图像边缘检测方法对比与实现

本文主要针对彩色图像和灰色图像边缘检测的一些方法进行了对比。对于灰色图像根据不同方法的优缺点提出了一种基于数据融合的边缘检测的方法。该方法对原始图像分别采用sobel算子和小波变换两种方法进行边缘提取,然后采用加权平均的方法进行融合并且得到了边界更为清晰的边缘图像;对于彩色图像则分别对比了在RGB彩色空间直接计算梯度得到的边缘图像,以及在分量图像分别计算然后相加得到的梯度图像的边缘效果。     

Color‐edge detection based on discrimination of noticeable color contrasts

Color‐edge detection is an important research task in the field of image processing. Efficient and accurate edge detection will lead to higher performance of subsequent image processing techniques, including image segmentation, object‐based image coding, and image retrieval. To improve the performance of color‐edge detection while considering that human eyes are ultimate receiver of color images, the perceptually insignificant edges should avoid being over‐detected. In this article, a color‐edge detection scheme based on the perceptual color contrast is proposed. The perceptual color contrast is defined as the visible color difference across an edge in the CIE‐Lab color space. A perceptual metric for measuring the visible color difference of a target color pixel is defined by utilizing the associated perceptually indistinguishable region. The perceptually indistinguishable region for each color pixel in the CIE‐Lab color space is estimated by the design of an experiment that considers the local property due to local changes in luminance. Simulation results show that the perceptual color contrast is effectively defined and the color edges in color images are detected while most of the perceptually insignificant edges are successfully suppressed through the proposed color‐edge detection scheme. © 2009 Wiley Periodicals, Inc. Int J Imaging Syst Technol, 19, 332–339, 2009     

基于边缘的标志牌文本提取方法

标志牌上包含了许多重要的信息，提取自然场景图像中标志牌上的文本具有很高的实用价值。本文提出了一种有效的基于边缘的文本提取方法。该方法对背景的复杂度、文字的颜色、大小以及排列方向具有很强的鲁棒性。首先，算法有效地去除大量不规则的非文本长边缘；然后。针对不同的字符大小范围进行分级提取，根据文本区域中边缘之间的关系，用窗口法扫描边缘图像，进一步去除非文本边缘；然后，将提取的结果合并。在验证阶段，本文应用了字符边缘的特点，提高验证的准确率。最后，详细介绍了实验结果。     

Color image sharpening inspired by human vision models

A method to sharpen digital color images that takes viewing conditions and human vision models into consideration is described. The method combines the Laplacian of Gaussian (LoG) operator with spatial filters that approximate the contrast sensitivity functions of human visual systems. The sharpening operation is introduced in the opponent color space, following the scheme proposed in the spatial extension of CIELAB (S-CIELAB). We deduce the modification of the original image necessary to obtain the spatially filtered image that approaches the perceived LoG-sharpened image for given viewing conditions. At short viewing distances, for which the spatial blurring is small, most fine edges and object contours are sharpened. At long distances, for which the spatial blurring is greater, only large figures are sharpened. Because of the smoothing Gaussian functions involved in the LoG operator, the proposed image sharpening does not tend to increase noise. When the sharpening operation is limited to the achromatic channel, the results are good. This is consistent with the high importance attached to the luminance channel in the spatial content of color images. Image sharpening based on only the Laplacian of the original is not sensitive to variations of viewing conditions, tends to increase noise, and suffers from its appearance deteriorating rather quickly with the depth of the sharpening operation.     

基于SPIHT和视觉显著性检测的彩色图像水声信道传输

在学术和工程领域,如何在带宽严重受限的水声信道中获取具有一定可用性的彩色图像一直是一个备受关注的问题。文章提出了一种新的水下彩色图像传输方法,利用基于分级树集合分裂(Set Partitioning in HierarchicalTrees, SPIHT)算法的图像渐进传输和视觉显著性检测,在复杂多变、带宽严重受限的水声信道中获得可用性较好的水下彩色图像。该方法根据信噪比动态调整数据传输方案,并使用红色通道补偿来提高频域中显著性检测的准确性。然后使用 SPIHT 渐进传输图像,并在接收端通过导向滤波解决高降采样率引起的块效应,以获得高质量的水下图像。实验结果表明,所提出的方法在压缩水下彩色图像方面具有一定的适用性。     

