共查询到19条相似文献,搜索用时 187 毫秒
1.
采用基于形态学增强和面积重构预处理的分水岭变换方法,对异种材料连接界面的超声检测图像进行了自适应分块阈值化分割处理.为了验证无损检测处理结果的可靠性,根据铜钢堆焊界面检测图像特征,对堆焊接头进行抽样破坏检测.结果表明,通过形态学增强和面积重构的预处理可有效抑制经典分水岭算法的过度分割,实现了检测图像按缺陷的分布特征进行自适应分块,进而通过阈值化分割,达到了超声弱信号缺陷的有效提取与量化的目的.经破坏性试验验证,该方法具有较高的检测可靠性. 相似文献
2.
3.
提出一种可靠提取焊缝边缘的图像处理方法.该方法通过对焊缝图像的梯度图像进行直方图均衡化,将梯度图像中反映边缘信息的像素的灰度级压缩到一个较小的范围内.然后,根据直方图均衡化后所得梯度图像的灰度级分布,确定图像的全局二值化阈值.以窗口半宽为步长在图像中滑动窗口,确定窗口内图像的局部二值化阈值.结合图像全局和局部二值化阈值,得到窗口内的自适应二值化阈值,对窗口内梯度图像进行二值化.此外,设计了一种迭代去噪的方法,以解决所得二值图像中存在大量噪声的问题.实际图像的测试结果表明了该方法的有效性. 相似文献
4.
5.
针对铸件X射线图像对比度低、边缘模糊、噪声多等特点,提出了基于二维属性直方图的最大相关准则图像分割算法。首先利用最大熵法得到的阈值构造图像的属性集,然后由原始图像及其属性集构造二维属性直方图。通过最大化图像的二维属性直方图中目标和背景分布的相关量来选择阈值向量。同时,为了节省二维阈值算法的计算时间,给出了递推算法,此算法减少了大量的重复计算,有利于该算法的实时应用。对铸件中气孔、缩孔和杂质三种缺陷进行了分割,试验结果表明,该算法能够快速、准确地分割出铸件图像中的缺陷。 相似文献
6.
针对X射线焊缝检测图像中存在大量背景冗余信息,焊缝和缺陷难于准确检测提取的问题,提出一种基于先验知识的有监督过渡区域提取及阈值分割方法.根据焊接图像本身的特点,通过先验知识对样本图像进行训练,确定某个区间来估算图像过渡区域的灰度范围,按照模糊子集理论,给出一种新的加权算子来描述局部窗口内灰度级的变化,从而能充分考虑到局部窗口内灰度级变化的频率和幅度,通过计算过渡区域像素的灰度均值,将其作为阈值对图像进行分割.结果表明,该方法能准确地将目标缺陷从焊缝X射线图像中分割出来,具有良好的适应性. 相似文献
7.
8.
为提高PET瓶口缺陷检测精度和检测速度,提出了一种基于机器视觉的PET瓶口自模板快速缺陷检测法。首先在全局阈值分割的基础上,对ROI区域(瓶口端面)构造自模板圆环,并且确保自模板图像和阈值分割图像坐标的对应关系不变。然后在ROI区域上,将自模板图像和阈值分割图像灰度做差进行缺陷检测,避免图像定位和缺陷定位对检测带来的大量复杂计算。通过实验验证,该方法缺陷检测精度达到99.9%,检测时间在50ms以内,有效提高了PET瓶口缺陷检测精度和速度,可以满足工业生产线上对PET瓶口缺陷检测准确性和实时性的要求。 相似文献
9.
基于改进C-V方法的焊接图像识别 总被引:1,自引:2,他引:1
基于简化的Mumford-Shah水平集图像分割模型,Chan-Vese提出了不依赖于图像边缘的水平集图像分割算法(C-V方法).文中对该算法进行了深入研究,指出了原方法存在的缺陷,即处理的图像必须具有比较明显的特征,分割目标过多且较为分散时则很难得到理想的结果,每次迭代过程都需要对所有的图像数据进行计算,比较费时.根据焊接图像本身的特点给出了三点改进,即强化特征模型的修正、多尺度快速算法和全局特性抑制.应用改进的算法,进行了模拟对比试验和真实熔池图像识别的试验.结果表明,该方法能识别出焊接图像连续轮廓,提取有用信息,具有良好的适应性.同时为复杂图像的特征物体目标提取提供了可行的思路. 相似文献
10.
