形状特征

弯曲级进模CAD／CAM系统中复杂弯曲件的形状特征模型

The Form Feature Model for Complicated Bend Parts in a Progressive Dies CAD / CAM System

本文以箱体类零件为例，对CAD／CAM集成技术进行了深入的研究，提出了形状特征关系图、基于投标的自治工艺规化方法等一些新概念，并对其进行了深入的论述。

In this dissertation , taking box parts for example , integrated CAD / CAM technology is studied and discussed . Some new ideas of form feature relationship diagram and bidding based autonomous process planning method etc are presented and discussed .

形状特征量&相对平均半径误差Δr。

Picking up the average radius error as the shape feature .

机械零件CAD图形的形状特征拼合法设计

Design of CAD Drawing for Mechanical Parts Using Shape Feature Method

三种检索技术在提取形状特征之前，需要对3D模型进行预处理。

Before extracting feature from 3D model , we need to do some pro-processing .

基于CAD系统的零件形状特征识别

Part Shape Feature Recognition Based on Auto CAD

本文第四章针对微重力蜡烛火焰的形状特征和温度特征开展了研究工作。用Simple算法对微重力蜡烛火焰进行了数值模拟，建立了数学模型。

In the forth chapter the paper investigates the features of the candle flame and temperature in microgravity and establishes candle flame mathematics model in Simple method .

Hough变换作为目标形状特征提取的有效方法得到了广泛的应用。

Hough transform as an effective method of shape feature extraction is widely used .

实现了一种基于FFT的多分辨率形状特征匹配算法，适用于多传感器异质图像的配准。

A multi-sensor image registration algorithm based on multi-resolution shape matching is proposed to align two heterogeneous spatial images .

提出了一种保持曲面形状特征（trimmingcurves）不变的曲面放缩新方法。

A new method to scale a surface while holding the shape of specific features ( trimming curves ) unchanged is presented .

重点讨论了基于形状特征的Zernike矩的描述方法，并对其不变性进行了分析。

The description of the Zernike moments is analyzed based on its invariance .

图像挖掘中基于Zernike矩的形状特征描述与评价

Image Shape Feature Description and Evaluation Measure Based on Zernike Moment in Image Mining

基于国际标准STEP，建立了管理信息、形状特征信息、精度信息、技术信息等零件信息模型；

Based on the international STEP standard , it has built the information model of machine part , including management information , shape feature information , precision information , technology information and so on .

利用改进的Hough变换检测目标形状特征，解决目标区域出现阴影及目标被部分遮挡对识别的影响。

Shape features of certain object with shadow on it or visualizing partly are detected by improved Hough transform .

研究用感知器和三层BP神经网络识别二维零件图的形状特征信息。

The paper gives a new approach to solve the problem of features recognition and extraction from 2D part drawing by means of perceptron and three layers BP neural network .

零件的对称性等形状特征是可装配性设计（DFA）中评价其可装配性好坏的重要指标。

Shape feature is an important factor when evaluating the assemblability of a part in DFA .

在分析阿拉伯数字以及大写英文字母的形状特征后，提出了一种适于现场可编程门阵列（FPGA）实现的图像实时识别算法。

A real-time recognization algorithm of Arabic numerals and English letters based on field-programmable gate array ( FPGA ) was proposed after analyzing the features of the numerals and letters .

而形状特征的提取则是采用非常经典的Canny算子与Otsu阈值分割法相结合的方法进行图像分割，同时，提取七个不变矩来描述图像的形状特征。

The images are divided image by combining Canny operator and Otsu threshold method to get seven rectangular-shape features .

针对具体芯片图像的形状特征，提出了基于改进Hough变换的几何配准算法。

According to the shape of the specific chip image , a new geometric image registration algorithm based on improved Hough transform is presented .

基于形状特征k-d树的多维时间序列相似搜索

Similarity Search Based on Shape k-d Tree for Multidimensional Time Sequences

在分析细胞边缘形状特征基础上，用改进的Hough变换实现了细胞边缘的直线拟合。

Based on the analysis on the shape character of the cell edge , the paper realizes cell edge fitting with straight line by improved Hough transform .

然后用共轭梯度算法改进BP神经网络，基于该网络与纹理特征计算肝脏纤维化的程度，并利用形状特征计算肝左叶钝化的程度；

Then , the degree of liver fibrosis is calculated according to its texture and the improved BP neural network by conjugate gradient algorithm , and the passivation of left liver leaf is calculated according to its shape characteristics .

利用GIS工具，基于1∶50万海南岛植被图，研究了海南岛植被斑块的大小和形状特征。

With the aid of the GIS tool ARC / INFO , based on the Hainan vegetation map at the scale of 1 ∶ 500 000 , the characteristics of the patch size and shape in Hainan vegetation landscape were analyzed .

本文对行人的特征进行分析，利用形状特征，Haar特征和根据其改进三角特征进行行人识别。

This paper analyzes the characteristics of pedestrians using the shape features , Haar features and characteristics in accordance with its improved triangular pedestrian recognition .

其次，本文研究了区域形状特征提取及基于PCA的特征选择方法，通过对区域特征进行优化选择，构造准确描述目标特性且维数较低的特征。

Secondly , the method of region feature extraction and optimal feature selection are studied based on PCA , and the effective features are constructed for the target by the analysis of the PCA .

通过一系列预处理，对分割后的图像进行特征抽取，抽取的特征包括：基于HSV颜色空间下的颜色直方图特征和基于梯度统计的形状特征。

Then it presents the method of image feature extraction , the extraction of the features include : HSV color space based on color histogram and the gradient-based shape feature .

在利用数学形态学方法提取目标对象并调整了区域像素的灰度值的基础上，以图像的Hu不变矩作为形状特征，构造检索框架，并进行图像检索。

On the base of detecting targets and adjusting pixel gray value , use the invariant moment of image for the shape characteristic and construct the retrieval frame , then realize image retrieval . 3 .

针对HSV颜色空间的H、S和V三个独立灰度分量，设计了状态矩阵来描述它们各自的形状特征；

According to H - , S - , and V - component of an image , state matrixes are designed on the base of gray change of the pixels in the image block to describe their shape feature .

浅层知识库是一个标准的模糊BP神经网络，知识表示为内部隐式，由来自缺陷图像形状特征与缺陷图像类别关系，通过学习即可获得网络有关的参数如权矩阵和阈值向量。

Shallow knowledge base is a standard fuzzy BP neural network , knowledge that is implicit within , from the shape of image defects and deficiencies image category , can be obtained through the learning network-related parameters such as the right matrix and vector threshold .

在预处理方面，提出了形态学高帽-低帽变换和一维最大类间方差相结合的方法滤除噪声，增强图像细节；用SOBEL边缘检测提取形状特征。

During preprocessing , a combination of high caps – low caps and OTSU is proposed to denoise and enhance the details ; SOBEL is used to extract the edge .