基于边缘检测技术的指纹预处理研究

介绍了一种基于二维边缘检测方法的指纹图像预处理算法.通过采用基于Gauss-Laplace图像边缘检测技术,来计算指纹脊线的方向,形成精确的指纹方向图.在此基础上,配合其它经典的数字图像像素规格、脊线提取和灰度修正方法形成本指纹图像预处理算法.试验结果表明,本算法在清晰地提取指纹脊线的同时,较好地保留了一些传统指纹预处理方法所容易丢失的精细指纹特征,提高了指纹图像预处理算法的运行速度和处理质量.     

自适应Catmull-Rom样条图像放大

针对Catmull-Rom样条图像插值放大不能保证图像内各物体之间边界清晰的问题,提出一种基于几何分类的自适应Catmull-Rom样条图像插值放大算法.通过对原图像的边缘进行几何分类,根据原图像的边缘几何类型插值目标图像中的未知像素点;若未知像素点为原图像中的边缘,则调整Catmull-Rom样条的切向方向和切向长度来计算未知像素值,得到边缘保持的目标图像.实验结果表明,应用该算法得到的目标图像边界清晰、细节模糊减少,忠实地反映了原图像的面貌.     

基于图像纹理复杂度和奇异值分解的重采样检测

针对图像篡改时可能会经历重采样操作,而重采样过程中的插值步骤会对重采样图像像素引入一定的线性相关性的问题,提出一种重采样检测算法.采用奇异值分解度量像素间的线性相关性,针对纹理复杂程度不同的子像素块分析插值处理对其线性相关性的影响;以零奇异值个数和奇异值均值作为分类特征,结合SVM进行重采样检测.实验结果表明,该算法能够实现对重采样图像和原始图像的准确分类.     

公路路面裂缝类病害图像处理算法研究

文章在对公路路面裂缝类病害的检测过程中,通过认真分析路面病害图像特征,研究了适合于路面病害识别的图像处理算法。由于裂缝类病害的类型包括横向裂缝、纵向裂缝和不规则裂缝,边缘可能在各个角度方向存在梯度,因此,文中构造了8个方向的模板对图像进行Sobel边缘检测。边缘检测处理后,结合加权的邻域平均噪声滤除算法和Ostu图像分割算法对病害图像进行处理,处理结果相对于其他经典算法,裂缝边缘宽度较细(2个像素),并且裂缝的边缘保护很好,裂缝边缘之间断续情况较少。该算法用于对公路路面裂缝类病害的识别检测过程中,检测精度和检测效果都很好。     

基于方向导数和B样条小波的图像边缘检测

根据图像边缘及噪声的多尺度传播特性和小波边缘检测的基本原理,提出了一种基于方向导数和三次B样条小波的边缘检测算法。该算法兼顾图像边缘的方向特征和小波基对称、线性相位的特点,较好地解决了边缘提取精度与噪声抑制能力之间的矛盾。通过计算机仿真对该算法进行验证,结果表明该算法不仅能准确地检测出图像边缘,而且能有效地抑制噪声,优于传统的边缘检测算法。     

图像边缘分割算法的优化研究与仿真

研究图像边缘分割问题,提高分割的准确性.针对图像中物体像素与其边缘像素容易发生像素粘连,粘连部分由于发生像素灰度混合,造成像素差异极小,传统的基于灰度的边缘检测算法由于不能很好的区分粘连部分的灰度差异,不能完整检测图像边缘的问题.提出了一种离散余弦变换(DCT)和数学形态学边缘分割算法.通过对提取过的特征图像在同一尺度下用多个结构元素分别对图像进行边缘分割,经过合成得到多尺度多结构元素形态学检测的边缘图像,摆脱分割算法对像素灰度的依赖.仿真结果表明:方法具有较好的抗干扰性和定位准确性,分割的边缘更为完整准确,取得了令人满意的效果.     

