基于纹理谱的纹理分割方法

纹理分析是图象处理中的一个重要领域。本文提出一种基于纹理谱特征分割纹理图象的方法。它首次将纹理谱特征与区域生长算法结合起来，从而实现了无监督的纹理分割。纹理谱特征具有对方向性敏感等优点，基于纹理谱的纹理图象分割取得了良好效果。     

空间灰度相关图象纹理分割方法

本文给出了图象纹理分割的空间灰度相关法(SGLDM)中四个描述性强的纹理特征。定义了纹理特征矢量。在此定义基础上,给出了一种新的图象纹理分割方法。最后以四幅分割难度较大的纹理图象实验,说明利用四种纹理特征的方法可以有效地对纹理子图案非随机旋转的图象进行纹理分割。     

基于Gabor多通道滤波和Hopfield神经网络的纹理图象分割

文章针对纹理图象的特点,提出了一种基于Gabor多通道滤波和Hopfield神经网络的纹理图象的分割算法。首先构造一组Gabor滤波器（2－D）提取纹理图象多分辨率和多方向性的空域和频域特征。为了使纹理特征更加明显,在此基础上对滤波图象进行非线性变换,最后利用Hopfield神经网络通过松弛迭代算法实现纹理图象的快速分割,取得了良好的分割效果。     

基于小波生成特征符号随机场的纹理匹配与分类

提出了一种用小波生成特征符号随机场的纹理图象分类方法。它通过一定尺度上的小波图象分解,由在最大尺度上分解生成的４个子图来生成原始图象的特征符号随机场,在此基础上产生共生矩阵,进而获取原始图象的纹理特征和向量。然后,用两个特征向量的距离作为判别标准,对纹理图象进行快速分类。     

基于神经网络的纹理图象生成

提出了一种利用多层前馈神经网络生成纹理图象的新方法 .利用该方法可方便地生成图案丰富的纹理图象集 ,并且该纹理图象集中的任何一幅图象均唯一地对应一组神经网络的权值和阈值 ,因此不仅便于图象保存 ,还大大地节省了图象存储空间 .     

基于方向性的多通道纹理图象分析及重构

纹理的各向异性特征（方向性）对于纹理分析有着重要意义。该特征的分析和描述，对纹理表征和图形化建模提供了重要的思路，在对纹理各向异性特征分析的基础上，提出了一种新的纹理图形化建模方法，基于各向同性和各向异性分离的思想，分别从频域和空域研究了纹理图象的方向性及非方向性特征。导出了确定纹理主控方向的有效计算方法，和残余图象的随机场模型逼近，并将分析所得的参数用于纹理的综合，实验结果和性能分析与比较皆证实了该方法的有效性和灵活性，表明能量多通道分析对于方向性纹理的表征和重构是一种行之有效的方法。     

一种新的结合纹理特征的SVM图象分割方法

本文提出了一种新的结合纹理特征的支持向量机图象分割方法,将纹理特征和灰度特征一起组成训练特征向量,利用支持向量机分类方法进行图象分割.该算法结合了纹理特征在图象描述中的重要意义和支持向量机方法在模式识别领域已表现出的优越性能,实验证明其在图象分割中取得了良好的效果.同时,当需要处理一批内容相似,感兴趣区域具有相同纹理、灰度特征的同类图象时,只需对其中一幅代表性的图象进行SVM训练,所产生的分类模型适用于所有该类图象,无需逐幅进行处理,大大简化了运算过程.     

方向测度及其在纹理识别中的应用

在一均匀的纹理图象中沿任何一个方向象素的灰度变化都服从一定的规律.依据这个特 点,本文提出一种新的纹理统计特征--方向测度.方向测度能够提取纹理的二阶及高阶统 计特征.高阶方向测度对自然纹理具有很高的识别率.另外方向测度的计算量小,运算结构简 单,利于多机并行处理.     

基于各向异性分离的纹理图象分析及重构

纹理的各向异性特征（方向性）对于纹理分析有重要意义，基于各向同性和各向异性分离的思想，提出了一种用于方向性纹理分析和综合的多通道模型。分别从频域和空域研究了纹理图象的方向性及非方向性特征，导出了确定纹理主控方向的有效计算方法和残余图象的随机场模型逼近，并将分析所得的参数用于纹理的综合。实验结果和性能分析与比较证实了该方法的有效性和灵活性。     

基于纹理分析的去图象噪声研究

针对中巴卫星高分辨率CCD相机接收影像存在明显的条带噪声，本文提出了基于纹理分析的去条带方法，即将图象上具有特定特征的噪声信息看作是某种对应的纹理特征，在基于纹理特征滤波法进行图象预处理的基础上，再用灰度共生矩阵法进行直方图平滑，以进一步消除局部噪声．     

Automatic texture segmentation for content-based image retrieval application

In this article, a brief review on texture segmentation is presented, before a novel automatic texture segmentation algorithm is developed. The algorithm is based on a modified discrete wavelet frames and the mean shift algorithm. The proposed technique is tested on a range of textured images including composite texture images, synthetic texture images, real scene images as well as our main source of images, the museum images of various kinds. An extension to the automatic texture segmentation, a texture identifier is also introduced for integration into a retrieval system, providing an excellent approach to content-based image retrieval using texture features.     

Efficient distance-based per-pixel texture classification with Gabor wavelet filters

This paper proposes an efficient solution to the problem of per-pixel classification of textured images with multichannel Gabor wavelet filters based on a selection scheme that automatically determines a subset of prototypes that characterize each texture class. Results with Brodatz compositions and outdoor images, and comparisons with alternative classification techniques are presented.     

