Adaptive scale filtering: a general method for obtaining shape fromtexture

Introduces adaptive scale filtering, a general method for deriving shape from texture under perspective projection without recourse to prior segmentation of the image into geometric texture elements (texels), and without thresholding of filtered images. If texels on a given surface can be identified in an image then the orientation of that surface can be obtained. However, there is no general characterization of texels for arbitrary textures. Furthermore, even if the size and shape of texels on the surface is invariant with regard to position, perspective projection ensures that the size and shape of the corresponding image texels vary by orders of magnitude. Commencing with an initial set F_O of identical image filters, adaptive scale filtering iteratively derives a set F_N which contains a unique filter for each image position. Each element of F_N is tuned to the three-dimensional structure of the surface; that is, all image filters in F_N back-project to an identical shape and size on the surface. Thus image texels of various sizes, but associated with a single spatial scale on the surface, can be identified in different parts of the image. When combined with conventional shape from texture methods, edges derived using F_N provide accurate estimates of surface orientation. Results for planar surfaces are presented     

Texture features for object salience

Although texture is important for many vision-related tasks, it is not used in most salience models. As a consequence, there are images where all existing salience algorithms fail. We introduce a novel set of texture features built on top of a fast model of complex cells in striate cortex, i.e., visual area V1. The texture at each position is characterised by the two-dimensional local power spectrum obtained from Gabor filters which are tuned to many scales and orientations. We then apply a parametric model and describe the local spectrum by the combination of two one-dimensional Gaussian approximations: the scale and orientation distributions. The scale distribution indicates whether the texture has a dominant frequency and what frequency it is. Likewise, the orientation distribution attests the degree of anisotropy. We evaluate the features in combination with the state-of-the-art VOCUS2 salience algorithm. We found that using our novel texture features in addition to colour improves AUC by 3.8% on the PASCAL-S dataset when compared to the colour-only baseline, and by 62% on a novel texture-based dataset.     

一种方向Gabor滤波纹理分割算法

结合人眼视觉特性，设计了一种方向Gabor滤波器，该滤波器顾及了纹理图像的方向特性；利用Gabor滤波器的带通技术，抑制次要纹理图像的主频率分量，增强目标纹理图像主频率分量，使滤波输出图像具有较大的类间离散度和较小的类内离散度，将纹理图像的分割转化为传统的图像分割，使图像的分割质量和算法效率都得到了提高。     

Shape from regular patterns

This paper describes an algorithm to obtain local surface orientation from the apparent surface-pattern distortion in an image.We propose a spherical projection to model perspective imaging. A mapping is defined based on the measurement of the local distortions of a repeated known texture pattern due to the image projection. This mapping maps an apparent shape on the image sphere to a locus of possible surface orientations on the Gaussian sphere.An iterative constraint propagation algorithm with the orientations at occluding boundaries reduces possible surface orientations to a unique orientation. This algorithm can recover local surface orientation as well as interpolate surface orientations where no information is available. This algorithm is applied to a real image to demonstrate its performance.     

基于匹配Gabor滤波器的规则纹理缺陷检测方法

许多工业产品表面纹理都可以被认为是由基本纹理单元在空间按照一定的规则进行排列组合的结果,但由于各种原因,这些有规则纹理图象经常出现的一些缺陷,因而检测这些有规则纹理图象的缺陷是机器视觉检测的重要内容,为了对这种缺陷进行有效地检测,在对这类纹理图象进行功率谱分析的基础上,根据人眼的视觉原理,设计了两类匹配Gabor滤波器,即正常纹理匹配Gabor滤波器和缺陷纹理匹配Gabor滤波器,前者能够突出正常纹理,抑制缺陷纹理,而后者恰恰相反,在将这两类滤波器用于规则纹理图象缺陷的自动检测时,均获得了良好的检测精度和速度。     

Shape from patterns: Regularization

We present a theory for the recovery of the shape of a surface covered with small elements (texels). The theory is based on the apparent surface-pattern distortion in the image and fits the regularization paradigm, recently introduced in computer vision by Poggio et al., [1985]. A mapping is defined on the basis of measurement of the local distortions of a repeated unknown texture pattern due to the image projection. From this, a constraint on the gradient orientation is determined from the apparent area of a texture element. The analysis is done under an approximation of the perspective projection called paraperspective. The resulting algorithm is applied to several synthetic and real images to demonstrate its performance.The author is Yiannis     

