分水岭变换和统计区域合并的图像分割算法研究

提出了一种基于分水岭变换和统计区域合并的图像分割方法.该方法综合利用高斯低通滤波、分水岭变换和统计区域合并,先对原始图像提取分割标记,然后利用Meyer分水岭变换对标记分水岭进行分割,最后利用概率统计的方法对过分割区域进行合并.该算法通过调节尺度参数可以实现由粗到细(coarse-to-fine)的分割.实验结果表明,这种简单可行的算法在分割噪声图像时依然有良好的效果,具有较强的鲁棒性.     

基于模板的前视红外图像建筑物分割方法

针对前视红外地面建筑物图像目标分割问题,在传统方法的基础上提出了一种基于模板制备的改进C-V模型分割方法.首先通过DSM数据制备目标二维形状模板;然后对图像进行高斯滤波去噪,并采用模板尺度相关的结构元素对图像进行灰度形态学增强;最后引入模板形状先验信息的概念,利用水平集方法表达轮廓先验信息,在C-V模型的基础上增加目标轮廓先验信息能量项,使分割曲线进化同时受到图像数据与形状先验信息驱动,实现目标分割.实测数据显示该方法能在复杂背景条件下精确分割前视红外建筑物目标.     

基于自动种子区域生长的超声B图像缺陷分割方法

提出一种基于自动种子区域生长的超声图像缺陷分割方法。首先使用最大类间方差（Otsu）分割法对超声B图像进行一次预分割;其次寻到绝对背景区,并且在此区域内自动设置种子起始点;然后利用区域生长法将缺陷从背景中分割;最后通过数字形态学降噪法来进一步提高缺陷的识别度。实验结果表明:该方法不仅能准确地分割出缺陷,且具有较好的缺陷边界信息,提高了对超声B图像的处理效率,有效地抑制了大部分图像噪声。     

自然场景图像的字符识别方法

目的基于大津算法(Otsu算法)对图像进行分割,利用光学字符识别方法对自然场景图像中的英文字符进行识别。方法首先用分块Otsu算法对图像进行初步的二值化,然后通过对二值化结果的分析,把原始的输入图片分割成单个字符的子图,再对各子图重新用Otsu算法进行二值化,最后对最终得到的二值化结果进行识别,再结合之前得到的每幅图的字符数量信息和词典信息,对识别结果进行修正,得到最终的识别结果。结果在ICDAR2013数据集上测试文中算法,单词正确识别率为46.03%,总编辑距离为474.5。结论文中提出的以Otsu为基础的分块识别算法,能够更好地分割复杂背景图像的背景和文本,同时结合词典信息对识别结果进行了修正,改善了识别效果。     

采用平面特征搜索的深度图像坐标对准

提出了一种包含平面特征的激光扫描深度图像行之有效的坐标自动调整方法.通过移动包围盒的方法在数据点集内自动搜索并判定特定平面特征作为基准;计算出平面特征的平均法向量,将点集的坐标向基准平面的法向对准;最后通过缩小包围盒范围并重复搜索,使点集的方向规范化.此方法在液货舱激光扫描数据上进行了应用,数据经过对准处理后,大大方便了后续的投影、分割等模型重建工作.     

纸塑复合袋表面缺陷图像分割算法的设计与实现

目的 纸塑复合袋表面缺陷图像受到噪声、光照不均以及自身缺陷等因素的影响,在对图像缺陷区域进行分割时会造成过分割或欠分割.针对此现象提出一种将边缘检测和自适应区域生长法相结合的纸塑复合袋表面缺陷图像的分割算法.方法 首先利用Sobel算子和形态学运算对双边滤波后的缺陷图像进行第1次分割;然后对缺陷区域进行最小外接矩形标记并计算其形状特征,通过判定形状特征大小来决定是否继续分割;最后将符合继续分割的图像缺陷区域质心作为初始种子点,在原始图像上进行自适应区域生长,形成第2次分割结果,完成缺陷图像分割.结果 与其他算法相比,该算法对各类常见缺陷均能取得较好的分割效果,Dice系数均在0.93以上.结论 该算法分割精度较高,有较强的鲁棒性,可以满足工业上的生产需求.     