Digital Forensics for Recoloring via Convolutional Neural Network

As a common medium in our daily life, images are important for most people to gather information. There are also people who edit or even tamper images to deliberately deliver false information under different purposes. Thus, in digital forensics, it is necessary to understand the manipulating history of images. That requires to verify all possible manipulations applied to images. Among all the image editing manipulations, recoloring is widely used to adjust or repaint the colors in images. The color information is an important visual information that image can deliver. Thus, it is necessary to guarantee the correctness of color in digital forensics. On the other hand, many image retouching or editing applications or software are equipped with recoloring function. This enables ordinary people without expertise of image processing to apply recoloring for images. Hence, in order to secure the color information of images, in this paper, a recoloring detection method is proposed. The method is based on convolutional neural network which is quite popular in recent years. Unlike the traditional linear classifier, the proposed method can be employed for binary classification as well as multiple labels classification. The classification performance of different structure for the proposed architecture is also investigated in this paper.     

闪光CCD图像的中值-非线性扩散滤波

根据闪光CCD图像的特点,提出了一种中值-非线性扩散滤波(Median-NonlinearDiffusionFiltering,简称MNDF)方法。该方法采用中值预滤波来估计图像的真实边缘,通过求解偏微分方程(PartialDifferentialEquation,简称PDE)来进行非线性扩散滤波,充分发挥了中值滤波和非线性扩散滤波的优势,能更好地消除噪声、保护边缘。实验结果表明,在高斯噪声和脉冲噪声同时存在的情况下,MNDF方法取得的滤波效果较P-M方案和Catte方案要好,信噪比改善因子提高3~5倍,均方误差减小1.3~2.7倍。对闪光照相CCD图像取得了很好的消噪声结果,保护了边缘信息。     

一种基于多模式融合的多视点图像颜色校正方法

针对各种多视点成像系统中视点图像颜色不一致的问题,提出了一种基于多模式融合的多视点图像颜色校正方法.该方法通过定义四种通用的线性和非线性校正模式,首先对输入的源图像和参考图像进行视差估计,以视差估计得到的匹配块作为样本,然后对样本分别用四种校正模式进行训练,得到各种模式的校正参数,最后基于最小均方误差准则对各种校正模式进行融合,得到最终的校正图像.实验结果表明,该方法能实现参考图像与校正图像的最小均方根误差,且具有较好的校正效果.     

保持边缘的SAR图像滤波方法

首先阐明了SAR图像边缘和边缘保持的概念。其次，提出了一种评价平滑图像边缘保持的方法。通过计算发现，常用的标准滤波方法：增强Lee滤波、Kuan滤波、增强Frost滤波和Gamma MAP滤波的边缘保持能力很差。最后发展了一种能保持边缘的SAR图像滤波方法。这种方法是对Han等人去除SAR图像斑点噪声方法的改进，并分析了这种方法能够保持图像边缘的原因。     

Color Image Steganalysis Based on Residuals of Channel Differences

This study proposes a color image steganalysis algorithm that extracts high-dimensional rich model features from the residuals of channel differences. First, the advantages of features extracted from channel differences are analyzed, and it shown that features extracted in this manner should be able to detect color stego images more effectively. A steganalysis feature extraction method based on channel differences is then proposed, and used to improve two types of typical color image steganalysis features. The improved features are combined with existing color image steganalysis features, and the ensemble classifiers are trained to detect color stego images. The experimental results indicate that, for WOW and S-UNIWARD steganography, the improved features clearly decreased the average test errors of the existing features, and the average test errors of the proposed algorithm is smaller than those of the existing color image steganalysis algorithms. Specifically, when the payload is smaller than 0.2 bpc, the average test error decreases achieve 4% and 3%.     

Using color histogram normalization for recovering chromatic illumination-changed images.

