Feature Detection with Automatic Scale Selection

The fact that objects in the world appear in different ways depending on the scale of observation has important implications if one aims at describing them. It shows that the notion of scale is of utmost importance when processing unknown measurement data by automatic methods. In their seminal works, Witkin (1983) and Koenderink (1984) proposed to approach this problem by representing image structures at different scales in a so-called scale-space representation. Traditional scale-space theory building on this work, however, does not address the problem of how to select local appropriate scales for further analysis. This article proposes a systematic methodology for dealing with this problem. A framework is presented for generating hypotheses about interesting scale levels in image data, based on a general principle stating that local extrema over scales of different combinations of -normalized derivatives are likely candidates to correspond to interesting structures. Specifically, it is shown how this idea can be used as a major mechanism in algorithms for automatic scale selection, which adapt the local scales of processing to the local image structure.Support for the proposed approach is given in terms of a general theoretical investigation of the behaviour of the scale selection method under rescalings of the input pattern and by integration with different types of early visual modules, including experiments on real-world and synthetic data. Support is also given by a detailed analysis of how different types of feature detectors perform when integrated with a scale selection mechanism and then applied to characteristic model patterns. Specifically, it is described in detail how the proposed methodology applies to the problems of blob detection, junction detection, edge detection, ridge detection and local frequency estimation.In many computer vision applications, the poor performance of the low-level vision modules constitutes a major bottleneck. It is argued that the inclusion of mechanisms for automatic scale selection is essential if we are to construct vision systems to automatically analyse complex unknown environments.     

基于多结构元多尺度的形态学边缘检测

在形态学梯度边缘检测算子的基础上,针对图像中的几何特征和噪声提出了一种基于多结构元、多尺度的边缘检测方法,用不同取向的结构元素对图像进行多尺度检测,并综合各尺度下的边缘,得到了噪声存在下的理想边缘。实验表明,文中的方法边缘定位准确、轮廓清晰,保留了更多的图像细节,具有较强的抗噪能力。     

3D Edge Detection by Selection of Level Surface Patches

We propose a new edge detector for 3D gray-scale images, extending the 2D edge detector of Desolneux et al. (J. Math. Imaging Vis. 14(3):271–284, 2001). While the edges of a planar image are pieces of curve, the edges of a volumetric image are pieces of surface, which are more delicate to manage. The proposed edge detector works by selecting those pieces of level surface which are well-contrasted according to a statistical test, called Helmholtz principle. As it is infeasible to treat all the possible pieces of each level surface, we restrict the search to the regions that result of optimizing the Mumford-Shah functional of the gradient over the surface, throughout all scales. We assert that this selection device results in a good edge detector for a wide class of images, including several types of medical images from X-ray computed tomography and magnetic resonance.

自适应多尺度边缘检测

提出了自适应多尺度边缘检测算法及其快速实现办法.算法通过自适应确定边缘像元的最佳滤波尺度来检测边缘,计算量较小.同时提出了一种自适应确定一幅图像边缘的尺度范围的方法,并为描述边缘特性增加了一个边缘尺度参数.用于检测实际图像边缘的实验结果是令人满意的.     

An efficient multiresolution edge detector employing a wide range of scales

Changes of image intensities can occur over a wide range of scales. Therefore, they should be analyzed accordingly. Until now, the reconstruction of a single edge map from the ones obtained at each scale has not been solved efficiently. We propose an edge detector that, using a local procedure to select an optimal scale, analyzes the input image with a virtually unlimited set of scales and yet has the same computational complexity as a single-scale convolution. The criteria to derive this algorithm and its ability to detect and localize step edges in the presence of noise are shown.     

多尺度形态学图像边缘检测方法

在深入地探讨数学形态学在边缘检测领域中的应用的基础上,提出了一种形态边缘检测算子,并用该算子提取图像边缘。然后进行形态结构元素尺度调整,综合各尺度下的边缘特征,得到了噪声存在条件下较为理想的图像边缘,实验证明了该算法的可行性和有效性。     

基于矢量Prewitt算子的多尺度彩色图象边缘检测方法

在矢量Ｐｒｅｗｉｔｔ算子的基础上,引入多凡度组合正则化处理,提出了一种新的彩色图象边缘检测方法,实验表明,若对检测精度,边缘完整性,抗噪性等方面进行综合评价,该方法优于标量算子和单一尺度下的矢量算子。     

Robust image corner detection through curvature scale space

This paper describes a novel method for image corner detection based on the curvature scale-space (CSS) representation. The first step is to extract edges from the original image using a Canny detector (1986). The corner points of an image are defined as points where image edges have their maxima of absolute curvature. The corner points are detected at a high scale of the CSS and tracked through multiple lower scales to improve localization. This method is very robust to noise, and we believe that it performs better than the existing corner detectors An improvement to Canny edge detector's response to 45° and 135° edges is also proposed. Furthermore, the CSS detector can provide additional point features (curvature zero-crossings of image edge contours) in addition to the traditional corners     

