基于最大目标函数的医学图像边缘检测

鉴于医学图像特点和传统算法的缺点,提出一种新的医学图像边缘检测算法,该算法通过考察3×3模板的理想边缘结构特征,将模板像素沿边缘方向分为两个集合,通过距离度量函数构造适当的目标函数,计算四个方向的目标函数值,从而获得最大目标函数值,并与给定的阈值比较,应用非极大抑制方法,判别该象素是否为边缘点,最后进行双阈值连接,可得到单像素边缘图像。仿真结果表明,该算法能够有效检测医学图像边缘,所检测出的图像边缘细节丰富,单像素宽,定位准确。     

Heterogeneous face matching using geometric edge-texture feature (GETF) and multiple fuzzy-classifier system

A novel and accurate method for matching of heterogeneous faces, such as sketch and near-infrared (NIR) images, with the visible (VIS) photo gallery and vice a versa has been presented here. A new geometric edge-texture feature (GETF) is proposed, which is not only able to capture the edge information but also the texture information. GETF is constructed from the combined information of edge and texture image of same individual. For texture information local binary pattern (LBP) is used, while for edge information canny edge detection is chosen. Edges are sensitive to illumination, so before applying canny edge operation, we convert the image into illumination invariant gradient domain. For each pixel of the edge image, the nearest edge pixel is found. Finally, the total hamming distance between any pixel and its nearest edge pixel of the corresponding texture image gives GETF_Dist and the angle between them gives the GETF_Ang feature. To classify the heterogeneous faces we proposed a multiple fuzzy-classifier system, which is a combination of fuzzy partial least square (FPLS) and fuzzy local feature-based discriminant analysis (FLFDA). We have tested statistically that, the proposed classifier performs better than the individual classifiers. In sketch-photo matching, a rank-1 accuracy of 99.66% is achieved in a gallery of 606 photos consisting of CUHK student dataset, AR face dataset, and XM2VTS dataset. In NIR–VIS image matching, a rank-1 accuracy of 99.50% is achieved in a gallery of 400 VIS images from CASIA-HFB dataset.     

Gibbs artifact reduction for POCS super-resolution image reconstruction

The topic of super-resolution image reconstruction has recently received considerable attention among the research community. Super-resolution image reconstruction methods attempt to create a single high-resolution image from a number of low-resolution images (or a video sequence). The method of projections onto convex sets (POCS) for super-resolution image reconstruction attracts many researchers’ attention. In this paper, we propose an improvement to reduce the amount of Gibbs artifacts presenting on the edges of the high-resolution image reconstructed by the POCS method. The proposed method weights the blur PSF centered at an edge pixel with an exponential function, and consequently decreases the coefficients of the PSF in the direction orthogonal to the edge. Experiment results show that the modification reduces effectively the visibility of Gibbs artifacts on edges and improves obviously the quality of the reconstructed high-resolution image.     

纹理边缘引导的深度图像超分辨率重建

目的 深度图像作为一种普遍的3维场景信息表达方式在立体视觉领域有着广泛的应用。Kinect深度相机能够实时获取场景的深度图像,但由于内部硬件的限制和外界因素的干扰,获取的深度图像存在分辨率低、边缘不准确的问题,无法满足实际应用的需要。为此提出了一种基于彩色图像边缘引导的Kinect深度图像超分辨率重建算法。方法 首先对深度图像进行初始化上采样,并提取初始化深度图像的边缘;进一步利用高分辨率彩色图像和深度图像的相似性,采用基于结构化学习的边缘检测方法提取深度图的正确边缘;最后找出初始化深度图的错误边缘和深度图正确边缘之间的不可靠区域,采用边缘对齐的策略对不可靠区域进行插值填充。结果 在NYU2数据集上进行实验,与8种最新的深度图像超分辨率重建算法作比较,用重建之后的深度图像和3维重建的点云效果进行验证。实验结果表明本文算法在提高深度图像的分辨率的同时,能有效修正上采样后深度图像的边缘,使深度边缘与纹理边缘对齐,也能抑制上采样算法带来的边缘模糊现象;3维点云效果显示,本文算法能准确区分场景中的前景和背景,应用于3维重建等应用能取得较其他算法更好的效果。结论 本文算法普遍适用于Kinect深度图像的超分辨率重建问题,该算法结合同场景彩色图像与深度图像的相似性,利用纹理边缘引导深度图像的超分辨率重建,可以得到较好的重建结果。     