Estimation of orientation of a textured planar surface using projective equations and separable analysis with M-channel wavelet decomposition

Estimation of the orientation of a textured planar surface is one of the basic tasks in the area of “shape from texture”. For the solution of this task, many successful approaches were proposed. In this paper, we have examined a few unaddressed questions: First, is there a mathematical formulation that relates the spectral characteristics of the texture pattern and the orientation of an inclined planar surface in a polar-coordinate system? Second, is there a good wavelet-based approach that produces an accurate estimate of the orientation angle of the textured planar surface by analyzing the spectral behavior of one single uncalibrated image?To answer these questions at first we present the formulation of a “texture projective equation”, which relates the depth and orientation of an inclined planar surface in a polar coordinate system with the spectral properties of its image texture. A suitable imaging geometry has been considered to enable separable analysis of the effect of inclination of the texture surface. Next, a method for shape from texture is presented based on discrete wavelet analysis to estimate the orientation of the planar surface. This approach although designed mainly for M-channel wavelets, is also applicable for dyadic wavelet analysis. Texture characteristics in the subbands of wavelet decomposition are analyzed using scalograms, and quantitatively evaluated based on texture projective equations. The proposed method of estimation of the orientation of a planar texture surface is evaluated using a set of simulated and real world textured images.     

Multiscale Bayesian texture segmentation using neural networks and Markov random fields

This paper presents a wavelet-based texture segmentation method using multilayer perceptron (MLP) networks and Markov random fields (MRF) in a multi-scale Bayesian framework. Inputs and outputs of MLP networks are constructed to estimate a posterior probability. The multi-scale features produced by multi-level wavelet decompositions of textured images are classified at each scale by maximum a posterior (MAP) classification and the posterior probabilities from MLP networks. An MRF model is used in order to model the prior distribution of each texture class, and a factor, which fuses the classification information through scales and acts as a guide for the labeling decision, is incorporated into the MAP classification of each scale. By fusing the multi-scale MAP classifications sequentially from coarse to fine scales, our proposed method gets the final and improved segmentation result at the finest scale. In this fusion process, the MRF model serves as the smoothness constraint and the Gibbs sampler acts as the MAP classifier. Our texture segmentation method was applied to segmentation of gray-level textured images. The proposed segmentation method shows better performance than texture segmentation using the hidden Markov trees (HMT) model and the HMTseg algorithm, which is a multi-scale Bayesian image segmentation algorithm.     

基于小波分形特征提取的图象分割方法

提出了一种基于小波分解和分形纹理特征计算的图象分割方法,首先考虑对图象进行小波变换,然后对不同通道的子图象提取纹理的分形特征和能量特征,最后用直方图阈值分割方法实现图象的分割,实验表明,该方法对模拟纹理图象以及多少谱遥感图象的分割都取得了满意的效果。     

结合活动轮廓模型的无监督纹理图像分割

定义了清晰度参数、细节信号能量参数和边缘信号能量参数3个纹理参数,对图像的纹理特征进行分析,以获取原图像的特征能量图;再利用基于简化Mumford-Shah的活动轮廓模型对图像进行纹理分割,该分割模型能较好地处理模糊、缺省的边界,同时具有去噪的功能．利用水平集方法求解该模型,解决了演化曲线拓扑可变的问题．与传统的纹理分析方法相比,文中方法能更好地表达图像中复杂纹理的信号特征．通过对合成纹理图与自然纹理图进行分割及大量实验结果表明：该方法能有效、快速地分割纹理图像．     

HVS-based scalable image watermarking

This paper proposes a novel human vision system based, spread spectrum method to scalable image watermarking. A scalable decomposition of the watermark is spread into the entire frequency sub-bands of the wavelet decomposed image. At each wavelet sub-band, the watermark data are inserted into the selected coefficients of the sub-band in a manner that the watermark embedding visual artifact occurs in the highly textured, highly contrasted and very dark/bright areas of the image. In the lowest frequency sub-band of wavelet transform, the coefficients are selected by independent analysis of texture, contrast and luminance information. In high frequency sub-bands, the coefficient selection is done by analyzing coefficients amplitude and local entropy. The experimental results show that the watermarked test images are highly transparent and robust against scalable wavelet-based image coding even at very low bit-rate coding. The proposed approach can guarantee content authentication for scalable coded images, especially on heterogeneous networks which different users with different process capabilities and network access bandwidth use unique multimedia sources.

     

基于图像纹理和小波变换的聚类分割方法

针对纹理图像,本文提出了一种基于图像纹理特征的非学习分割方法。采用小波变换和快速k-means聚类分割算法,减少了整个处理过程的运算量。为了保证分类算法的精确性,运用了总体流量变化最小（Total Variation Flow）[1]非线性去噪方法对图像进行预处理,从而将减小图像噪声污染带来的分割误差。在图像特征的提取上,运用Gabor滤波器原理生成滤波空间,并让图像通过滤波空间而生成特征向量空间。通过制定一个快速寻优策略,从而达到分割图像的目的。     

Independent component analysis for texture segmentation

Independent component analysis (ICA) of textured images is presented as a computational technique for creating a new data dependent filter bank for use in texture segmentation. We show that the ICA filters are able to capture the inherent properties of textured images. The new filters are similar to Gabor filters, but seem to be richer in the sense that their frequency responses may be more complex. These properties enable us to use the ICA filter bank to create energy features for effective texture segmentation. Our experiments using multi-textured images show that the ICA filter bank yields similar or better segmentation results than the Gabor filter bank.