Image and texture segmentation using local spectral histograms.

We present a method for segmenting images consisting of texture and nontexture regions based on local spectral histograms. Defined as a vector consisting of marginal distributions of chosen filter responses, local spectral histograms provide a feature statistic for both types of regions. Using local spectral histograms of homogeneous regions, we decompose the segmentation process into three stages. The first is the initial classification stage, where probability models for homogeneous texture and nontexture regions are derived and an initial segmentation result is obtained by classifying local windows. In the second stage, we give an algorithm that iteratively updates the segmentation using the derived probability models. The third is the boundary localization stage, where region boundaries are localized by building refined probability models that are sensitive to spatial patterns in segmented regions. We present segmentation results on texture as well as nontexture images. Our comparison with other methods shows that the proposed method produces more accurate segmentation results.     

Image retrieval using both color and texture features

In order to improve the retrieval performance of images, this paper proposes an efficient approach for extracting and retrieving color images. The block diagram of our proposed approach to content-based image retrieval (CBIR) is given firstly, and then we introduce three image feature extracting arithmetic including color histogram, edge histogram and edge direction histogram, the histogram Euclidean distance, cosine distance and histogram intersection are used to measure the image level similarity. On the basis of using color and texture features separately, a new method for image retrieval using combined features is proposed. With the test for an image database including 766 general-purpose images and comparison and analysis of performance evaluation for features and similarity measures, our proposed retrieval approach demonstrates a promising performance. Experiment shows that combined features are superior to every single one of the three features in retrieval.     

基于时间—顶点谱图小波变换的动态纹理分类方法

动态纹理在空间和时间上表现出"外观"和"运动"属性,为了有效结合这两种属性进行动态纹理分析,本文提出一种基于时间—顶点谱图小波变换与边缘分布协方差模型的动态纹理分类方法.该方法将动态纹理看成时间—顶点图信号,利用时间—顶点谱图Meyer小波变换对动态纹理进行多尺度分解,再对每个子带应用边缘分布协方差模型,由此得到带内相...     

Texture Recognition and Image Retrieval Using Gradient Indexing

Our starting point is gradient indexing, the characterization of texture by a feature vector that comprises a histogram derived from the image gradient field. We investigate the use of gradient indexing for texture recognition and image retrieval. We find that gradient indexing is a robust measure with respect to the number of bins and to the choice of the gradient operator. We also find that the gradient direction and magnitude are equally effective in recognizing different textures. Furthermore, a variant of gradient indexing called local activity spectrum is proposed and shown to have improved performance. Local activity spectrum is employed in an image retrieval system as the texture statistic. The retrieval system is based on a segmentation technique employing a distance measure called Sum of Minimum Distance. This system enables content-based retrieval of database images from templates of arbitrary size.     

一种基于局部拓扑与l1/2范数的解析字典分类的人群事件检测

所提方案在传统解析字典算法基础上,加入局部拓扑项用以描述数据之间的结构信息,同时用l_1/2范数代替 l₁范数作为稀疏约束,从而提高表示系数的稀疏度。在特征提取上,融合了包含丰富运动信息的相互作用力直方图与包含纹理信息的梯度方向直方图,然后用改进的字典对特征数据进行训练,最后通过计算测试样本在该字典下的重构误差来判断测试样本是否为异常样本。在标准行为库UMN（University of Minnesota）数据库上进行的实验证实了算法具有较高的性能。与传统的算法相比,提出的改进的解析字典分类算法在针对人群异常事件中取得了更为有效的检测。     