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。     

基于局部尺度控制的模糊边缘检测算法

基于容错思想定位边缘是为了解决自然图像中难以获取典型边缘特征的前后景相融处的模糊边缘定位问题,它为图像的每一点建立唯一的、局部可计算的最小可靠尺度以对模糊边缘定位并提取。文中对算法中求图像二阶导数时每个像素点都要沿着各自梯度方向确定卷积模板计算各像素点二阶导数的过程进行简化分析。通过将局部尺度判定与LoG算法相结合,避免各梯度方向上所进行的繁琐的二阶导数运算,并提出一个近似确定零交叉点位置的模糊边缘判别和定位流程。详细分析算法的可行性,对比多种算法对3类不同程度模糊的典型图像的边缘定位效果。实验表明,该算法对模糊边缘的定位和提取效果更好,运算速度更快,算法更实用。     

采用积分图块间距离检测图像边缘

目的 边缘是图像的重要特征之一,是后续测量、基于形状配准的基础,为了更好地获得图像中的边缘信息,提出一种利用积分图块间距离检测图像边缘的方法。方法 首先,分析欧氏距离图理论,给出采用局部区块内和距离的方式检测图像边缘的方法。其次,提出采用积分图完成高斯模板块内求和算法,并利用这种方法加速完成了图像块内像素求和,以此提高算法的执行速度。最后,给出了本文算法的执行流程。结果 以人工标注模拟图像的边缘为标准,采用本文方法得到的边缘检测结果重叠率高于97%,Canny算法的重叠率为80%、高斯曼哈顿距离与欧式距离算法的重叠率分别低于63%和28%。从真实图像实验结果上看,随着图像尺寸的增加,Canny与本文方法的执行时间均略有增加,但幅度不大,在处理1024×768的图像时分别耗时1.7 s与4.6 s。由于本文方法增加了积分图及块内和的求解,因此耗时略高于Canny方法。综上,采用本文方法获得的边缘检测结果不仅具备较高的重叠率,而且执行时间较少,其执行速度不会随图像尺寸的增加而大幅度降低。结论 由实验结果可见,本文提出的图像边缘检测方法具备较高的准确性与实用性。由于本文方法具备较高的执行速度,因此适用于所有以边缘检测结果为基础的后期图像处理技术,包括对于实时性要求较高的视频流边缘检测与分析。     

A scheme for edge-based multi-focus Color image fusion

In this paper, a novel region-based multi-focus color image fusion method is proposed, which employs the focused edges extracted from the source images to obtain a fused image with better focus. At first, the edges are obtained from the source images, using two suitable edge operators (Zero-cross and Canny). Then, a block-wise region comparison is performed to extract out the focused edges which have been morphologically dilated, followed by the selection of the largest component to remove isolated points. Any discontinuity in the detected edges is removed by consulting with the edge detection output from the Canny edge operator. The best reconstructed edge image is chosen, which is later converted into a focused region. Finally, the fused image is constructed by selecting pixels from the source images with the help of a prescribed color decision map. The proposed method has been implemented and tested on a set of real 2-D multi-focus image pairs (both gray-scale and color). The algorithm has a competitive performance with respect to the recent fusion methods in terms of subjective and objective evaluation.

     

A knowledge-based neural network for fusing edge maps of multi-sensor images

With the goal of fusion prescribed as building an edge map that contains as many edges as possible from the given multi-spectral/sensor images, a new fusion scheme, called the knowledge-based neural network fusion (KBNNF), is proposed to fuse edge maps of these images in order to generate a combined edge map that has more complete and reliable edge information than what one can obtain from any single image.The KBNNF is used to fuse edge maps of images having mutually complementary edge information in the following sense: (i) the edges in the images are compatible, i.e., can be interpreted together; and (ii) the edges in the different images reveal different parts of the scene. More complete edge contours of the same object are obtained by linking the edge sections obtained from different images together. The resulting edge map can be used for subsequent study (like object recognition).The proposed scheme bases its confidence and reliability on the analysis of variance (ANOVA)-based edge detector that can address two important issues of edge based image fusion well: (i) the difference in edge position among the images because of the different characteristics of the images and the error in the image registration process; and (ii) the variance existing among the edge test values calculated from different images. The KBNNF has been applied to fuse: (i) radar (SAR)–optical (SPOT), (ii) optical–optical, (iii) infrared–infrared, and (iv) optical–infrared (satellite) image combinations. Comparisons are made with the relevant existing techniques in the literature. The paper concludes with some examples to illustrate the efficacy of the proposed scheme.     