多方向灰度形态学边缘检测算法

本文介绍了基于灰度形态学的多方向边缘检测算法.基于边缘的多方向特征,构造了多方向的结构元素,并将边缘检测的过程与形态学开闲滤波相结合,提出了一种新的边缘检测算法.该算法在较好地检测图像边缘的同时很好地抑制了噪声.     

一种图像亚像素边缘检测算法的改进研究

为了提高刀具预调测量仪的检测精度,提出了一种改进的图像快速亚像素边缘检测算法——基于正交多项式拟合的亚像素边缘检测算法。首先,利用传统的Sobel算子完成边缘点整像素级别的检测,确定边缘的主体区域;然后,过边缘点沿边缘法线方向拓展像素,取一系列像素点并计算其灰度值;最后根据像素点灰度分布的数学特征,利用正交多项式和最小二乘法求拟合函数,通过拟合曲线确定图像边缘点的精确位置,实现图像亚像素边缘检测。实验证明,该算法运行时间短,约为0.63 s;检测精度高,可达0.1 pixels。     

利用Gabor方向导数相关矩阵的角点检测

为了提高角点检测的准确率,提出了一种使用图像的Gabor方向导数构建相关矩阵来进行图像角点检测的算法。算法首先通过Canny边缘检测算法提取检测图像的边缘轮廓;然后使用Gabor滤波器对图像进行平滑,利用每一个边缘像素和其邻近像素的Gabor方向导数构建相关矩阵,若相关矩阵的归一化特征值的和大于预定阈值并且是局部极大值,则标记该像素为角点。算法利用邻近像素Gabor方向导数之间的相关信息提取角点,与传统的基于轮廓的角点检测算法相比,检测性能更加稳健。实验结果表明：在含噪声和无噪声情况下,提出的算法检测到的真实角点更多,而错误角点更少,整体性能有明显提升     

运动汽车图像静态视点平滑特征优化仿真

由于运动汽车图像在特征采集过程中,汽车处于高速运动状态,采集的过程无法与汽车完全同步,造成汽车的特征像素分量在高速运动中丢失,产生较大的像素运动噪声,使得汽车图像边缘高频特征因为运动干扰而模糊.传统的平滑过渡方法在对运动汽车图像进行平滑处理时,按照图像中像元灰度值计算突变特性,但受到像素丢失与噪声无法抑制的影响,无法解决运动汽车图像高频分量对图像像元灰度值的干扰问题.提出基于替身运动DR算法的运动汽车图像静态视点平滑过渡方法,用替身像素描述汽车在场景中的运动特征,替身像素在场景中运动并同其它汽车的替身进行交互,采用局部化的车辆模型提高运动汽车场景的逼真度,通过依据替身运动的平滑过渡算法完成归一化线性运动汽车图像静态视点的平滑过渡,解决了运动汽车图像的平滑过渡问题.实验结果说明,所提方法可确保运动汽车图像边缘锐化,有效处理平滑噪声和锐化边缘.     

基于分数阶微积分的噪声检测和图像去噪

目的 提出一种利用分数阶微分梯度检测图像中的噪声点,并用于改进基于分数阶积分的图像去噪算法性能的算法。方法 该算法首先使用不同方向的分数阶微分梯度模板与含噪声图像进行卷积,计算出图像在不同方向上的分数阶微分梯度,依据预先设定的阈值获得不同方向的分数阶微分梯度检测图,将在所有选定方向上梯度都发生跳变的像素点判定为噪声点;然后只对被检测出的噪声点,在8个方向上进行分数阶积分运算完成去噪处理。结果 通过在人工图像中分别添加高斯噪声和椒盐噪声以及在自然图像中分别添加高斯噪声和椒盐噪声的去噪对比实验得出相同结论,即只对图像中检测出的噪声点使用分数阶积分运算进行去噪有更好的去噪性能,获得了更好的视觉效果和更高的峰值信噪比。结论 实验结果表明,基于分数阶微分梯度的噪声检测算法对解决图像去噪和保留图像纹理细节之间的矛盾有所帮助。随着对基于分数阶微分梯度噪声检测方法研究的深入,对图像中噪声检测的准确度会进一步提高,这将提供一种用于改进目前去噪算法性能的研究方向。     