基于统计处理和B样条小波变换的毫米波图像边缘检测

针对毫米波图像噪声强、分辨率低的特点,提出了一种新的边缘检测方法。该方法首先根据统计信号处理理论定义了标准化梯度强度这一物理量;然后采用3次B样条函数的一阶导数作为边缘检测算子,由小波变换后得到的图像水平、垂直方向的高频信息,并根据这些信息确定出标准化梯度强度;接着采用单门限的处理得到图像粗边缘;最后对粗边缘施行非最大抑制处理和滤波来得到检测结果。实验证明,该方法可用固定的单门限自动、快速地检测出毫米波图像中人体背景下物体的边缘,满足安检需要。     

A new edge detector integrating scale-spectrum information

This paper presents a new scale space-based method to extract edges in gray level images. The method is based on a novel representation of gray-level shape called the scale-spectrum space. The scale space representation is used to describe an image at different scales. In order to obtain the original image edges, an edge detector is applied to each simplified image on the corresponding scale. At best, some form of compromise among the edges at different scale levels may be sought. To overcome this problem, we present a stability criterion to combine edges obtained at different scales. Usual problems in edge detection such as displacement, redundancy and error are analyzed and solved using a realistic estimation of displacement of points across scale space. The proposed approach suppress the finer details without weakening or dislocating the larger scale edges (the usual problems of edge detection using an isotropic diffusion procedure) in an improved manner compared to anisotropic diffusion procedures because a tuning function is not required. The proposed methodology is biologically inspired by the behavior of visual cortex neurones as well as retinal cells.     

一种改进型Canny边缘检测算法

边缘检测是提取图像特征的首要条件。文章提出了一种改进型Canny边缘检测算法。首先在边缘梯度计算时,将二维滤波模板分解为两个一维滤波模板,实现并行处理,提高运算速度;引入双阈值法则同时保证图像中强边缘点和弱边缘点的提取,并基于非局部最大值抑制原理检测边缘点,大大提高了边缘检测的精度和准确度;最后采用形态学算子实现对检测边缘进行细化处理,实现了单像素级细化边缘提取。实验结果表明,该算法在保证实时性的同时,具有很好的检测精度和准确度。     

Adaptive determination of filter scales for edge detection

The authors suggest a regularization method for determining scales for edge detection adaptively for each site in the image plane. Specifically, they extend the optimal filter concept of T. Poggio et al. (1984) and the scale-space concept of A. Witkin (1983) to an adaptive scale parameter. To avoid an ill-posed feature synthesis problem, the scheme automatically finds optimal scales adaptively for each pixel before detecting final edge maps. The authors introduce an energy function defined as a functional over continuous scale space. Natural constraints for edge detection are incorporated into the energy function. To obtain a set of optimal scales that can minimize the energy function, a parallel relaxation algorithm is introduced. Experiments for synthetic and natural scenes show the advantages of the algorithm. In particular, it is shown that this system can detect both step and diffuse edges while drastically filtering out the random noise     

基于多尺度多分辨率局部边缘模式的边缘检测

由于传统基于梯度的方形边缘检测算子包含边缘方向过少（一般为2个或4个方向）,因此无法从多分辨率角度检测边缘,进而会丢失其他方向的边缘信息。针对上述问题,提出一种具有多尺度、多分辨率特性的边缘检测算子,称为可变局部边缘模式（Varied Local Edge Pattern,VLEP）算子,并用来提取图像边缘信息。算法主要思路包括,将图像经过高斯滤波器平滑,使用一组或多组VLEP算子与滤波后的图像进行卷积,得到边缘强度,从而获得边缘梯度值,最后设置适当的梯度阈值,对梯度图像进行二值化处理,完成图像的边缘检测。此外,当多组VLEP算子被同时使用时,考虑结合加权融合思想,以便获得更加丰富的边缘信息。实验结果表明,提出的边缘检测算法比其他经典的方法具有更好的边缘检测效果。     

Edge Detection by Helmholtz Principle

We apply to edge detection a recently introduced method for computing geometric structures in a digital image, without any a priori information. According to a basic principle of perception due to Helmholtz, an observed geometric structure is perceptually meaningful if its number of occurences would be very small in a random situation: in this context, geometric structures are characterized as large deviations from randomness. This leads us to define and compute edges and boundaries (closed edges) in an image by a parameter-free method. Maximal detectable boundaries and edges are defined, computed, and the results compared with the ones obtained by classical algorithms.     

