误率（EqualErrorRate）已经降到0.1%以下，但是想进一步提高识别率，单凭二维图像难度很大。

At present , the Equal Error Rate ( EER ) of 2D palmprint recognition on a medium size palmprint database can reach 0.1 % or less . It is hard to improve the accuracy by just using 2D images .

方法观察完整时相，分析初始强化形式及与二维图像、CDFI的关系。

Methods The whole manifestation phases were observed to analyze the early enhancement forms and the relationship of the images with B-mode image and CDFI .

传统的OCT系统通常采用点扫描方式获取二维图像，其速度较慢，限制了系统的实时探测。

The traditional OCT system produces a two dimensional image through point scanning whose scanning speed is slow , and it limits the real time measurement of the system .

匹配过程是在二维图像空间的随机寻优，提出优势遗传的AGA，用匹配距离作为适应度函数，并自适应改变交叉变异概率进行匹配寻优，快速准确求出全局最优匹配点。

Adaptive genetic algorithm based on superiority inheritance is presented , which regards match-distance as fitness function , and varies the probabilities of crossover self-adaptively .

研究了一种线性降维算法：近邻保持嵌入（NPE），在二维图像矩阵上的扩展及其图像识别应用。

Fourthly , we investigate a linear dimensionality reduction method-neighbourhood preserving embedding ( NPE ) and its extension on two dimensional image .

目的：通过比较螺旋CT二维图像（薄层横断面与多平面重建MPR）与三维图像（SSD）诊断颌面骨骨折的准确性，探讨三维图像的临床应用价值。

Objective : To compare the diagnostic accuracy of 3D ( SSD ) spiral CT images with 2 D ( axial and MPR ) images in facial fracture and to assess the clinical values of three dimensional images .

其判读系统接收CCD视频信号，经自动或半自动判读进行二维图像叠加及三维数据处理，得出10密位圈内的弹数，完成实弹射击成绩评定。

The evaluation system accepted CCD video frequency signal and read the count of the passing points in the 10-mill circle by automatism or half-automatism judgment to carry out 2-dimension image addition and 3-dimension data disposal , accordingly accomplish the evaluation of the firing results .

论文首先介绍了CBS重建技术的基本原理以及图像重建时的离散化计算公式，然后对CBS二维图像重建的算法进行了优化设计，分析了算法的性能。

The paper first includes the basic theory of CBS technology and discusses discrete computation formula about image reconstruction , then the optimal algorithm is designed for CBS 2D image construction and some performance are analyzed .

全方位M型技术（anatomicM-mode）则是一条或多条独立取样线可以在二维图像上任意旋转取样并以M型曲线的形式显示取样部位运动情况的新技术。

Anatomic M-mode is a technique through which one or multiple independent cursors can be placed and rotated freely in the two dimentional images and the motion of the corresponding ventricular wall can be revealed in M-mode curve .

取其数据图像中有关下颌骨的二维图像，提取轮廓线，应用Amira软件重建下颌骨。

The 2-D imaging data of mandible were obtained from this virtual human , and the virtual mandible was reconstructed using Amira software .

目前，基于电场敏感原理的ECT二维图像重建只能反映某一时刻管截面的介质分布情况，不能反映两相流流型的变化趋势，因此在功能使用上受到诸多限制。

Currently , 2D image reconstruction based on electric field sensitivity theory could only reflect the material distributions in one sectional plane in some special time , but incapable of reflecting the flow pattern change details . The function is very limited .

为建立二维图像信息与三维空间信息间的对应关系，通过对现有摄像机标定方法的基本原理和特点的分析比较，选用两步标定方法完成了AGV视觉导航系统的标定。

In order to build up the corresponding relationship between 2D image information and 3D space of AGV surroundings , the basic principle and characteristics of camera calibration were analyzed and compared , the two-step calibration method was selected to calibrate AGV vision system . 3 .

利用真实世界中车辆在二维图像平面中的透视特征，提出了基于二值有序变换（BROT）的障碍物检测新方法。

With the help of perspective properties , a new algorithm for obstacle detection in image plane is given by using binary rank order transform .

研究结果用于论文以后的试验、视觉模型的参数标定和数据重构等研究内容。第二部分研究了SLM立体视觉的建模型问题，视觉模型描述了二维图像空间与三维物空间的映射关系。

Results will server the need of test , parameter calibration and data reconstruction . Second , the modeling problem of micro stereovision with SLM is discussed , and a vision model that describes the projection between 2D image space and 3D object space is derived .