小波域基于层内和层间系数约束的边缘软判决与图像去噪

在提出依概率对边缘系数软判决的基础上,运用图像小波分解后在尺度和空间方向的相关性,引入调谐函数,对边缘发生概率增加邻域约束,以进一步提高边缘发生概率的估计精度。应用于图像去噪的仿真结果表明,引入层问和层内约束后,在较好滤除噪声的同时,图像边缘也得到了明显加强。该方法也可用于边缘检测和图像分割。     

Zero crossings on lines of curvature

We investigate how much information can be found about the geometry of an object from an image when the general form of the reflection function is known but its specific form is not. We prove theorems showing that the zero crossings of the second directional derivatives occur near the extrema of the curvature along the principal directions of curvature. We next rederive and extend results of Koenderink and van Doorn showing that most extrema of the image intensity lie on parabolic lines. We prove that the directions of the isophotes (the lines of constant image intensity) always lie along the directions of curvature at parabolic lines and hence are photometric invariants. We prove that isophotes which are brighter (or dimmer) than their neighbours must necessarily be parabolic lines.     

基于边缘检测的斜纹布匹瑕疵检测

为了对布匹瑕疵进行快速准确的检测,提出了一种基于边缘检测的新算法。利用布匹图像中瑕疵与正常纹理产生的纹理边缘,将布匹瑕疵作为正常纹理的边缘检测出来。利用Sobel算子的方向性,分别对织物疵点在水平和垂直方向进行增强,计算出RGB图像中水平与垂直方向的梯度后进行边缘检测,通过图像融合和二值化完成最终检测。实验证明,该方法准确性高并且检测速率大大提高。     

基于灰色关联分析和Canny算子的图像边缘提取算法

基于灰色关联分析和Canny算子,提出了一种有效的边缘提取策略。相对于传统边缘检测方法中的梯度图像,首次提出灰色关联度图像的概念,并对两种图像进行了对比和分析。指出并讨论了灰色序列方向对边缘方向的敏感性,采用不同方向的灰色序列可以得到和梯度方向算子相似的效果。由各方向序列下的灰色关联度图像进行边缘方向判断,沿各方向进行非极小值抑制,对灰色关联度图像进行细化,然后设定自适应高低阈值进行边缘连接。实验表明该算法具有很好的处理效果。     

Tagging image by merging multiple features in a integrated manner

Image tagging is a task that automatically assigns the query image with semantic keywords called tags, which significantly facilitates image search and organization. Since tags and image visual content are represented in different feature space, how to merge the multiple features by their correlation to tag the query image is an important problem. However, most of existing approaches merge the features by using a relatively simple mechanism rather than fully exploiting the correlations between different features. In this paper, we propose a new approach to fusing different features and their correlation simultaneously for image tagging. Specifically, we employ a Feature Correlation Graph to capture the correlations between different features in an integrated manner, which take features as nodes and their correlations as edges. Then, a revised probabilistic model based on Markov Random Field is used to describe the graph for evaluating tag??s relevance to query image. Based on that, we design an image tagging algorithm for large scale web image dataset. We evaluate our approach using two large real-life corpuses collected from Flickr, and the experimental results indicate the superiority of our proposed approach over state-of-the-art techniques.     