联合改进LBP和超像素级决策的高光谱图像分类

高光谱图像在有标签样本数目较少的情况下进行分类时,除了利用光谱特征外,空间纹理特征也是必不可少的。本文提出了一种利用多尺度多方向局部二值模式（LBP）描述子获取纹理特征,并结合超像素级指导决策的支持向量机分类方法。首先,本文方法将传统LBP描述子改进为多尺度多方向LBP描述子,一方面充分考虑了邻域像素之间的关系,另一方面在计算时分别考虑了水平垂直方向和对角方向。其次,在利用统计直方图获得纹理特征时,采用了多个尺寸窗口组合的方式,以获得多范围、高精度的纹理特征。第三,对传统的简单线性迭代聚类（SLIC）超像素分割方法进行改进,重新定义了光谱距离并引入了纹理特征距离,获得更精确的超像素分割图。最后,利用超像素分割图结合多数投票策略,对分类结果进行进一步的指导校正。实验表明,本文方法能够更有效的提取纹理特征,再结合超像素分割图的指导决策,进一步提升高光谱图像的分类性能。     

基于变化检测的机场毁伤评估算法

提出了一种基于遥感图像变化检测的机场毁伤效果评估算法,该算法由图像预处理、兴趣区域划定、毁伤特征提取和分级评估4个模块组成。首先对图像进行直方图规定化,提高图像局部对比度,并采用Hough变换提取机场区域,抑制掉过多的背景干扰;然后利用变化检测参数指标对目标特征进行描述,实现毁伤信息的有效提取;最后建立整体的特征向量"相似度",几何、纹理特征"二次距离",设计分级评估准则。仿真结果表明,该算法有效地实现了对机场目标毁伤效果的评估,同时经过适当扩展和改进,可用于各种人造目标毁伤效果的评估。     

基于SVM混合核的遥感图像变化检测

针对由实际遥感地物类型难以确定导致的多光谱遥感影像变化检测精度较低的问题,提出一种基于SVM混合核的遥感图像变化检测。首先利用CVA算法构造差异影像,其次利用灰度共生矩阵提取差异影像的纹理特征与差异影像的灰度特征组成特征向量,接着利用差异影像的直方图选择置信度高的训练样本,并利用构造的SVM混合核进行训练得到分类超平面,最后利用SVM混合核函数对差异影像进行二分类得到最后的变化检测结果。实际遥感数据验证结果表明,所构造的SVM混合核函数用于多光谱遥感影像变化检测中是可行、有效的。     

Content-based image retrieval using H.264 intra coding features

Efficient multimedia retrieval has become a vital issue because more audio and video data are now available. This paper focuses on content-based image retrieval (CBIR) in the compression domain (CPD). The retrieval features are extracted based on I-frame coding information in H.264. This paper proposes using a local mode histogram as the texture feature to match images and applying the residual coefficients to filter non-confident modes. The geometrical correspondence between two images is also considered. The experimental results show that the proposed method can substantially reduce computational and memory resource consumption, and provides similar performance compared with methods that extract features from decompressed images.     

A dynamic classifier selection and combination approach to image region labelling

In this paper we propose a ‘bank of classifiers’ approach to image region labelling and evaluate dynamic classifier selection and classifier combination approaches against a baseline approach that works with a single best classifier chosen using a validation set. In this analysis, image segmentation, feature extraction, and classification are treated as three separate steps of analysis. The classifiers used are each trained with a different texture feature representation of training images. The paper proposes a new knowledge-based predictive approach based on estimating the Mahalanobis distance between test sample feature values and the corresponding probability distribution function from training data that selectively triggers classifiers. This approach is shown to perform better than probability-based classifier combination (all classifiers are triggered but their decisions are fused with combination rules), and single classifier, respectively, based on classification rates and confusion matrices. The experiments are performed on the natural scene analysis application.     