We propose a novel image-recovery method using the covariance matrix of the red-green-blue (R-G-B) color histogram and tensor theories. The image-recovery method is called the color histogram normalization algorithm. It is known that the color histograms of an image taken under varied illuminations are related by a general affine transformation of the R-G-B coordinates when the illumination is changed. We propose a simplified affine model for application with illumination variation. This simplified affine model considers the effects of only three basic forms of distortion: translation, scaling, and rotation. According to this principle, we can estimate the affine transformation matrix necessary to recover images whose color distributions are varied as a result of illumination changes. We compare the normalized color histogram of the standard image with that of the tested image. By performing some operations of simple linear algebra, we can estimate the matrix of the affine transformation between two images under different illuminations. To demonstrate the performance of the proposed algorithm, we divide the experiments into two parts: computer-simulated images and real images corresponding to illumination changes. Simulation results show that the proposed algorithm is effective for both types of images. We also explain the noise-sensitive skew-rotation estimation that exists in the general affine model and demonstrate that the proposed simplified affine model without the use of skew rotation is better than the general affine model for such applications.     

彩色图像的复变函数模型及其边缘检测

本文在彩色图像的HSI颜色空间中,根据其分量的不相关特性,针对H、S分量建立了彩色图像的复变函数模型,并给出其边缘检测方法,得到H、S分量的边缘图像.抽取彩色图像的1分量构造灰度图像,利用当前成熟的灰度边缘检测方法(基于小波的多尺度边缘检测方法)得到1分量的边缘图像.最后,利用信息融合技术,将上述获得的两幅边缘图像进行信息组合得到最终的边缘检测结果.从试验的结果来看,本文所采用的方案充分利用了彩色图像所包含的信息,对图像的彩色边缘比较敏感,获得了满意的边缘检测结果.     

Color image denoising using evolutionary computation

Noise suppression in multichannel data sets, such as color images, has drawn much attention in the last few years. An issue of paramount importance in designing color image filters is the determination of the coefficients that should be used to weight the inputs to the filter. In this study, we propose an evolutionary computation‐based approach to select and optimize the coefficients in the class of weighted vector directional filters. Using a genetic algorithm, we were able to adapt the filter weights to match varying image and noise characteristics. Extended experimentation with realistic image processing applications, including television image enhancement and virtual restoration of artworks, indicates that the proposed filters are capable of removing noise while preserving chromaticity information, edges, and fine details, as well as structural image content. © 2006 Wiley Periodicals, Inc. Int J Imaging Syst Technol, 15, 236–251, 2005     

Efficient edge-directed deblocking algorithm for KOMPSAT-2 satellite images

In this paper, we present a deblocking algorithm that removes grid and staircase artefacts, which result from the compression of images. The KORea Multi-Purpose SATellite-2 images are efficiently compressed using an algorithm that assigns quantisation coefficients, by rows, according to local region complexity, in such a way that more complicated regions are more compressed. However, this approach is problematic in that it produces blocking artefacts in those relatively less complicated areas within the same row as the complicated regions. Removing these artefacts with a general deblocking algorithm can, undesirably, blur the complicated regions as well as the artefacts; additionally, the general filter is poor at preserving curved edges. Therefore, the algorithm proposed herein presents an adaptive filtering scheme for removing blocking artefacts while preserving image details, including curved edges, using a content analysis. Particularly, edge adaptive filtering has been introduced to remove staircase artefacts around the big image edges. Experimental analyses revealed that the proposed method outperforms several state-of-the-art approaches in terms of subjective or objective image quality, and computational speed.     

一种新的彩色图像碎片全自动拼接算法

目的为了实现横向和纵向分切的彩色图像碎片的拼接,提出针对同一张经过横向和纵向分切的彩色图像碎片建立关于相关系数的拼接复原模型和算法。方法通过获取彩色图像碎片的各单色图像,并提取单色图像边缘的灰度值,根据图像碎片边缘灰度值之间的相似程度自动拼接碎片。结果文中算法对彩色图像碎片的拼接效果优于常规算法,实验中采用100张彩色图,对每张彩图分切成64张300×300像素的彩图碎片进行顺序复原,综合拼接成功率达到100%,拼接平均耗时1.59 s。此外,文中算法实验性强,不仅能拼接仅纵切的图像,还能拼接横向和纵向分切的彩色图像。结论实验结果表明该算法对彩色图像碎片的拼接具有很好的适应性和可重复性,对图像碎片的大小和颜色无严格要求,是一套完整有效的针对规则彩色图像碎片的全自动拼接方案。     

