结合四元数与最小核值相似区的边缘检测

目的 针对传统彩色图像边缘检测方法中未充分利用图像色度信息、颜色模型间非线性转换过程中时间和空间的大量耗费、算法实现复杂等问题,将四元数引入最小核值相似区（SUSAN）算法中,提出一种RGB空间下的结合四元数与最小核值相似区的边缘检测算法。方法 该算法首先对彩色图像进行四元数描述,然后用改进的SUSAN算子进行边缘检测。针对其中单一几何阈值g的限制,以及检测出的边缘较粗等问题,本文采用Otsu算法自适应获取双几何阈值,再对弱边缘点集进行边缘生长,最后根据USAN重心及其对称最长轴来确定边缘局部方向,实现对边缘点的局部非极大值抑制,得到最终细化后的边缘图像。结果 实验选取1幅合成彩色图像及3幅标准图像库图像,与彩色Canny算法、SUSAN算法,及采用单阈值的本文算法进行对比,并采用Pratt品质因数衡量边缘定位精度。本文算法能够检测出亮度相近的不同颜色区域之间的边缘,且提取的边缘比较连续、细致,漏检边缘较少。与公认边缘检测效果较好的彩色Canny算法相比,本文算法的品质因数提高了0.012 0,耗时缩短了2.527 9 s。结论 本文提出了一种结合四元数与最小核值相似区的边缘检测算法,实现了四元数与SUSAN算子的有效融合。实验结果表明,该算法能够提高边缘定位精度,对弱噪声具有较好的抑制能力,适用于对实时性要求不高的低层次彩色图像处理。     

Mode Decomposition Evolution Equations

Partial differential equation (PDE) based methods have become some of the most powerful tools for exploring the fundamental problems in signal processing, image processing, computer vision, machine vision and artificial intelligence in the past two decades. The advantages of PDE based approaches are that they can be made fully automatic, robust for the analysis of images, videos and high dimensional data. A fundamental question is whether one can use PDEs to perform all the basic tasks in the image processing. If one can devise PDEs to perform full-scale mode decomposition for signals and images, the modes thus generated would be very useful for secondary processing to meet the needs in various types of signal and image processing. Despite of great progress in PDE based image analysis in the past two decades, the basic roles of PDEs in image/signal analysis are only limited to PDE based low-pass filters, and their applications to noise removal, edge detection, segmentation, etc. At present, it is not clear how to construct PDE based methods for full-scale mode decomposition. The above-mentioned limitation of most current PDE based image/signal processing methods is addressed in the proposed work, in which we introduce a family of mode decomposition evolution equations (MoDEEs) for a vast variety of applications. The MoDEEs are constructed as an extension of a PDE based high-pass filter (Wei and Jia in Europhys. Lett. 59(6):814–819, 2002) by using arbitrarily high order PDE based low-pass filters introduced by Wei (IEEE Signal Process. Lett. 6(7):165–167, 1999). The use of arbitrarily high order PDEs is essential to the frequency localization in the mode decomposition. Similar to the wavelet transform, the present MoDEEs have a controllable time-frequency localization and allow a perfect reconstruction of the original function. Therefore, the MoDEE operation is also called a PDE transform. However, modes generated from the present approach are in the spatial or time domain and can be easily used for secondary processing. Various simplifications of the proposed MoDEEs, including a linearized version, and an algebraic version, are discussed for computational convenience. The Fourier pseudospectral method, which is unconditionally stable for linearized high order MoDEEs, is utilized in our computation. Validation is carried out to mode separation of high frequency adjacent modes. Applications are considered to signal and image denoising, image edge detection, feature extraction, enhancement etc. It is hoped that this work enhances the understanding of high order PDEs and yields robust and useful tools for image and signal analysis.     

一种基于形态学多结构元的自适应边缘检测算法*

基于形态学的图像边缘检测是图像处理的新技术之一,针对形态学单结构元在边缘检测中遗漏边缘信息的问题,提出了基于多结构元的自适应边缘检测算法。实验证明,该算法在检测边缘时能够获得比单结构元检测更多的边缘信息,具有较高的效率和很好的抗噪声能力,是一种有效的边缘检测方法。     

