1) image texture
图像纹理
1.
The choice of the superior wavelet bases in the image texture identifies;
图像纹理识别中最优小波基的选择
2.
Develops a system that can analyzes MRI medical image texture feature,the functions of which include implementing image display,reading image information,selecting ROI,extracting five texture features and forming samples that is saved to the samples library,as well as classifying the samples using four different methods and statistical tests for the various features.
很多研究都已经证实当人体的组织发生病理变化时,图像纹理特征也会相应改变,如何从MRI图像中提取表征这种常规MRI无法观察到的微观结构改变的特征是本文研究的重点。
3.
Combing the energy,coarseness and structure property of the texture,an algorithm for image texture feature detection based on Gabor filter is proposed according to human vision characteristics.
结合纹理的能量特性、粗糙性、结构性等特点,根据人类视觉特性,提出了Gabor小波变换滤波器的图像纹理特征提取方法。
2) texture image
纹理图像
1.
Mapping based complex contourlet transform texture image retrieval system
基于映射的复轮廓波变换纹理图像检索系统
2.
Second generation contourlet transform based texture image retrieval system
第二代轮廓波纹理图像检索系统
3.
Research on texture image segmentation method
复杂纹理图像分割方法研究与实现
3) texture images
纹理图像
1.
Leather has typical texture and the texture images differ from common gray images in pixels space dist.
因为皮革具有典型的纹理特征,纹理图像其特殊的像素空间分布方式有别于普通的灰度图像,因此常用的灰度图像分类特征对纹理图像的分类不适用。
4) textured image
纹理图像
1.
In this paper an approach to object extraction in textured images is proposed based on a mask stochastic method in object edge extraction, and its aim is to detect the object hidden in texture.
提出了一种基于纹理图像的目标提取方法。
2.
In the field of textured image segmentation,some propose a two step textured image segmentation method by taking interacting parameter of neighbor pixel in Gauss Markov Random Field as features,taking Gauss Mixture Model as classifier.
针对以高斯马尔可夫随机场中的邻域像素互作用参数为特征、以高斯混合模型为分类器的二步纹理图像分割方法,提出一个两者相互结合的一步模型———高斯马尔可夫随机场混合模型,并给出其EM算法的迭代计算公式。
3.
The author proposes a textured image segmentation algorithm which is based on multiresolution wavelet and Gaussian mixture models.
提出了一个基于多分辨率小波采样和高斯混合模型的纹理图像分割方法。
5) fingerprint image preprocessing
指纹图像预处理
1.
An arithmetic of fingerprint image preprocessing is presented on the basis of available algorithms and Radon transforms.
为了增强指纹图像预处理的效果,在指纹图像预处理算法的基础上,文中提出了一种新的指纹图像预处理的算法。
2.
In this paper, fingerprint image preprocessing algorithms, fingerprint singular points and minutiae extraction algorithms and fingerprint classification and indexing algorithms are analyzed and discussed in detail.
本文在指纹图像预处理算法、指纹奇异点与细节点提取算法、指纹分类及检索算法等方面进行了较为深入的分析研究,取得了以下成果:1、在指纹图像预处理算法方面,一是提出采用指纹图像子块的频谱能量比与灰度对比度构成特征向量,利用线性支持向量机对这些特征向量进行分类,再运用二值图像形态学操作实现指纹图像分割;二是提出对指纹块方向图进行选择性平滑后,通过对投影信号进行谱分析估计纹线间距,再结合Gabor滤波实现指纹图像增强。
6) texture image segmentation
纹理图像分割
1.
Graph semi-supervised texture image segmentation combined with Nystrm
结合Nystrm逼近的图半监督纹理图像分割
2.
To verify the proposed algorithm,we apply it to texture image segmentation with satisfactory results.
为了将谱聚类算法应用于大规模聚类问题,该文提出一种两阶段纹理图像分割算法,采用改进的分水岭算法进行预分割,然后用特征值尺度化特征multiway谱聚类算法进行最终分割。
补充资料：高光谱分辨率遥感图像及图像光谱信息提取
高光谱分辨率遥感图像及图像光谱信息提取
高光谱分辨率遥感图像及图像光谱信息提取 郑兰芬供稿
说明：补充资料仅用于学习参考，请勿用于其它任何用途。
参考词条