基于小波变换与灰色系统理论的图像边缘检测

多尺度边缘综合一直是多尺度思想中较难解决的问题。本文将灰色系统理论与多尺度边缘检测思想相结合．提出基于灰色关联分析和梯度方向的图像边缘宽度计算策略,并根据边缘宽度自适应地调整样条小波的滤波尺度参数,从而实现对有噪图像进行自适应尺度边缘检测。仿真结果表明本文算法不仅能有效地抑制噪声,而且对细节边缘和模糊弱边缘均有较好的检测效果。     

Scale Selection Properties of Generalized Scale-Space Interest Point Detectors

Scale-invariant interest points have found several highly successful applications in computer vision, in particular for image-based matching and recognition. This paper presents a theoretical analysis of the scale selection properties of a generalized framework for detecting interest points from scale-space features presented in Lindeberg (Int. J. Comput. Vis. 2010, under revision) and comprising:

an enriched set of differential interest operators at a fixed scale including the Laplacian operator, the determinant of the Hessian, the new Hessian feature strength measures I and II and the rescaled level curve curvature operator, as well as

an enriched set of scale selection mechanisms including scale selection based on local extrema over scale, complementary post-smoothing after the computation of non-linear differential invariants and scale selection based on weighted averaging of scale values along feature trajectories over scale.

It is shown how the selected scales of different linear and non-linear interest point detectors can be analyzed for Gaussian blob models. Specifically it is shown that for a rotationally symmetric Gaussian blob model, the scale estimates obtained by weighted scale selection will be similar to the scale estimates obtained from local extrema over scale of scale normalized derivatives for each one of the pure second-order operators. In this respect, no scale compensation is needed between the two types of scale selection approaches. When using post-smoothing, the scale estimates may, however, be different between different types of interest point operators, and it is shown how relative calibration factors can be derived to enable comparable scale estimates for each purely second-order operator and for different amounts of self-similar post-smoothing. A theoretical analysis of the sensitivity to affine image deformations is presented, and it is shown that the scale estimates obtained from the determinant of the Hessian operator are affine covariant for an anisotropic Gaussian blob model. Among the other purely second-order operators, the Hessian feature strength measure I has the lowest sensitivity to non-uniform scaling transformations, followed by the Laplacian operator and the Hessian feature strength measure II. The predictions from this theoretical analysis agree with experimental results of the repeatability properties of the different interest point detectors under affine and perspective transformations of real image data. A number of less complete results are derived for the level curve curvature operator.     

基于语义信息的精细化边缘检测方法

边缘检测是在图像中准确地提取视觉上显著的边缘像素,以得到图像的边缘信息,然而传统基于全卷积网络的边缘检测方法通常存在预测边缘粗糙、模糊等问题。提出一种语义信息指导的精细化边缘检测方法。通过图像分割子网络将学习到的图像语义信息传递给边缘检测子网络,同时利用图像语义信息指导边缘检测子网络,其引入具有注意力机制与残差结构的特征融合模块,以生成精细的图像边缘,增强不同尺度的特征融合。在此基础上,结合图像分割任务和图像边缘检测任务中的代价函数定义新的模型代价函数并进行训练,进一步提高网络边缘检测质量。在BSDS500数据集上的实验结果验证了该方法的有效性,结果表明,该方法的固定轮廓阈值与图像最佳阈值分别达到0.818和0.841,相比HED、RCF等主流边缘检测方法,能够预测更精细的边缘图像,且鲁棒性更优。     

基于边缘特征的车道偏移检测与预警

车道偏移的检测是智能车辆辅助驾驶系统中的重要技术问题之一.通过基于灰度阈值分割的梯度边缘检测技术,在对路面图像进行边缘检测的同时,配合以路面的灰度信息,准确地分离出车道标志线的边缘,再依此定义车道的跟踪区域--感兴趣区域(ROI),利用车道边缘信息定义边缘分布函数EDF(Edge Distribution Function),通过对跟踪区域中车道线梯度方向的分析,获取两条车道标志线在道路图像中的方向,以此作为车道偏移判断与预警的主要根据.该方法能够有效地抑制图像中非线性物体的干扰,是一种有效、可靠的车道偏移检测与预警方法.     

改进的数学形态学图像边缘提取算法研究

研究图像边缘优化提取问题。由于图像在进行边缘提取过程中,容易受到外界信息的干扰,特别是当受到噪声等因素影响时,造成图像边缘提取困难。为此提出了一种新的采用两层数学形态学增强操作提取图像边缘的技术。首先将利用形态学对灰度图像进行增强,并以为基础利用形态学的膨胀操作单独对边缘进行增强,然后将图像切分成小块,针对不同的小块来区分边缘与非边缘;最终经过模板滤波,获得清晰的边缘结果图像。仿真结果表明,改进的算法快速有效,在提取完整的边缘的同时,能够有效的抑制噪声和背景因素对边缘的干扰,并优于其他传统边缘提取方法。