Statistical edge detection: learning and evaluating edge cues

We formulate edge detection as statistical inference. This statistical edge detection is data driven, unlike standard methods for edge detection which are model based. For any set of edge detection filters (implementing local edge cues), we use presegmented images to learn the probability distributions of filter responses conditioned on whether they are evaluated on or off an edge. Edge detection is formulated as a discrimination task specified by a likelihood ratio test on the filter responses. This approach emphasizes the necessity of modeling the image background (the off-edges). We represent the conditional probability distributions nonparametrically and illustrate them on two different data sets of 100 (Sowerby) and 50 (South Florida) images. Multiple edges cues, including chrominance and multiple-scale, are combined by using their joint distributions. Hence, this cue combination is optimal in the statistical sense. We evaluate the effectiveness of different visual cues using the Chernoff information and Receiver Operator Characteristic (ROC) curves. This shows that our approach gives quantitatively better results than the Canny edge detector when the image background contains significant clutter. In addition, it enables us to determine the effectiveness of different edge cues and gives quantitative measures for the advantages of multilevel processing, for the use of chrominance, and for the relative effectiveness of different detectors. Furthermore, we show that we can learn these conditional distributions on one data set and adapt them to the other with only slight degradation of performance without knowing the ground truth on the second data set. This shows that our results are not purely domain specific. We apply the same approach to the spatial grouping of edge cues and obtain analogies to nonmaximal suppression and hysteresis.     

一种基于模糊划分的边缘检测算法

基于信息论中最大熵原理，提出了一种新的基于模糊划分的边缘检测算法，并介绍了模糊概率和用条件概率与条件熵来定义模糊划分熵的概念以及模糊划分的原理。该算法是利用自然划分以及梯度图像模糊划分的关系，在条件概率与模糊划分熵的基础上，通过最大模糊熵原则来实现图像分割中最优阈值的自动提取，以实现图像的边缘检测。通过不同类型测试图像的边缘检测结果比较表明，该算法用于边缘检测能获得很好的效果。     

基于遥感数据特征和像元替换技术的边缘提取方法

随着城市化的发展，城市遥感领域在中国发展迅速。高分辨遥感图像的边缘提取是当前城市遥感的重要研究领域。实践中，传统的边缘检测算子主要是通过图像空城特征微分，建立不同结构的模板完成。高分辨率遥感数字图像包括了空间域和光谱域两种信息，因此，借助于图像的光谱和空间域两种特征信息提高提取城市边缘信息精度已经成为当前算法开发的基本思路。该研究通过设计光谱分解和边缘检测的算子模板，综合利用了图像的光谱、空间特征信息。研究结果表明，这种方法有效地提高了城市遥感数据边缘信息的提取精度，同时还具有方法简便、计算速度怏的特点。     

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。     

融合多特征与先验信息的显著性目标检测

目的 图像的显著性目标检测是计算机视觉领域的重要研究课题。针对现有显著性目标检测结果存在的纹理细节刻画不明显和边缘轮廓显示不完整的问题,提出一种融合多特征与先验信息的显著性目标检测方法,该方法能够高效而全面地获取图像中的显著性区域。方法 首先,提取图像感兴趣的点集,计算全局对比度图,利用贝叶斯方法融合凸包和全局对比度图获得对比度特征图。通过多尺度下的颜色直方图得到颜色空间图,根据信息熵定理计算最小信息熵,并将该尺度下的颜色空间图作为颜色特征图。通过反锐化掩模方法提高图像清晰度,利用局部二值算子（LBP）获得纹理特征图。然后,通过图形正则化（GR）和流行排序（MR）算法得到中心先验图和边缘先验图。最后,利用元胞自动机融合对比度特征图、颜色特征图、纹理特征图、中心先验图和边缘先验图获得初级显著图,再通过快速引导滤波器优化处理得到最终显著图。结果 在2个公开的数据集MSRA10K和ECSSD上验证本文算法并与12种具有开源代码的流行算法进行比较,实验结果表明,本文算法在准确率-召回率（PR）曲线、受试者工作特征（ROC）曲线、综合评价指标（F-measure）、平均绝对误差（MAE）和结构化度量指标（S-measure）等方面有显著提升,整体性能优于对比算法。结论 本文算法充分利用了图像的对比度特征、颜色特征、纹理特征,采用中心先验和边缘先验算法,在全面提取显著性区域的同时,能够较好地保留图像的纹理信息和细节信息,使得边缘轮廓更加完整,满足人眼的层次要求和细节要求,并具有一定的适用性。     

Image steganography using deep learning based edge detection

This paper introduces a deep learning-based Steganography method for hiding secret information within the cover image. For this, we use a convolutional neural network (CNN) with Deep Supervision based edge detector, which can retain more edge pixels over conventional edge detection algorithms. Initially, the cover image is pre-processed by masking the last 5-bits of each pixel. The said edge detector model is then applied to obtain a gray-scale edge map. To get the prominent edge information, the gray-scale edge map is converted into a binary version using both global and adaptive binarization schemes. The purpose of using different binarization techniques is to prove the less sensitive nature of the edge detection method to the thresholding approaches. Our rule for embedding secret bits within the cover image is as follows: more bits into the edge pixels while fewer bits into the non-edge pixels. Experimental outcomes on various standard images confirm that compared to state-of-the-art methods, the proposed method achieves a higher payload.