结合相位一致与全变差模型的高分辨率遥感图像边缘检测

目的边缘检测是有效利用遥感数据开展地物目标自动识别的重要步骤。高分辨率遥感图像地物类型复杂,细节信息过于丰富,使得基于相位一致的边缘检测结果中存在过多的噪声与伪边缘。为此提出了一种结合相位一致与全变差模型的高分辨率遥感图像边缘检测方法。方法根据相位一致原理,应用Log Gabor构造的2维相位一致模型,引入全变差去噪模型对基于相位一致的边缘强度图进行改进。结果借助有界变差空间对图像光滑性的约束,实现了高分辨率遥感图像噪声去除与伪边缘抑制,利用改进后的相位一致边缘强度图可有效检测高分辨率遥感图像的边缘。结论实验结果表明,与相位一致模型、Canny算法相比,该方法能消除了高分辨率遥感图像中同类地物内部细节特征形成的噪声,抑制相位一致边缘检测结果中的伪边缘,突出地物的真实边缘,并能正确地提取地物目标的整体轮廓信息,有助于后续地物目标的自动识别。     

基于边缘自相似特征的遥感图像边缘检测算法

据分形理论可知，物体或物体各组成部分的边缘应具有自似性，图像边缘上的像素应具有较大的灰度化值和自相似系数。本基于这种思想，提出了一种结合边缘自相似特征和图像灰度梯度变化进行边缘检测的新算法，并利用该算法对试验图像进行了边缘检测试验。试验结果表明，该算法有效地提取图像边缘，且对含有噪声的遥感图像仍能提取较为丰富的边缘细节，具有一定的抗噪声性能。这对于含有噪声的遥感图像边缘所取与检测，尤其是雷达遥感图像，具有一定的实用价值。     

Gibbs artifact reduction for POCS super-resolution image reconstruction

The topic of super-resolution image reconstruction has recently received considerable attention among the research community. Super-resolution image reconstruction methods attempt to create a single high-resolution image from a number of low-resolution images (or a video sequence). The method of projections onto convex sets (POCS) for super-resolution image reconstruction attracts many researchers’ attention. In this paper, we propose an improvement to reduce the amount of Gibbs artifacts presenting on the edges of the high-resolution image reconstructed by the POCS method. The proposed method weights the blur PSF centered at an edge pixel with an exponential function, and consequently decreases the coefficients of the PSF in the direction orthogonal to the edge. Experiment results show that the modification reduces effectively the visibility of Gibbs artifacts on edges and improves obviously the quality of the reconstructed high-resolution image.     

消除图像伪轮廓的各向异性自适应滤波

摘要：目的：图像反差增强、重复量化、有损压缩等操作容易造成伪轮廓瑕疵,使原本平滑的区域呈现不真实的亮度和颜色跳变,损害图像质量。针对这一问题提出一种各向异性自适应滤波方法,用于消除伪轮廓．方法：首先检测图像中的边缘和平坦区,若边缘位于平坦区域则判定其为伪轮廓,得到一幅伪轮廓分布图．对伪轮廓上每一点计算两个特性：伪轮廓走向和分布密度,量化为8个方向和6种尺度,据此确定不同方向特性和不同尺度的滤波参数,选择相应的滤波器．为保护目标边缘不受损伤,在含有伪轮廓的图像中提取强度超过指定阈值的边缘,对其进行膨胀生成模板用以屏蔽滤波效果．结果：该方法能有效消除伪轮廓并保护真实边缘不受损伤。实验中采用峰值信噪比（PSNR）和结构相似度（SSIM）评估图像质量,结果表明,各向异性自适应滤波器特性优于其他方法．结论：消除伪轮廓的自适应图像滤波方法能消除因过度增强或不当量化造成的伪轮廓瑕疵,并保留真实边缘,提高图像的视觉质量.     

引入欧氏距离的各向异性扩散相干斑抑制

目的 相干斑噪声严重影响SAR影像解译。抑制相干斑同时,获取较好的边缘保持效果始终是相干斑抑制的重点。针对该问题,提出一种引入欧氏距离的各向异性扩散（EDAD）相干斑抑制方法。方法 EDAD算法以P-M模型与SRAD算法为基础,利用邻近像素间区域欧氏距离代替原有边缘检测算子,自适应区分同质区与异质区,有效构造各向异性扩散系数,完成相干斑抑制。结果 运用EDAD算法与现存各向异性扩散算法对截取的两景TanDEM-X影像进行试验研究并比较各类算法的评估参数。EDAD算法的等效视数分别为3.996与5.859,均高于其他算法,体现优越的相干斑抑制能力;EDAD算法相干斑抑制前后比值影像的均值分别为0.999与1.001,方差分别为0.270与0.269,较其他算法均更接近理想值1与0.273,展现更优边缘保持与相干斑抑制能力。结论 本文算法可有效提高边缘检测能力,获取更优相干斑抑制效果。经验证,对分布较散的弱相干斑区域与分布较集中的强相干斑区域均有较好适用性。     

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.     

