基于神经网络的图像边缘检测方法

提出了一种基于神经网络的图像边缘检测新方法.该方法首先基于邻域灰度极值提取边界候选图像,然后以边界候选象素及其邻域象素的二值模式作为样本集,输入边缘检测神经网络进行训练.边缘检测神经网络采用BP网络,为加快网络的训练速度,采用了滚动训练和权值随机扰动的方法.实验表明,该方法提高了神经网络的学习效率,获得的边缘图像封闭性好,边缘描述真实.     

Vision-based edge detection between plant column and soil of ningxia lycium barbarum garden

ABSTRACT

The cultivation of Lycium barbarum (L.barbarum) is a highly traditional and advantageous industry in Ningxia, China, and has strong development prospects. At present, the protection, fertilization, picking, and other production aspects of L.barbarum are generally inefficient and labor intensive, presenting a bottleneck that restricts the development of the industry. Developing intelligent production equipment in the form of a ‘general self-moving host platform + operation module’ is an urgent task for the healthy development of the L.barbarum industry. A self-planning, self-organizing, host platform must be able to perform adaptive navigation in complex unstructured environments. For this purpose, a method of edge detection that can distinguish between the plant column and soil is required. Using a color difference model with Otsu’s method for image segmentation, a corrected gradient image based on the marking method is employed to remove small noise regions and then perform edge detection. Experiments demonstrate that one particular color model offers strong adaptability for light and shadow, which is good for distinguishing between the plant column and soil. The proposed method can effectively detect the edges between the plant column and soil, laying the foundation for detecting a suitable path for a self-moving platform and visual navigation.     

基于拉普拉斯金字塔分解的多尺度边缘检测

边缘表现为图像中具有奇异性点的集合,利用改进的拉普拉斯金字塔分解捕获这些奇异性点,得到各尺度下的带通图像,通过分析,得出分解后的带通图像在边缘处产生零交叉点,构造统计量帮助提取零交叉点,再通过多尺度边缘融合实现多尺度边缘提取.与LOG和Canny边缘检测的对比实验表明,所建立的算法能够可靠、有效、精确的获得图像的边缘.     

基于Daubechies小波的图像边缘检测技术

利用Daubechies正交小波变换的性质,通过Mallat多尺度分析方法对图像进行小波变换,把图像分解成低频轮廓,水平高频、垂直高频和斜线高频四个部分。针对图像边缘主要集中在高频部分,该文先保持小波变换后的高频小波系数,同时对低频小波系数进行再次小波变换,提取出次高频信号的边缘信息。最后对保留下来的高频小波系数和次高频小波系数进行逆变换获取最大边缘信息。     

Color edge detection using multiscale quaternion convolution

This article presents a novel color edge detection algorithm based on quaternion convolution. A set of multiscale quaternion masks are presented, and the filtered results are multiplied at adjacent scales using dot product to enhance the edge structures while diluting noise. Experimental results show that the proposed method is efficient and robust for color images. © 2010 Wiley Periodicals, Inc. Int J Imaging Syst Technol, 20, 354–358, 2010     

基于边缘矢量的镰刀弯在线检测方法研究

针对热连轧车间里带钢的镰刀弯检测问题,提出一种基于机器视觉的镰刀弯在线检测方法.首先,对预处理后的图像采用图像二值化处理提取目标,再使用形态学运算消除目标上的杂质以及不连通区域.然后在图像中以图像的中心点像素作为原点建立坐标系,提取中间坯两侧边缘点,接着获取相邻点之间的向量,并进行单位绝对值化,计算相邻单位向量之间的关...     

Edge‐adaptive color interpolation for complementary color filter array

Complementary color filter array (CCFA) is widely used in consumer‐level digital video cameras, since it not only has high sensitivity and good signal‐to‐noise ratio in low‐light condition but also is compatible with the interlaced scanning used in broadcast systems. However, the full‐color images obtained from CCFA suffer from the color artifacts such as false color and zipper effects. These artifacts can be removed with edge‐adaptive color interpolation (ECI) approaches which are generally used in primary color filter array (PCFA). Unfortunately, the unique array pattern of CCFA makes it difficult that CCFA adopts ECI approaches. Therefore, to apply ECI approaches suitable for CCFA to color interpolation is one of the major issues to reconstruct the full‐color images. In this paper, we propose a new ECI algorithm for CCFA. To estimate an edge direction precisely and enhance the quality of the reconstructed image, a function of spatial variances is used as a weight, and new color conversion matrices are presented for considering various edge directions. Experimental results indicate that the proposed algorithm outperforms the conventional method with respect to both objective and subjective criteria. © 2006 Wiley Periodicals, Inc. Int J Imaging Syst Technol, 16, 92–102, 2006     

A sub-pixel edge detection algorithm based on Zernike moments

Abstract

A novel hybrid technique of combining an improved morphological gradient operator and Zernike moments, named MGZ edge detection algorithm, is developed to meet the stringent requirements for measuring accuracies of charge coupled device metrology system. The mathematical morphological gradient and Zernike moment algorithm are discussed based on the pixels grey-scale and spatial structure information of the images. To improve the algorithm process, the image edge is oriented and extracted by using improved morphological gradient operator firstly; then, the calculation errors of the typical ideal step edge model are analysed and corrected by the proposed error compensation formula. The edge point is relocated with sub-pixel accuracy by means of Zernike moment operator based on the edge point vectors and the threshold value. Finally, the sub-pixel edge detecting of the image is attained. The extensive experimental results show that the measuring error of the edge point is compensated reliably and accurately, and the new algorithm has short operation time, more precise and stronger robustness to noise than the prior similar algorithms. Meanwhile, the proposed method can well meet the need of charge coupled device metrology system for sub-pixel edge detection.     