基于金字塔分解和扇形局部均值二值模式的鲁棒纹理分类方法

针对传统局部二值模式(LBP)的特征鉴别力有限和噪声敏感性问题,该文提出一种基于金字塔分解和扇形局部均值二值模式的纹理特征提取方法。首先,将原始图像进行金字塔分解,得到对应于不同分解级别的低频和高频(差分)图像。为提取兼具鉴别力和稳健性的特征,进一步采用阈值化处理技术将高频图像转化为正、负高频图。然后,基于局部均值操作提出一种扇形局部均值二值模式(SLMBP),用于计算各级分解图像的纹理特征码。最后,对纹理特征码进行跨频带的联合编码和跨级别的直方图加权,从而获得最终的纹理特征。在公开的3个纹理数据库(Outex, Brodatz和UIUC)上进行分类实验,结果表明该文所提方法能够有效地提高纹理图像在无噪声环境和含高斯噪声环境下的分类精度。     

利用灰度和纹理特征的SAR图像分类研究

多类别多特征量情况下的合成孔径雷达(SAR)图像的目标分类是一个难以解决的问题.从灰度和纹理模型出发,提出了综合利用灰度和纹理特征的目标分类方法.均值和方差是灰度模型中重要的特征统计量,而能量、熵、对比度、局部相似性和相关性是纹理模型中重要的特征统计量.灰度和纹理特征能确切地描述SAR图像中的目标.通过构造特征向量,定义向量之间的距离,并按照最小距离方法进行目标分类.以一定大小的窗口读入样本,提高了算法的运行速度和抗噪能力.理论上,窗口越大,特征向量值越接近真实值.窗口越小,边缘的分类精度越高.实验表明该方法较好地处理了多类别多特征量情况下的SAR图像分类问题,分类结果是有效的,这为SAR图像目标分类提供了一条简单可行的途径.     

Extreme learning machine with multi-scale local receptive fields for texture classification

Texture classification is a challenging task due to the wide range of natural texture types and large intra-class variations in texture images, such as different rotations, scales, positions and lighting conditions. Many existing methods for extracting texture features are designed carefully by user for specific applications. The extracted texture features are then used as input to various classification methods, such as support vector machines, to classify the textures. The system performance greatly depends on the feature extractor. Unfortunately, there is no systematic approach for feature extractor design. In this paper, we propose a method called extreme learning machine with multi-scale local receptive fields (ELM-MSLRF) to achieve feature learning and classification simultaneously for texture classification. In contrast to traditional methods, the proposed method learns the features by the network itself and can be applied to more general applications. Additionally, it is fast and requires few computations. Experiments on the ALOT texture dataset demonstrate the attractive performance of ELM-MSLRF even compared with the state-of-the-art algorithms. Moreover, the proposed ELM-MSLRF achieves the best performance on the NORB dataset.     

基于形状无关纹理和Boosting学习的人口统计学分类

基于形状无关纹理和boosting学习,该文提出了对性别和年龄分类的方法,其中年龄被划分为儿童、青年、中年和老年4类。检测到人脸后,利用人脸配准的结果规范化人脸图像获得形状无关纹理。在此基础上提取Haar型特征、LBP直方图和Gabor Jet 3种特征,通过boosting学习分别训练分类器。实验表明,LBP直方图特征能够鲁棒地区分儿童和老人,Haar型特征用作区分青年和中年人则更为有效,而Gabor Jet特征更适于性别分类。     

Low dimensional adaptive texture feature vectors from class distance and class difference matrices

In many popular texture analysis methods, second or higher order statistics on the relation between pixel gray level values are stored in matrices. A high dimensional vector of predefined, nonadaptive features is then extracted from these matrices. Identifying a few consistently valuable features is important, as it improves classification reliability and enhances our understanding of the phenomena that we are modeling. Whatever sophisticated selection algorithm we use, there is a risk of selecting purely coincidental "good" feature sets, especially if we have a large number of features to choose from and the available data set is limited. In a unified approach to statistical texture feature extraction, we have used class distance and class difference matrices to obtain low dimensional adaptive feature vectors for texture classification. We have applied this approach to four relevant texture analysis methods. The new adaptive features outperformed the classical features when applied to the most difficult set of 45 Brodatz texture pairs. Class distance and difference matrices also clearly illustrated the difference in texture between cell nucleus images from two different prognostic classes of early ovarian cancer. For each of the texture analysis methods, one adaptive feature contained most of the discriminatory power of the method.