基于Gabor滤波器组的车牌汉字特征提取

提出基于Gabor滤波器组的特征提取新方法.利用汉字图像的统计信息及归一化信息,提出针对车牌汉字的有效的Gabor滤波器组参数优化方法,并设计一组Gabor滤波器用于提取车牌汉字图像中不同中心频率和方位的笔画纹理特征,实现直接对灰度图像的特征提取.实验结果表明,相比传统二值化特征提取方法,采用基于Gabor滤波器组的小波变换提取特征能够获得更良好的识别性能.     

基于局部谱能量自相似矩阵的纹理描述

对于纹理检测和分类中的纹理描述问题,提出一种新的基于Gabor滤波器组局部谱能量的自相似矩阵来描述纹理的方法。首先采用多尺度、方向的极坐标对数Gabor滤波器组对纹理模板进行滤波,获得频域上局部频段和方向上的纹理信息;然后计算频域上各尺度、方向上局部谱能量的自相似度量,将这些度量值以自相似矩阵的形式进行存储,并作为纹理特征的描述子;最后将这种描述方法应用到纹理检测和分类中。由于该描述子主要体现的是纹理模板在不同频段和方向局部谱能量的自相似程度,所以它对滤波器参数的依赖度较低。实验中利用纹理特征描述子可以实现比较准确的纹理检测,多类纹理合成图像分类实验的准确率达到了91%以上。实验结果说明,纹理局部谱能量的自相似矩阵是一种十分有效的纹理描述方法,其检测和分类的结果对后期的纹理分割、纹理识别等研究领域具有广泛的应用前景。     

Shape from texture for smooth curved surfaces in perspective projection

Projective distortion of surface texture observed in a perspective image can provide direct information about the shape of the underlying surface. Previous theories have generally concerned planar surfaces; this paper presents a systematic analysis of first- and second-order texture distortion cues for the case of a smooth, curved surface. In particular, several kinds of texture gradients are analyzed and are related to surface orientation and surface curvature. The local estimates obtained from these cues can be integrated to obtain a global surface shape, and it is shown that the two surfaces resulting from the well-known tilt ambiguity in the local foreshortening cue typically have qualitatively different shapes. As an example of a practical application of the analysis, a shape-from-texture algorithm based on local orientation-selective filtering is described, and some experimental results are shown.     

Texture isolation by adaptive digital filtering

The separation of different types of texture information is performed in the Fourier domain through two-dimensional binary filters of radial asymmetry. The filters are designed after Fourier transformation of local samples and weighting of the spectral energy at each spatial frequency for the different types of texture information. Some results of using the filters to separate urban and forest areas in a photographic image are presented.     

Shape from texture using local spectral moments

Presents a non-feature-based solution to the problem of computing the shape of curved surfaces from texture information. First, the use of local spatial-frequency spectra and their moments to describe texture is discussed and motivated. A new, more accurate method for measuring the local spatial-frequency moments of an image texture using Gabor elementary functions and their derivatives is presented. Also described is a technique for separating shading from texture information, which makes the shape-from-texture algorithm robust to the shading effects found in real imagery. Second, a detailed model for the projection of local spectra and spectral moments of any surface reflectance patterns (not just textures) is developed. Third, the conditions under which the projection model can be solved for the orientation of the surface at each point are explored. Unlike earlier non-feature-based, curved surface shape-from-texture approaches, the assumption that the surface texture is isotropic is not required; surface texture homogeneity can be assumed instead. The algorithm's ability to operate on anisotropic and nondeterministic textures, and on both smooth- and rough-textured surfaces, is demonstrated     

