特征

The process of the algorithm include: image enhancement, using self-adapting threshold value reduce redundance, using Hough transformation extract first feature line, according to the vertical projection of the horizontal gradient perform characters line, using the improving Hough transformation with angle constraints acquire the intersection of the two feature lines, according the characters of geometry position to judge the fault.

算法流程包括图像增强，自适应阈值变换滤除无关特征，应用Hough变换提取主特征线条，依据线型特征图像水平梯度沿垂直方向的积分投影定位主特征线，基于极角约束Hough变换推出两条主特征线交点，最后根据安全链和支架的几何形态特征判读故障。

Feature of principal lines spatial distribution: detect the principal lines through edge detecting technology, and then divide the image of palmprint into blocks with same dimension, compute the mean and variance as feature; Feature of palmprint direction: divide the image into sub-images; compute the max angle of projection and coordinate of each sub-image, which stand for the direction and location of the line on the palm; Feature of moment invariants: compute the moment invariants of each sub-image and the whole image as feature.

掌纹主线空间分布特征：利用边缘检测技术检测出掌纹的主线，将图像分割成相同大小互不重叠的子图，提取每一个子图的均值和方差作为特征；掌纹线方向特征：将图像分成不重叠的子图，利用Radon变换求出每一个子图的最大投影角度和坐标，也就是子图内掌纹线的方向和位置，构造特征向量；掌纹不变矩特征：提取图像整体和分割后的子图的不变矩作为特征。

It solves the problem that the unitary contour presentation can not correctly extract face contour in a face image which suffers from scale, rotation etc. The definition of the internal and external energy function is provided. At the same time, the global matching algorithm and local matching algorithm is given. The experiment shows that this presentation and the accompanying matching algorithm can be used to extract the face contour very well. So the image segmentation can be implemented by using it.②By analyzing the recognition principle of PCA method, we can conclude that the face images coming from different surrounding consist of different face image space. This is the essential reason that makes the generality of PCA method worse. Also, we give a measurement means to measure the distance from different face image space, so we can analyze face image space more conveniently.③We also construct various scale models and rotation pose models to detect the scale and rotating angle of face image to be recognized. The experiment results show that the detecting precision is very high. So it is good for face image feature extraction and face image representation.④Similarly, we construct local feature models of face image and utilize them to detect the local feature of face image. At the same time, we put forward a novel face image local feature detection algorithm, locating step by step. The experiment results show that this method can accurately detect the location of local face feature in a image.⑤A novel face image presentation model, dual attribute graph , is put forward. Firstly, it utilizes attribute graph to present the face image, then exact the local principal component coefficient and Gabor transform coefficient of thc pixels which corresponds to the nodes of the graph as the attribute of the nodes. This representation fully makes use of the statistical characteristic of the local face feature and utilizes Gabor transform to present the topographical structure of face image. So DAG has more general property.⑥Based on the DAG presentation, we give a DAG matching function and matching algorithm. During the design of the function and algorithm, the noise factor, e. g., lighting, scale and rotation pose are considered and tried to be eliminated. So the algorithm can give more general property.⑦A general face image recognition system is implemented. The experiment show the system can get better recognition performance under the noise surrounding of lighting, scale and rotation pose.

本文在上述研究的基础上，取得了如下主要研究成果：①构造了一个通用的人脸轮廓模型表示，解决了由于人脸图象尺度、旋转等因素而使得仅用单一轮廓表示无法正确提取人脸轮廓的问题，并给出了模型内、外能函数的定义，同时给出了模型的全局与局部匹配算法，实验表明，使用这种表示形式以及匹配算法，能够较好地提取人脸图象的轮廓，可实际用于人脸图象的分割；②深入分析了PCA方法的识别机制，得出不同成象条件下的人脸图象构成不同的人脸图象空间的结论，同时指出这也是造成PCA方法通用性较差的本质原因，并给出了不同人脸空间距离的一种度量方法，使用该度量方法能够直观地对人脸图象空间进行分析；③构造了各种尺度模板、旋转姿势模板以用于探测待识人脸图象的尺度、旋转角度，实验结果表明，探测精确度很高，从而有利于人脸图象特征提取，以及图象的有效表示；④构造了人脸图象的各局部特征模板，用于人脸图象局部特征的探测；同时提出了一种新的人脸图象局部特征探测法---逐步求精定位法，实验结果表明，使用这种方法能够精确地得到人脸图象各局部特征的位置；⑤提出了一种新的人脸图象表示法---双属性图表示法；利用属性图来表示人脸图象，并提取图节点对应图象位置的局部主成分特征系数以及Gabor变换系数作为图节点的属性，这种表示方法充分利用了人脸图象的局部特征的统计特性，并且使用Gabor变换来反映人脸图象的拓扑结构，从而使得双属性图表示法具有较强的通用性；⑥在双属性图表示的基础上，给出双属性图匹配函数及匹配算法，在函数及算法设计过程中，考虑并解决了光照、尺度、旋转姿势变化等因素对人脸图象识别的影响，使得匹配算法具有较强的通用性；⑦设计并实现了一个通用的人脸图象识别系统，实验结果表明，该系统在图象光照、尺度、旋转姿势情况下，得到了较好的识别效果。

The methods of computing for similar coefficient were Discriminance of Minimal Difference of Parameters, Discriminance of Limen of Tree Compositive Character and Synthetic Weight Similarity of Parameters. The contribution of all parameters were considering as same for DMDP and DLTC, but it estimate s the similarity between parameters according to the limen for DLTC. DMDP was based on the principal component analysis for wood transverse section micrograph characters and computing the similar coefficient according to the contribution of every parameter.