     

An Adaptive Two-Stage Edge Detection Scheme for Digital Color Images

An adaptive two-stage edge detection scheme for digital color images is proposed in this paper. In the first stage of this scheme, each three-dimensional color image is reduced to a one-dimensional gray-level image using the moment-preserving thresholding technique. Then, a new edge detection technique based on the block truncation coding scheme is introduced to detect the edge boundary in the second stage. The edge detection process makes use of the bit plane information of each BTC-encoded block to detect the edge boundary. The experimental results show that the performance of the detected edge image of the proposed scheme is as good as in Yang's scheme and in the Sobel operator. However, the computational cost consumed by the proposed scheme is less than that of Yang's scheme. In addition, the proposed scheme provides an adaptive edge quality decision mechanism. This mechanism can provide different edge images to meet various applications and the subjective evaluation. Moreover, this scheme locates the edge boundaries to the sub-pixel accuracy, which is an advantage to applications such as data hiding and image watermarking.     

结合MNF变换和Canny算子的遥感影像变化检测

针对大面积区域的多时相遥感影像变化检测的需求，提出了一种基于最小噪声分离（MNF）的Canny边缘检测提取影像变化信息的检测方法。对多时相影像采用多种变换组合成具有多维波段信息的影像，采用最小噪声分离法分离噪声并得到单波段差异图，通过Canny边缘检测法计算梯度幅值，采用高低双阈值法细化边缘，从而提取差异图变化边缘，有效突出了变化信息。以1995年和2003年加扎勒河的两期遥感影像为例，利用两时相影像进行土地覆被变化检测。实验结果表明，该方法适用于监测大面积区域内地物的突变情况。在数据基础上进行最小噪声分离可以有效解决传统Canny边缘检测提取边缘时造成的伪边缘现象，同时采用高低双阈值法有效去除伪边缘点，从而获得更加精确、直观的变化检测效果，在自然地理变化监测、地理国情灾害监测等有很好的应用价值。     

基于欧氏距离图的图像边缘检测

图像边缘检测技术直接影响以目标识别为目的的后续图像处理操作,有效地提取出图像中所携带的目标信息是图像边缘检测的主要目的.为了实现目标轮廓的有效提取,提出一种基于欧氏距离图的图像边缘检测算法.该方法计算图像内像素点之间的欧氏距离,得到图像的距离图,距离图很好地描述了图中景物的外部轮廓;对距离图进行改进的Canny算子边缘检测,可以有效地得到图中物体的轮廓.与一般的边缘检测算法相比,本文算法能够抑制过于细小和琐碎的细节,并能够准确地提取目标的整体轮廓信息,为后续目标识别奠定了良好基础.     

基于深度学习的卫星遥感图像边缘检测方法

为解决卫星遥感图像边缘模糊噪点过多,导致图像清晰度过低的问题,提出基于深度学习的卫星遥感图像边缘检测方法;利用Softmax分类器结构,提取边缘图像节点处的数据信息参量,遵循深度学习算法完成对图像信息的卷积与池化处理,基于CV算法实现基于深度学习的卫星遥感图像识别;根据尺度空间定义原则,确定边缘检测特征点所处位置,再联合梯度信息熵计算结果,完成对卫星遥感图像的拼接处理;分别计算一阶微分边缘算子、二阶微分边缘算子的具体数值,确定梯度幅值的取值区间,总结已知数值参量,建立完整的双阈值表达式,完成基于深度学习的卫星遥感图像边缘检测方法的设计;实验结果表明,应用所提方法后卫星遥感图像边缘节点处信噪比指标在55.1～62.7 dB范围内,图像模糊噪点个数最大为1.32×10⁵个,可获得较为清晰的遥感图像,在卫星遥感图像边缘精准检测方面具有较强的实用性。     

基于自适应边缘检测的小波包图像去噪

为了在滤除图像噪声的同时能很好地保持图像的细节，提出了一种基于自适应边缘检测的小渡包图像去噪方法，先用自适应滤波多尺度边缘检测方法检测出图像的边缘，小波包去噪时就可选用全局闽值而不必担心损害图像的边缘特征。实验结果表明，谊方法不但可以保持图像的边缘信息，而且能够提高去噪后图像的信噪比。     