关于图像边缘检测的 Laplace算子的改进

该文对图像边缘检测的 L aplace模板 ,增加 8个检测方向 ,并适当设置了权系数 ,改进了 Laplace算子 ,实验结果表明使用改进的 Laplace算子 ,图像边缘检测的效果得到了明显的改善 .     

Addressable and Color‐Tunable Piezophotonic Light‐Emitting Stripes

Piezophotonic light‐emitting devices have great potential for future microelectromechanical systems (MEMS) and nanoelectromechanical systems (NEMS) due to the added functionality provided by the electromechanical transduction coupled with the ability of light emission. Piezophotonic light‐emitting source based on Pb(Mg_1/3Nb_2/3)O₃–PbTiO₃ (PMN–PT) bulk is severely restricted by many challenges, such as high voltage burden, low integration density, and micromanufacturing complexity. Developing chip‐integrated devices or incorporating such photonic components onto a Si platform is highly sought after in this field. In this work, the authors overcome the abovementioned problems by introducing single‐crystal PMN–PT thin films on Si as central active elements. Taking advantage of mature microfabrication techniques, arrays of PMN–PT actuators with small footprints and low operation voltages have been implemented. Each actuator can be individually addressed, generating local deformation to trigger piezophotonic luminescence from ZnS:Mn thin films. Moreover, the authors have realized continuous and reversible color manipulation of piezophotonic luminescence on a bilayer film of ZnS:Cu,Al/ZnS:Mn. The color tunability promises an extra degree of freedom and distinctly suggests its great potential in developing a more compact and colorful piezophotonic light sources and displays related applications together with the “single pixel” addressability.     

基于肤色特征和动态聚类的彩色人脸检测

在人类视觉机制和肤色聚类特性的基础上,提出了一种复杂背景下人脸检测方法。该方法采用K-均值动态聚类分析算法,利用人类肤色特征在输入图像中检测包含人脸的似人脸区作为候选人脸,再用同样的方法对候选人脸区域进行扫描,得到真正的人脸。实验结果表明,该方法的正确检出率达到84%,受背景、光照、角度、姿态的影响很小,具有较好的鲁棒性。     

基于变差函数的噪声图像的多尺度边缘检测

基于区域化变量理论,针对受噪声污染的图像,本文提出了一种基于变差函数的多尺度边缘检测新方法.该方法根据图像各个不同区域的数据的不同方向的变差函数值来判断该区域是否存在边缘以及边缘的方向性,然后根据该区域边缘的方向性,在水平和垂直方向分别进行不同尺度的小波变换,进而达到在确保边缘定位准确的同时,尽最大可能去除由于噪声以及图像灰度不均匀产生的伪边缘点.仿真实验表明,本文算法在对受高斯白噪声污染较严重的图像进行边缘检测时能有效的去除噪声对图像边缘检测的影响,从而证明了该方法的可行性、有效性.     

Effect of the Nanodiamond Host on a Nitrogen‐Vacancy Color‐Centre Emission State

Control over the quantum states of individual luminescent nitrogen‐vacancy (NV) centres in nanodiamonds (NDs) is demonstrated by careful design of the crystal host: its size, surface functional groups, and interfacing substrate. By progressive etching of the ND host, the NV centres are induced to switch from latent, through continuous, to intermittent or “blinking” emission states. The blinking mechanism of the NV centre in NDs is elucidated and a qualitative model proposed to explain this phenomenon in terms of the centre electron(s) tunnelling to acceptor site(s). These measurements suggest that the substrate material and its proximity to the NV are responsible for the fluorescence intermittency.     

彩色印刷品缺陷在线检测方法的研究与探讨

介绍彩色印刷品图像在线检测的基本流程.探讨相比于灰度图像缺陷在线检测的几个关键技术,对彩色印刷图像颜色缺陷在线检测提出一些新思路.     

A snake‐based approach to automated segmentation of tongue image using polar edge detector

Tongue diagnosis, one of the most important diagnosis methods of Traditional Chinese Medicine, is very competitive as a candidate of remote diagnosis method because of its simplicity and noninvasiveness. Recently, considerable research interests have been given to the development of automated tongue segmentation technologies, which is difficult due to the complexity of pathological tongue, variance of tongue shape, and interference of the lips. In this paper, we propose a novel automated tongue segmentation method via combining polar edge detector and active contour model (ACM) technique. First, a polar edge detector is presented to effectively extract the edge of the tongue body. Then we design an edge filtering scheme to avoid the adverse interference from the nontongue boundary. After edge filtering, a local adaptive edge bi‐thresholding algorithm is introduced to perform the edge binarization. Finally, a heuristic initialization and an ACM are proposed to segment the tongue body from the image. The experimental results demonstrate that the proposed method can segment the tongue body accurately and effectively. A quantitative evaluation on 200 images indicates that the normalized mean distance to the closest point is 0.48%, and the average true positive percent of our method is 97.1%. © 2007 Wiley Periodicals, Inc. Int J Imaging Syst Technol, 16, 103–112, 2006.     

新的梯度边缘检测方法

提出了一种新的基于梯度算子法检测灰度图像边缘的方法。该方法在3×3的邻域窗内,分别用梯度法对窗内的水平方向、垂直方向和正、负45°角方向上的边缘线进行检测,找到梯度最大的边缘线,从而组成最终的边缘图像。实验表明:该方法简单,边缘检测图像效果好。在此基础上,又提出了增强边缘检测方法和简化边缘检测方法。这两种对基于梯度算子法的改进方法分别适用于检测小的边缘梯度和需要快速检测边缘这两种情况。