Learning an epipolar shift compensation for light field image super-resolution

Light field imaging has drawn broad attention since the advent of practical light field capturing systems that facilitate a wide range of applications in computer vision. However, existing learning-based methods for improving the spatial resolution of light field images neglect the shifts in the sub-pixel domain that are widely used by super-resolution techniques, thus, fail in recovering rich high-frequency information. To fully exploit the shift information, our method attempts to learn an epipolar shift compensation for light field image super-resolution that allows the restored light field image to be angular coherent with the enhancement of spatial resolution. The proposed method first utilizes the rich surrounding views along some typical epipolar directions to explore the inter-view correlations. We then implement feature-level registration to capture accurate sub-pixel shifts of central view, which is constructed by the compensation module equipped with dynamic deformable convolution. Finally, the complementary information from different spatial directions is fused to provide high-frequency details for the target view. By taking each sub-aperture image as a central view, our method could be applied for light field images with any angular resolution. Extensive experiments on both synthetic and real scene datasets demonstrate the superiority of our method over the state-of-the-art qualitatively and quantitatively. Moreover, the proposed method shows good performance in preserving the inherent epipolar structures in light field images. Specifically, our LFESCN method outperforms the state-of-the-art method with about 0.7 dB (PSNR) on average.     

The role of spatial heterogeneity in detecting urban slums

Satellite images allow characterizing and monitoring urban slums. Yet the urban landscape as a complex geographic system is composed of hierarchical patterns and discrete objects in a spatial and temporal continuum with different scales and anisotropy which can only be estimated from image snapshots. Understanding the spatial heterogeneity of slums in terms of scale and anisotropy from discrete image pixels is nontrivial and has not been explicitly addressed by image-based studies detecting slums, where scale and direction in characterizing slum features are commonly done by trial and error. This study addresses this gap by analyzing the impact of scales and anisotropy detected in the scale space and frequency domain for the calculation of texture indices that ultimately govern the detection of slums. Employing case studies of three cities with a large portion of slum population and for which we have very high resolution satellite imagery, we identify the characteristic scales of slum and formal built-up areas. Results show that the characteristic scales correspond with the optimal grain size to obtain image texture features for detecting slums, while the directional spectral energy at the pixel level identifies characteristic directions. Thus texture indices calculated at the characteristic scale and along the characteristic directions of slum patterns improve the efficiency in feature extraction and classification of slums, where optimizing the scale has a higher impact on the detection of slums than choosing the optimal directions. This study provides a framework for scientifically selecting optimal scales and directions for slum mapping studies. The framework is recommended to be tested for more general applications in land surface characterization and classification especially by using high order texture indices.     

Autocorrelation-based interlaced to progressive format conversion

To generate a high resolution image from a low resolution one, interpolation plays a crucial role. However, conventional interpolation methods including edge-based interpolation methods have some drawbacks such as the limited number of edge directions, imprecise edge detection, and inefficient interpolation. To overcome these shortcomings, we propose a new edge-directed interpolation method, which has three aims: various edge directions, reliable edge detection, and outstanding interpolation. Since the number of candidate edge directions in the proposed method is flexible, we can use several edges included in the high resolution image. To accurately determine the edge direction, we use autocorrelation of neighboring pixels for candidate directions based on the duality between a high resolution image and its corresponding low resolution image. For the interpolation step, we utilize a Blackman–Harris windowed-sinc weighted average filter where we use correlation values obtained in the edge detection step as weights. Experimental results show that the proposed method outperforms conventional methods in terms of both the subjective and the objective results.     

图像异常检测研究现状综述

图像异常检测是计算机视觉领域的一个热门研究课题, 其目标是在不使用真实异常样本的情况下, 利用现有的正常样本构建模型以检测可能出现的各种异常图像, 在工业外观缺陷检测、医学图像分析、高光谱图像处理等领域有较高的研究意义和应用价值. 本文首先介绍了异常的定义以及常见的异常类型. 然后, 本文根据在模型构建过程中有无神经网络的参与, 将图像异常检测方法分为基于传统方法和基于深度学习两大类型, 并分别对相应的检测方法的设计思路、优点和局限性进行了综述与分析. 其次, 梳理了图像异常检测任务中面临的主要挑战. 最后, 对该领域未来可能的研究方向进行了展望.