By adopting texture statistics for ray-space slice initial search direction was established and then multi-layer rectilinear direction search method was realized in inter-slice prediction .

在片间预测中，通过对光线空间片的 纹理 统计，确立初始的搜索方向，实现分层的直线方向搜索方法。

The statistic method of image analysis is used to evaluate the fabric wrinkling analyse the texture statistics properties .

利用计算机图像处理的 统计分析方法对 织物的抗皱恢复性能进行了系统地分析。

With the above pretreatment it adopts contour detection to check contour defects employs the algorithm of image subtraction method and gray correlation detection to detect the bamboo image texture defects and further uses the gray value statistics method to detect the precision of lamination defect .

在上述预处理的基础上，运用轮廓检测法检测轮廓缺陷，采用图像的差影法和灰度相关性算法检测竹片图像的 纹理缺陷，进一步采用灰度值 统计法对纹理缺陷进行精度检测。

A Texture Classification Method Based on Structure Statistics

基于结构 统计 的 纹理分类

For color images this paper compares the three types of skin texture detection algorithm : Gabor filtering gray co-occurrence matrix method and the simple gray level statistics .

针对肤色图片的特点，比较了三种皮肤 纹理检测算法：Gabor滤波法、灰度共生矩阵法和简单灰度 统计 法。

Texture segmentation is always the problem in the texture research that involves pattern recognition applied mathematics statistics neurophysiology neural networks and other fields .

而在 纹理分析研究技术中纹理分割一直都是研究的难点，它涉及神经网络、 统计学、模式识别、神经生理学、应用数学、生物制药等多个研究领域。

Furthermore actual physical sense of texture feature of above statistics methods is proved through a group of testing images .

定性地分析了这几种 统计方法中 各个特征的实际 纹理意义，并且利用一组测试图像验证每种 算法 纹理 特征的物理意义。

Texture Classification and Shape Statistics Variational Approach for Segmentation of Left Ventricle Tagged MR Images

结合 纹理与形状的 TaggedMR图像左心室分割算法

This paper systematically introduces kinds of texture feature extracting methods applied in B-scan liver images in recent years including the conventional methods based on statistics and models and other newly developed methods .

系统介绍了近年来应用于肝脏B超图像 纹理特征提取的各种方法，包括传统的 统计 法、模型法和其他新方法等。

Image texture analysis by statistics of centroid patterns

利用质心模式 统计进行图像 纹理分析

This thesis based on the Theory of Mathematical Morphology Designed an content-based image retrieval system by texture and shape at the same time Put forward a new algorithms of texture descriptor So-called the Statistics method of Crevice Pixel .

本文以数学形态学为理论基础，设计了一个基于纹理和形状特征的图像检索实验系统，同时还提出了一个新的 纹理描述算法，本文称之为空隙像素 统计法。

A defect inspection method for statistics texture image which uses texture difference statistics feature in wavelet domain is presented .

针对统计纹理图像，提出了一种小波差分 统计 纹理特征缺陷检测方法。

Texture defect inspection method using difference statistics feature in wavelet domain

基于小波差分 统计特征的 纹理缺陷检测方法

Analysis and Discrimination of Tongue Texture Characteristics by Difference Statistics

基于差分 统计 方法的舌象 纹理特征的分析与识别

Psychology research on texture perception and graphical study about texture synthesis show that high order statistics of feature are key clues for texture recognition .

纹理感知的心理学研究和计算机图形学的 纹理合成研究表明：特征的高阶 统计量是纹理辨识的关键因素。

The texture features such as direction and contrast of the image can be obtained from weighted projection statistics of primitive feature which are more matched with human vision .

然后通过对基元特征进行加权投影 统计，得到图像的方向性、对比度等 纹理特征，这些特征可以更好的适应人类视觉特性。

Texture detecting of fusion cloud image based on histogram statistics method

融合卫星云图的直方图 统计法 纹理检测