Edge Detection from Non-Uniform Fourier Data Using the Convolutional Gridding Algorithm

Detecting edges in images from a finite sampling of Fourier data is important in a variety of applications. For example, internal edge information can be used to identify tissue boundaries of the brain in a magnetic resonance imaging (MRI) scan, which is an essential part of clinical diagnosis. Likewise, it can also be used to identify targets from synthetic aperture radar data. Edge information is also critical in determining regions of smoothness so that high resolution reconstruction algorithms, i.e. those that do not “smear over” the internal boundaries of an image, can be applied. In some applications, such as MRI, the sampling patterns may be designed to oversample the low frequency while more sparsely sampling the high frequency modes. This type of non-uniform sampling creates additional difficulties in processing the image. In particular, there is no fast reconstruction algorithm, since the FFT is not applicable. However, interpolating such highly non-uniform Fourier data to the uniform coefficients (so that the FFT can be employed) may introduce large errors in the high frequency modes, which is especially problematic for edge detection. Convolutional gridding, also referred to as the non-uniform FFT, is a forward method that uses a convolution process to obtain uniform Fourier data so that the FFT can be directly applied to recover the underlying image. Carefully chosen parameters ensure that the algorithm retains accuracy in the high frequency coefficients. Similarly, the convolutional gridding edge detection algorithm developed in this paper provides an efficient and robust way to calculate edges. We demonstrate our technique in one and two dimensional examples.     

3-D B-spline Wavelet-Based Local Standard Deviation (BWLSD): Its Application to Edge Detection and Vascular Segmentation in Magnetic Resonance Angiography

Extracting reliable image edge information is crucial for active contour models as well as vascular segmentation in magnetic resonance angiography (MRA). However, conventional edge detection techniques, such as gradient-based methods and wavelet-based methods, are incapable of returning reliable detection responses from low contrast edges in the images. In this paper, we propose a novel edge detection method by combining B-spline wavelet magnitude with standard deviation inside local region. It is proved theoretically and demonstrated experimentally in this paper that the new edge detection method, namely BWLSD, is able to give consistent and reliable strengths for edges with different image contrasts. Moreover, the relationship between the size of local region with non-zero wavelet magnitudes and the scale of wavelet function is established. This relationship indicates that if the scale of the adopted wavelet function is s, then the size of a local region, from which the standard deviation is estimated, should be 2s−1. The proposed edge detection technique is embedded in FLUX, namely, BWLSD-FLUX, for vascular segmentation in MRA image volumes. Experimental results on clinical images show that, as compared with the conventional FLUX, BWLSD-FLUX can achieve better segmentations of vasculatures in MRA images under same initial conditions.     

Significant edges in the case of non-stationary Gaussian noise

In this paper, we propose an edge detection technique based on some local smoothing of the image followed by a statistical hypothesis testing on the gradient. An edge point being defined as a zero-crossing of the Laplacian, it is said to be a significant edge point if the gradient at this point is larger than a threshold s(ε) defined by: if the image I is pure noise, then the probability of ∥∇I(x)∥?s(ε) conditionally on ΔI(x)=0 is less than ε. In other words, a significant edge is an edge which has a very low probability to be there because of noise. We will show that the threshold s(ε) can be explicitly computed in the case of a stationary Gaussian noise. In the images we are interested in, which are obtained by tomographic reconstruction from a radiograph, this method fails since the Gaussian noise is not stationary anymore. Nevertheless, we are still able to give the law of the gradient conditionally on the zero-crossing of the Laplacian, and thus compute the threshold s(ε). We will end this paper with some experiments and compare the results with those obtained with other edge detection methods.     

An Improved Method for Edge Detection and Image Segmentation Using Fuzzy Cellular Automata

Image segmentation is one of the most important and challenging problems in image processing. The main purpose of image segmentation is to partition an image into a set of disjoint regions with uniform attributes. In this study, we propose an improved method for edge detection and image segmentation using fuzzy cellular automata. In the first stage, we introduce a new edge detection method based on fuzzy cellular automata, called the texture histogram, and empirically demonstrate the efficiency of the proposed method and its robustness in denoising images. In the second stage, we propose an edge detection algorithm by considering the mean values of the edges matrix. In this algorithm, we use four fuzzy rules instead of 32 fuzzy rules reported earlier in the literature. In the third and final stage, we use the local edge in the edge detection stage to more accurately accomplish image segmentation. We demonstrate that the proposed method produces better output images in comparison with the separate segmentation and edge detection methods studied in the literature. In addition, we show that the method proposed in this study is more flexible and efficient when noise is added to an image.