Computing Local Surface Orientation and Shape from Texture for Curved Surfaces

Shape from texture is best analyzed in two stages, analogous to stereopsis and structure from motion: (a) Computing the texture distortion from the image, and (b) Interpreting the texture distortion to infer the orientation and shape of the surface in the scene. We model the texture distortion for a given point and direction on the image plane as an affine transformation and derive the relationship between the parameters of this transformation and the shape parameters. We have developed a technique for estimating affine transforms between nearby image patches which is based on solving a system of linear constraints derived from a differential analysis. One need not explicitly identify texels or make restrictive assumptions about the nature of the texture such as isotropy. We use non-linear minimization of a least squares error criterion to recover the surface orientation (slant and tilt) and shape (principal curvatures and directions) based on the estimated affine transforms in a number of different directions. A simple linear algorithm based on singular value decomposition of the linear parts of the affine transforms provides the initial guess for the minimization procedure. Experimental results on both planar and curved surfaces under perspective projection demonstrate good estimates for both orientation and shape. A sensitivity analysis yields predictions for both computer vision algorithms and human perception of shape from texture.     

基于方向可调滤波器的不同焦点图像融合

该文提出了一种基于方向可调滤波器的图像融合新方法。在该方法中,采用方向可调滤波器及其Hilbert变换组成的正交滤波器组,分析两幅不同焦点图像的高频成分中的主要方向及局部方向能量,自动判别出每幅源图像中的清晰部分,并把各个清晰区域融合入结果图像中。仿真试验表明,这种算法能很好地保存图像边界及纹理信息,并具有较好的综合感观。     

基于楔形滤波器的纹理图像方向信息提取

提出了一种基于楔形滤波器的图像方向信息提取方法。通过设计一个原型楔形滤波器,对该滤波器的系数矩阵进行插值后得到一组方向滤波器。之后,对图像进行滤波,并对各方向滤波器的输出进行判断以提取图像中的方向信息。实验结果表明,该方法简单有效,可用于纹理图像的方向检测。     

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.     

基于句子级的唇语识别技术

唇读是通过口型变化判断话者内容,唇读研究属于人机交互范畴。识别在生物界大体包括两个方面,人物身份的鉴别和基本内容的认知。现阶段唇读的研究主要是基于说话者内容的识别,对采集的话者唇动图像序列进行有效的预处理(包括视频切割,图像增强,唇边缘定位),预处理后如何选择合适的特征是解决识别准确性的关键问题,在唇读识别研究中采用了基于口型变化序列的形状特征和图象特征进行实验。最后采用半连续hmm模型完成计算机唇语识别。     

Efficient recovery of shape from texture

Witkin proposed a maximum likelihood model for the recovery of surface orientation from image texture. We develop two efficient algorithms for solving this shape from texture problem and compare the results of these algorithms with the algorithm described in [1].     

Textural filters based on the texture spectrum

Conventional digital filtering techniques, based on classical Fourier analysis (that is, low-pass, high-pass and band-pass), are widely used in digital image processing. Unsatisfaction may be encountered when applying these filters to texture analysis of images, where one needs some specific spatial filters which are able to transform an image in the sense of texture rather than the spectral properties. Such textural filters can be designed in the texture spectrum domain and they are of interest for texture analysis. An example is given in this paper, and has been applied to four of Brodatz's natural images. The result shows a promising potential of the texture spectrum for designing textural filters.     

基于Haar特性的LBP纹理特征

图像纹理特征能够反映图像的灰度分布程度、对比度、空间分布和图像的内在变化特性,在确保较低计算复杂度的前提下,有效提取深层次的图像纹理信息是其研究的难点问题。针对这一问题,从相邻区域的统计特征分析入手,提出了一种Haar型特性局部二元模式(Haar local binary pattern,简称HLBP)的图像纹理特征提取方法。鉴于Haar型特征运算简单、快捷,统计局部特征有效、可靠,将其引入LBP中。该方法首先给出8组Haar型特征编码模式,按照局部二元模式(local binary pattern,简称LBP)统计图像局部纹理特征,因采用局部区域统计方法能够有效降低噪声的影响;其次,为了进一步提高图像纹理特征的有效呈现,结合Gabor小波滤波在不同方向、不同尺度对灰度水平图像进行特征提取,以增强纹理有效提取的性能,提高不变特征的稳健性;最后,通过4组对比实验验证了该方法的可行性。实验分别在标准的 Brodatz 正常分块纹理库测试集、分块且缩放 Brodatz 纹理库测试集、分块且旋转Brodatz纹理库测试集以及Yale B扩展的非均匀光照条件人脸库测试集上进行。实验结果表明,该方法能够有效地表达图像的纹理特征。