其中最小差值差数判别法与树种综合特征阈值法是将每个特征参数对木材横切面显微图像特征的贡献率视为一致，只是树种综合特征阈值法是以阈值的大小来判断特征的相似性，而综合加权相似法是建立在对木材横切面显微图像特征参数的主成分分析的基础上，根据每个特征参数的贡献率大小计算相似系数。

Videlicet, this sequence represents the accountability of the 11 features in distinguishing insects on the level of species. According to the above results, some features varies not remarkably on all levels, such as Lobation, Shape-Parameter etc. This shows that such kind of features are nearly same in all species of insects, and can represent the feature suitable to distinguish all insects from other classes of animals. On the other hand, they are not suitable as distinguishable features of levels which lower than insect Class.

从结果可以看出，有些特征在各个分类阶元上差异均不是很显著，如叶状性、形状参数，说明此类特征在昆虫中具有较强的共性，可以代表整体昆虫的特征，而不适合于作昆虫纲下阶元的分类特征；有些特征在各分类阶元下的差异始终比较显著，如周长、面积等，说明这些特征适合在各分类阶元上作为昆虫的分类特征。

First, the algrithm classify the measurement characteristics as point, line and surface which can be classified to conicoid and free surface. Then, this algorithm establishes the parametric equation according to various features. After that this paper brings forward the characteristic parameters utilising least square method with several characteristic points. Finally high precision probe radius compensation is carried out according to the features.

该算法首先把测量特征分为点、线、面3种基本特征（其中面特征又分为二次曲面和自由曲面），然后建立各种特征的参数方程，利用测量得到的少量特征点，采用最小二乘法拟合得到被测特征的参数，最后根据被测特征参数进行高精度半径补偿。

All above laid a foundation for the research of polarimetric information processing and application. Then, target optimum polarization and polarimetric synthesis technique were studied. By constraining polarimetric states of transmitting and receiving antennas, co-polarized and cross-polarized signatures were obtained. Because the received wave was partially polarized, completely polarized, completely unpolarized, and total available power signatures were defined based on the power of the return wave.

接着，论文深入研究了目标最佳极化和极化合成技术，通过约束收发天线的极化状态可以得到共极化特征图和交叉极化特征图，由于雷达接收的电磁波通常是部分极化的，根据接收波的平均功率密度可以得到未极化特征图、完全极化特征图和匹配极化特征图，在极化特征图空间中搜索可以很容易地获得目标的最佳极化，这些目标最佳极化可以作为极化目标识别和分类的极化特征。

There are three main methods in face localization: localization according to face outline, localization according to complexion and localization according to templates constructed by some standard sample images. As to feature extraction, it can be divided into two parts because face features can be divided into geometrical features and algebraic features. While extracting geometrical features, the features of eyes, nose, mouth, eyebrows can be gained by some image processes: binary, sharpen, smooth, projection, calculating gradient and so on. In order to extract algebraic features, we can do some mathematical transformation for the digital images such as singular value decomposition, K-L transformation.

在人脸检测部分，目前存在的方法有利用人脸的几何轮廓进行检测、利用人脸的肤色信息进行检测、构造标准人脸模板进行匹配检测等等；在人脸特征提取部分，可以用一些图像处理的方法如投影、二值化、求梯度图像等提取人脸中各特征器官如眼睛、鼻子、嘴巴等的几何特征，另外也可以借助于数学变换，求取人脸图像的一些代数特征，如对图像进行奇异值分解，以奇异值代表图象的特征，或对图像进行K-L变换，以图像在构造的特征空间上的投影系数作为图像的特征等；在识别部分，可以通过距离度量或相似度来判断输入图像与样本图像的匹配程度，还可以通过神经网络方法进行人脸的识别。

The concept of form feature and form feature line in terms of describing the automobile form was introduced based on the 100 digital models of automobile.20 form feature lines was captured from the 100 digital models,and sorted into three classes: the main feature line,the transition feature line,and the subjoin feature line.

在构建100个汽车造型数字模型的基础上，引入特征的概念对汽车造型进行描述，提取了20条汽车造型特征线，将其分类为主特征线、过渡特征线和附加特征线，建立了基于特征和特征线的汽车造型描述模型。

A new scheme of target discrimination in SAR images, consisted of frames, models and algorithms, is proposed. Under such a scheme, a global frame, combining orderly the algorithm based on feature extraction and that based on knowledge, is then proposed. Moreover, in the method of target discrimination based on feature extraction, a "loose-coupling" model is given. The existing features are chosen and three new features about the contrast are given under the "loose-coupling". Meanwhile, an algorithm of feature selection based on Genetic Algorithm is also modified to solve the problem that the existing algorithm can not evaluate the goodness-of-features comprehensively. The weighted quadratic distance discriminator is designed to improve the performance of target discrimination. Finally, a method based on the knowledge of target groups to remove clutter false alarms is also given.

提出了一种目标鉴别的新方案，该方案包括目标鉴别的框架、模型以及算法；提出了基于特征选取鉴别和基于编队提取鉴别"序贯"连接相结合的目标鉴别框架；在基于特征选取进行目标鉴别的方法中，提出了目标鉴别的"松耦合"模型；提出了"松耦合"模型下目标鉴别的特征提取方法，包括已有特征的筛选和3个新的对比度特征的提出；改进了一种基于GA的特征选择方法，克服了已有方法对特征优劣评价不全面的问题；设计了加权二次距离鉴别器，提高了鉴别的性能；研究了基于目标编队知识进行进一步杂波虚警剔除的方法。

This is not an ordinary box, which is used as a background picture of the dialog box, very pretty.

详细说明：这可不是一个一般的对话框，它是用图片作为背景的对话框，非常好看。

Conceal me what I am,and be my aid for such disguise as haply shall become the form of my intent.

遮掩我的身份，帮助我，我的面具将成为我的目的。