动态生成掩膜弱监督语义分割

目的 传统图像语义分割需要的像素级标注数据难以大量获取,图像语义分割的弱监督学习是当前的重要研究方向。弱监督学习是指使用弱标注样本完成监督学习,弱标注比像素级标注的标注速度快、标注方式简单,包括散点、边界框、涂鸦等标注方式。方法 针对现有方法对多层特征利用不充分的问题,提出了一种基于动态掩膜生成的弱监督语义分割方法。该方法以边界框作为初始前景分割轮廓,使用迭代方式通过卷积神经网络（convolutional neural network,CNN） 多层特征获取前景目标的边缘信息,根据边缘信息生成掩膜。迭代的过程中首先使用高层特征对前景目标的大体形状和位置做出估计,得到粗略的物体分割掩膜。然后根据已获得的粗略掩膜,逐层使用CNN 特征对掩膜进行更新。结果 在Pascal VOC（visual object classes） 2012 数据集上取得了78.06% 的分割精度,相比于边界框监督、弱—半监督、掩膜排序和实例剪切方法,分别提高了14.71%、4.04%、3.10% 和0.92%。结论 该方法能够利用高层语义特征,减少分割掩膜中语义级别的错误,同时使用底层特征对掩膜进行更新,可以提高分割边缘的准确性。     

SEDMI: Saliency based edge detection in multispectral images

Detecting edges in multispectral images is difficult because different spectral bands may contain different edges. Existing approaches calculate the edge strength of a pixel locally, based on the variation in intensity between this pixel and its neighbors. Thus, they often fail to detect the edges of objects embedded in background clutter or objects which appear in only some of the bands.We propose SEDMI, a method that aims to overcome this problem by considering the salient properties of edges in an image. Based on the observation that edges are rare events in the image, we recast the problem of edge detection into the problem of detecting events that have a small probability in a newly defined feature space. The feature space is constructed by the spatial gradient magnitude in all spectral channels. As edges are often confined to small, isolated clusters in this feature space, the edge strength of a pixel, or the confidence value that this pixel is an event with a small probability, can be calculated based on the size of the cluster to which it belongs.Experimental results on a number of multispectral data sets and a comparison with other methods demonstrate the robustness of the proposed method in detecting objects embedded in background clutter or appearing only in a few bands.     

Facial feature detection using distance vector fields

A novel method for eye and mouth detection and eye center and mouth corner localization, based on geometrical information is presented in this paper. First, a face detector is applied to detect the facial region, and the edge map of this region is calculated. The distance vector field of the face is extracted by assigning to every facial image pixel a vector pointing to the closest edge pixel. The x and y components of these vectors are used to detect the eyes and mouth regions. Luminance information is used for eye center localization, after removing unwanted effects, such as specular highlights, whereas the hue channel of the lip area is used for the detection of the mouth corners. The proposed method has been tested on the XM2VTS and BioID databases, with very good results.     

结合小波滤波和形态学的图像边缘检测方法

针对传统的边缘检测方法对含噪图像检测效果不理想,提出了一种小波滤波和多结构元素的数学形态学相结合的图像边缘检测方法。用广义交叉验证准则进行小波阈值的自适应选取,用此阈值的广义阈值函数的小波滤波方法对含噪图像去噪;构造4种具有代表性的结构元素,根据边缘方向自动选择相应方向的结构元素,用改进的形态学边缘检测算子对图像进行边缘检测,得到在噪声存在条件下较为理想的图像边缘。实验结果表明,该算法能够有效地抑制噪声,检测的边缘较清晰、连续,其检测效果优于传统边缘检测算法。     

垂直交叉双向搜索策略的自适应窗口匹配算法

目的 基于区域的局部匹配算法是一种简单高效的立体匹配方法.针对局部算法中窗口的抉择问题,提出了基于垂直交叉双向搜索的自适应窗口匹配算法.方法 该算法考虑到局部区域内灰度值与视差值的相关性,通过垂直交叉双向搜索策略自适应地调节窗口的形状和大小,并获得相应掩码窗口;再利用积分图像计算掩码窗口的匹配代价,获取视差图;最后采用米字投票和双边滤波器两个步骤对视差图进行修复.结果 针对不同图像采用提出的自适应窗口算法,得到了适用于各种图像结构的匹配窗口,相较于原始垂直交叉算法的匹配精度提高了约30％ (Teddy),同时两步骤视差后处理较好地保持了图像边缘.结论 实验结果表明,该算法改善了规则窗口产生的视差边缘扩充问题,在提高视差精度的同时提高了算法鲁棒性.