一种基于YC-rC-b颜色空间和视觉特性的彩色图像水印技术

根据图像离散余弦变换频谱图特征及结合人眼对亮度和颜色的对比度敏感视觉特性,提出了一种人眼感知图像最小误差即JND阈值的计算方法,通过计算出的JND阈值,提出了一种基于YCrCb颜色空间的彩色图像水印技术方案。方案依据JND阈值筛选彩色图像的3个分量亮度图变换域频谱系数来进行水印的嵌入和提取。从水印技术方案上看,JND阈值的引入使得水印的嵌入达到最大;嵌入算法使得水印嵌入的位置具有随机性,有力地保证了水印信息的安全性。仿真实验和攻击测试表明:含水印图经压缩攻击后的图像与原始图像基本一样,提取的水印信息与原始水印基本相同;攻击后的含水印图具有较好的透明性和较高的鲁棒性。提出的基于YCrCb颜色空间和人眼视觉特性的彩色图像水印技术方案,是一种可行的、较好的彩色图像技术。     

Median-prior tomography reconstruction combined with nonlinear anisotropic diffusion filtering

Positron emission tomography (PET) is becoming increasingly important in the fields of medicine and biology. Penalized iterative algorithms based on maximum a posteriori (MAP) estimation for image reconstruction in emission tomography place conditions on which types of images are accepted as solutions. The recently introduced median root prior (MRP) favors locally monotonic images. MRP can preserve sharp edges, but a steplike streaking effect and much noise are still observed in the reconstructed image, both of which are undesirable. An MRP tomography reconstruction combined with nonlinear anisotropic diffusion interfiltering is proposed for removing noise and preserving edges. Analysis shows that the proposed algorithm is capable of producing better reconstructed images compared with those reconstructed by conventional maximum-likelihood expectation maximization (MLEM), MAP, and MRP-based algorithms in PET image reconstruction.     

一种新的用于图象拼接的颜色融合方法

基于图象的虚拟现实是实现虚现实系统的一种新方法，对于该方法而言，全景图的制作是至关重要的，全景图制作中的一项关键技术是颜色融合，即在接接图象时，如何使颜色能平滑过度，对此，本文提出了一种基于塔形结构的颜色融合算法，首先，它将图象分解成一组带通图象，然后在第五个频率带内使用没的加权函数进行颜色融合。在每一个频率带内，加权函数的系数以及颜色融合区域的大小，是由两幅图象的图象特征在该频率带内的差异决定的     

Integrated color defect detection method for polysilicon wafers using machine vision

For the typical color defects of polysilicon wafers,i.e.,edge discoloration,color inaccuracy and color non-uniformity,a new integrated machine vision detection method is proposed based on an HSV color model.By transforming RGB image into three-channel HSV images,the HSV model can efficiently reduce the disturbances of complex wafer textures.A fuzzy color clustering method is used to detect edge discoloration by defining membership function for each channel image.The mean-value classifying method and region growing method are used to identify the other two defects,respectively.A vision detection system is developed and applied in the production of polysilicon wafers.     

基于支持向量机分类策略的多晶硅电池片色差检测

针对复杂颜色和纹理特征条件下,多晶硅电池片上的色差检测问题,提出了一种基于支持向量机分类策略的多晶硅电池片色差检测方法。首先对预处理后电池片图像进行颜色模型转换和通道分离,利用Otsu方法对单通道图像进行阈值分割处理,并计算各阈值图像的区域对比度,然后根据区域对比度情况选择合适的阈值图像,利用阈值图像所提供的信息提取图像特征;最后使用支持向量机分类器来判别电池片是否存在色差缺陷。实验结果表明提出的色差检测算法可以实现多晶硅电池片色差高效检测,色差缺陷检测的准确度、误检率和检测时间分别达到96.88%, 5％和109ms。