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.
其后，详细讨论了常用的一些医学图象配准方法，如基于标志点配准法、基于特征配准法和互信息法等。
Then we discuss some image registration methods which are frequently used, such as registration based on landmark, feature-based method and mutual information method, etc.
本文设计了一种基于区域划分的分形图象压缩方法。
In this paper, a fractal image compression method based on region partition is devised.
文章讨论了计算机图形学的和基于图象的建模方法，在此基础上，分析了图形-图象混合全景建模方法。
This paper, on the basis of discussing, the computer graphics modeling methods and image-based modeling methods analyze the figure-image hybrid scene modeling method.
基于人的视觉特性提出了一种图象质量的感知测量方法。
A image quality measure scheme based on the Human Visual System Characteristics was proposed.
分析了传统的图象检索方法的困难，比较了基于内容的图象检索系统所具有的优点、系统结构及一般的处理方法。
We analyzed the difficulties of traditional method of retrieval and introduced the highlights of content based image retrieval systems, its structure modules and general processing methods.
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.
本文提出了一种基于模糊-神经网络混合系统(FNNHS)的图象分割方法。
This paper presents an image segmentation approach which is based on fuzzy-neural-network hybrid system (FNNHS).
这部分中，本文提出了基于密码学算法的图象置乱方法和基于混沌序列的图象置乱方法，并把电视信号加密方法应用到数字图象置乱中去。
In this part, the scrambling methods based on cryptography and chaos sequences are presented, and the encryption methods used in the TV are applied to the digital image scrambling.
传统的基于颜色直方图特征的图象检索方法简单且易于实现，但其直方图求交运算量过大，而且丢失了颜色的空间分布信息。
It is easy to perform for traditional image retrieval based on color histogram, however, its calculation in color histogram intersection is too large and the space distribution information is lost.
用基于图象的视觉伺服方法来预测特征点在图象平面的运动轨迹。
Trajectories of feature points on image plane were predicted by image-based visual servo method.
本文基于马尔可夫随机场，提出了改进的遗传图象恢复方法。
Based on Markov random field, an improved GA image restoration method is presented.
现有的目标表示方法往往是基于目标的图象特性和几何特性的。
The current object representation methods are usually based on the image attributes and the geometric attributes of the objects.
本文提出一种基于光谱形状描述的多门限的二进制编码分类方法，并给出了图象实验的结果。
In this paper, a classification algorithm based on multi-threshold binary encoding for Description of Spectral Shape is introduced, and result of image experimentation is present.
本文提出了一种基于特征元素的图象分类方法。
In this paper a novel approach for image classification based on feature element is proposed.
提出了一种新型的火灾探测方法：基于BP神经网络的火灾图象探测方法。
A new fire detection method, BP networks based image fire detection method, is presented in this paper.
实验结果表明这种基于图象内容的检索方法，较方便和准确地达到了图象检索之目的。
The results indicate that the Content-based image retrieval method offers distinct advantages over some other image retrieval methods.
本文通过分析基因芯片的图象特征，提出了基于变形模板技术的基因芯片杂交样点自动识别方法。
In this paper, based on the recognized microarray image features, an automatic spot identification method using the deformable template technique is proposed.
本文中作者提出了一种新的基于鲁棒统计的快速线搜索方法，可以用于图象帧间主运动估计，能够提高算法速度。
A new rapid line search method based on robust statistics is presented in this paper, which could be used in global motion estimation between consecutive video frames for speeding up objective.
作者提出了基于图象匹配的显微图象快速拼接的新方法。
A new method for microscopic image Mosaic with computer image registration technique is introduced.
在这种检索方法中，基于光照强度对图象灰度的影响，在检索中对于图象的灰度强度的处理，这个因素是必不可少的。
In this method, some reasons on grey will influence the result. So in this process, we must consider the grey of image.
提出了基于数学形态学理论来提取图象中的骨架并由骨架重建图象的方法。
In this paper, a method for extract and reconstruction image skeleton based on mathematical morphology is presented.
构建了一种基于不等距的可变性插值算法生成控制点网格的图象变形方法。
An image warping method is implemented, which generates control point grid by uneven distance interpolation.
给出了一种复杂条件下基于视频图象的实现船舶目标自动检测的图象预处理方法，其成功运行于长江三峡临时船闸的船舶检测系统中。
This paper introduces the image preprocess methods for ship detection method under complex conditions. which has been successfully running in the temporary ship lock of Three Gorges.
改进并提出了基于频域维纳滤波器方法的空域图象模糊复原算法。
An improved spatial domain image deblurring algorithm is proposed based on wiener filter and deconvolution.
本文提出的彩色图象压缩方法基于BTC(块截断编码)和PCA(主成分分析)的有效结合。
A method is presented here for color image compression which is based on efficient combination of Block Truncation coding (BTC) and Principal Component Analysis (PCA).
文章提出一种基于高阶累积量的序列图象运动目标检测方法。
This paper presents a new method for the detection of moving targets from image sequence based on high-er-order cumulants.
通过该系统，借助排序的评价方法，对本文的基于纹理特征的图象检索算法进行了评价。
By using a sorting assessment method, this paper assesses and compares the algorithms, the CBIR system proves to run well with a large image library.
基于传统立体图象匹配技术，提出了一种新的使用遗传算法的特征匹配方法。
Based on the traditional processing technology in stereo image matching, this algorithm is devised to be suitable for stereo image matching.
基于传统立体图象匹配技术，提出了一种新的使用遗传算法的特征匹配方法。
Based on the traditional processing technology in stereo image matching, this algorithm is devised to be suitable for stereo image matching.
应用推荐