基于FCM和图割的交互式图像分割方法

为了提高在前景和背景颜色相似情况下图像的分割效果,提出了一种基于模糊C均值聚类(FCM)和图割的交互式图像分割方法。首先,利用分水岭算法对图像进行预处理,将图像分成多个小区域,用区域代替像素点进行分析。然后,采用模糊C均值算法对用户标记的前景区域和背景区域分别进行聚类分析,挖掘用户交互所提供的隐藏信息。用未标记区域的颜色分量到前景区域及背景区域类心的最小距离表示相似能量,用未标记区域与其相邻区域的相关性表示先验能量。最后,利用最大流/最小割算法求能量函数的全局最优解。与其他方法相比,该文方法具有较好的分割性能,能从前景背景相似的图像中较精确地提取感兴趣的物体,且用户操作简单。     

红外车辆目标的自动模糊分割

针对红外图像的特点,提出了一种基于遗传算法的自动模糊分割红外车辆目标图像的方法.首先选取图像的感兴趣区域以加快运算速度;然后对感兴趣区域图像进行模糊增强,借助于二维OTSU方法对增强后的感兴趣区域进行阈值分割,为了加快分割算法的速度,先限定一个最佳阈值范围,再利用遗传算法在此阈值范围内自动搜索最佳分割阈值;为了弥补单独利用二维OTSU方法分割的不足,采用缩短模糊边缘宽度的方法来提取感兴趣区域红外车辆目标图像的边缘.最后把二维OTSU方法分割的图像与模糊边缘提取得到的边缘图像进行或运算后进行填充以得到最终的车辆目标分割图像.实验结果表明,对于红外车辆目标图像,一维OTSU和二维OTSU算法只是基本分割出了红外车辆目标的主体,而本文提出的自动模糊分割技术不仅准确分割出了红外车辆目标的主体,而且对于坦克的模糊炮塔亦得到了完整的分割.     

一种基于DA-GMRF的无监督图像分割方法

提出一种基于间断自适应高斯马尔可夫随机场(DA-GMRF)模型的无监督图像分割方法.针对MRF模型中的过平滑问题,利用边缘信息构造能量函数,定义了一种DA-GMRF模型.利用灰度直方图势函数自动确定分类数及分割阈值,进行多阈值分割,得到DA-GMRF模型中标记场的初始化,用Metroplis采样器算法进行标记场的优化,实现了图像的无监督分割.实验结果表明了该方法的有效性.     

基于边缘探测的密集颗粒图像分割方法

针对密集的颗粒图像提出了一种基于边缘探测的颗粒分割方法.该方法采用分块自适应的边缘检测算法实现对图像的边缘检测,并采用形态学方法去除边缘噪音;采用分水岭算法对图像进行初步分割,根据分割区域自动选取种子点,并利用区域面积对种子点进行修正,然后从种子点发射探测线探测边缘位置,记录边界点,通过判断机制判别出由于边缘不完整或噪...     

基于Tsallis广义散度的图像阈值分割

为了有效获取图像自动分割的最佳闽值,基于Tsallis广义散度概念,提出了一种新的图像阈值化方法.首先,对Tsallis广义散度公式进行化简,进而建立该简化公式的对称形式.接着,在简化公式的对称形式上构造阈值化前后图像前景与背景的散度和,然后对该和式求职极小值获取图像分割的最佳阈值.实验结果表明,新方法是可行的且能更好的适应复杂多样的图像,是一个有效的阈值分割方法.     

红外序列图像的支持向量机分割方法

红外序列图像的准确分割是自动目标识别的关键,而当图像背景复杂时,传统的图像分割技术往往难以满足要求,为此,提出了基于支持向量机的红外序列图像分割方法。序列图像中的部分帧被作为训练样本,通过选择适合的模型参数,运用支持向量机方法建立学习机器,将后续图像帧中的目标从复杂的背景中识别出来,从而实现红外图像分割。实际红外序列图像分割表明,基于支持向量机的图像分割方法不需要复杂的预处理和后处理工作,分割效果理想,对于小目标的图像,识别正确率可达 99%。     

Double regularization control based on level set evolution for tablet packaging image segmentation

This paper proposes a novel double regularization control(DRC) method which is used for tablet packaging image segmentation.Since the intensities of tablet packaging images are inhomogenous,it is difficult to make image segmentation.Compared to methods based on level set,the proposed DRC method has some advantages for tablet packaging image segmentation.The local regional control term and the rectangle initialization contour are first employed in this method to quickly segment uneven grayscale images and accelerate the curve evolution rate.Gaussian filter operator and the convolution calculation are then adopted to remove the effects of texture noises in image segmentation.The developed penalty energy function,as regularization term,increases the constrained conditions based on the gradient flow conditions.Since the potential function is embedded into the level set of evolution equations and the image contour evolutions are bilaterally extended,the proposed method further improves the accuracy of image contours.Experimental studies show that the DRC method greatly improves the computational efficiency and numerical accuracy,and achieves better results for image contour segmentation compared to other level set methods.     

Image Processing of Manganese Nodules Based on Background Gray Value Calculation

To troubleshoot two problems arising from the segmentation of manganese nodule images-uneven illumination and morphological defects caused by white sand coverage, we propose, with reference to features of manganese nodules, a method called “background gray value calculation”. As the result of the image procession with the aid this method, the two problems above are solved eventually, together with acquisition of a segmentable image of manganese nodules. As a result, its comparison with other segmentation methods justifies its feasibility and stability. Judging from simulation results, it is indicated that this method is applicable to repair the target shape in the image, and segment the manganese nodule image in a short time. Also, it could be used to synchronously process a large number of manganese nodules on different conditions in an image, laying a good foundation for automatic underwater manganese nodule survey. Even if the target in the image is slightly distorted, the statistical data of manganese nodules are still accurate. Moreover, other methods cannot be fully applied to the segmentation of manganese nodule images; in another word, the effectiveness and stability of this method are proved.     

Multi-Scale 3D U-Nets: An approach to automatic segmentation of brain tumor

Gliomas segmentation is a critical and challenging task in surgery and treatment, and it is also the basis for subsequent evaluation of gliomas. Magnetic resonance imaging is extensively employed in diagnosing brain and nervous system abnormalities. However, brain tumor segmentation remains a challenging task, because differentiating brain tumors from normal tissues is difficult, tumor boundaries are often ambiguous and there is a high degree of variability in the shape, location, and extent of the patient. It is therefore desired to devise effective image segmentation architectures. In the past few decades, many algorithms for automatic segmentation of brain tumors have been proposed. Methods based on deep learning have achieved favorable performance for brain tumor segmentation. In this article, we propose a Multi-Scale 3D U-Nets architecture, which uses several U-net blocks to capture long-distance spatial information at different resolutions. We upsample feature maps at different resolutions to extract and utilize sufficient features, and we hypothesize that semantically similar features are easier to learn and process. In order to reduce the computational cost, we use 3D depthwise separable convolution instead of some standard 3D convolution. On BraTS 2015 testing set, we obtained dice scores of 0.85, 0.72, and 0.61 for the whole tumor, tumor core, and enhancing tumor, respectively. Our segmentation performance was competitive compared to other state-of-the-art methods.     

Deer Body Adaptive Threshold Segmentation Algorithm Based on Color Space

In large-scale deer farming image analysis, K-means or maximum betweenclass variance (Otsu) algorithms can be used to distinguish the deer from the background. However, in an actual breeding environment, the barbed wire or chain-link fencing has a certain isolating effect on the deer which greatly interferes with the identification of the individual deer. Also, when the target and background grey values are similar, the multiple background targets cannot be completely separated. To better identify the posture and behaviour of deer in a deer shed, we used digital image processing to separate the deer from the background. To address the problems mentioned above, this paper proposes an adaptive threshold segmentation algorithm based on color space. First, the original image is pre-processed and optimized. On this basis, the data are enhanced and contrasted. Next, color space is used to extract the several backgrounds through various color channels, then the adaptive space segmentation of the extracted part of the color space is performed. Based on the segmentation effect of the traditional Otsu algorithm, we designed a comparative experiment that divided the four postures of turning, getting up, lying, and standing, and successfully separated multiple target deer from the background. Experimental results show that compared with K-means, Otsu and hue saturation value (HSV)+K-means, this method is better in performance and accuracy for adaptive segmentation of deer in artificial breeding scenes and can be used to separate artificially cultivated deer from their backgrounds. Both the subjective and objective aspects achieved good segmentation results. This article lays a foundation for the effective identification of abnormal behaviour in sika deer.     

Referenceless segmentation of flaws in woven fabrics

The automatic segmentation of flaws in woven fabrics is achieved by applying Fourier analysis to the image of the sample under inspection, without considering any reference image. No prior information about the fabric structure or the defect is required. The algorithm is based on the structural feature extraction of the weave repeat from the Fourier transform of the sample image. These features are used to define a set of multiresolution bandpass filters, adapted to the fabric structure, that operate in the Fourier domain. Inverse Fourier transformation, binarization, and merging of the information obtained at different scales lead to the output image that contains flaws segmented from the fabric background. The whole process is fully automatic and can be implemented either optically or electronically. Experimental results are presented and discussed for a variety of fabrics and defects.     

复杂背景下基于HSV空间和模板匹配的车牌识别方法研究

车牌识别技术作为交通管理自动化的重要手段,在交通监视和控制中占有很重要的地位.车牌识别过程可分为车牌定位、车牌校正、字符分割和字符识别四个部分.在车牌定位中,若单纯采用纹理特征或颜色特征来进行定位,往往适用于背景较为简单的场景,对复杂背景的定位效果尚有待改进.在字符分割中,目前单行车牌的分割已比较成熟,但双行车牌的分割仍不理想.提出一种在HSV空间下两次颜色标定和纹理特征相结合的定位方法和一种单双行车牌的字符分割方法.该定位方法利用车牌固定颜色搭配特性,对图片两次标记并利用投影法定位车牌,对200张不同背景图片测试,定位准确率达到98％.在字符分割部分,利用改进的模板匹配方法对字符分割,可适用于单、双行车牌分割,准确率达到95％.