为了减少焊接桥梁因疲劳产生裂纹,减少安全威胁,提出正交异性钢结构桥梁面板焊接区缺陷空间视觉定位方法。利用视觉注意力机制分别采集方向和亮度显著特征图,通过融合算法将二者融合,生成初始焊接区域图像。使用二值化处理方法计算图像初始对比度和像素分布系数,设定像素阈值,去除噪声点,提高图像质量。采用改进区域生长算法确定生长准则,通过阈值更新的方式实现图像背景与目标分离,获取图像条纹斜率,比较相邻像素点的斜率值,将该值做为判断特征拐点的依据,提取缺陷特征;结合获取的特征,利用最近邻域法识别出缺陷,实现缺陷视觉定位。结果表明,所提方法能够获得高质量的视觉图像,定位误差小。 相似文献
11.
In order to improve the work efficiency of non-destructive testing(NDT)and the reliability of NDT results,an automatic method to detect defects in the ultrasonic image was researched.According to the characterization of ultrasonic D-scan image,clutter wave suppression and de-noising were presented firstly.Then,the image is processed by binaryzation using KSW 2 D entropy based on image segmentation method.The results showed that,the global threshold based segmentation method was somewhat ineffective for D-scan image because of under-segmentation.Especially,when the image is big in size,small targets which are composed by a small amount of pixels are often undetected.Whereas,local threshold based image segmentation method is effective in recognizing small defects because it takes local image character into account. 相似文献
12.
In ultrasonic time of flight diffraction (TOFD) D-scan image, only a small fraction represents defects, whereas the majority is redundant. Because of the low contrast between defect and background image, it is difficult to manually interpret TOFD image. In addition, due to the nature of the weak amplitude of ultrasonic diffracted signals, the human factor introduces inconsistency into the interpretation. In order to automatically distinguish weld defects from the D-scan image, a defect detection method based on image processing technique is proposed. First, image pre-processing including clutter and noise suppression is conducted. Second, information entropy based image segmentation technique is employed to extract defects in the pre-processed image. At last, mathematical morphology based post-processing is carried out. The experimental results show that with the proposed method, TOFD can be used for automatic weld defect detection with satisfactory level of reliability. 相似文献
13.
超声TOFD(time of flight diffraction,衍射时差)法检测的D扫描图像中,作为背景杂波的侧向波与近表面缺陷波会发生混叠,致使近表面缺陷不易于检测. 针对这一问题,提出一种基于杂波抑制的缺陷检测方法. 该方法通过图像能量分布统计,确定背景杂波分量并予以去除,从而分离出与其混叠的缺陷信号,实现近表面缺陷的检测. 建立了的超声TOFD法检测信号的数学模型,阐明了基于图像能量分布的杂波抑制原理. 制作了人工缺陷试块及实际焊缝试块,并对其检测获取的图像进行了杂波抑制处理. 结果表明,提出的方法可有效去除图像中的非缺陷目标、提取近表面缺陷波,从而提高系统的有效检测范围. 相似文献
14.
15.
In this paper, the X-ray nondestructive test method of small defects in precision weldments with complex structure was presented. To resolve the difficulty of defect segmentation in variable grey image, the image processing based on Visual Basic programming method was adopted. The methods of automatic contrast and partial grey stretch were used to enhance the X-ray detection image which has relatively low contrast, then automatic threshold method was carried out to segment the two high intensity zones, and weld zones which contain the small defects was extracted. Smoothing and sharpen processing were proceeded on the extracted weld zones, and small defects in X-ray detection image of weldments with complex structure were segmented by using the method of background subtraction in the end. The effects of raster were eliminated, and because of that the image processing was only proceeded on the extracted weld zones, the calculated speed using the above provided algorithm was improved. 相似文献
16.
为实现飞机碳纤维复合材料(Carbon Fiber Reinforced Plastics,CFRP)层板在役检测,采用同侧空气耦合超声兰姆波特征成像检测的方法对其缺陷进行检测。将非接触空气耦合超声传感器置于CFRP层板同侧,激发A0模态兰姆波,对其冲击损伤进行D扫描检测。引入时间反转损伤指数表征复合材料层板的冲击损伤。结合概率损伤算法,以该指数作为损伤重构成像的特征值,将不同扫描路径上的特征值数据进行融合,得到CFRP层板冲击损伤缺陷的兰姆波图像。结果表明,基于时间反转的兰姆波图像不仅能够直观地呈现损伤缺陷的位置和形状,而且能够通过避免基准信号选取和减少扫描步进次数显著提高检测效率。 相似文献
17.
针对常规超声TOFD(time of flight diffraction,衍射时差)法存在超声衍射声场能量低、检测回波信号弱的问题,提出一种线聚焦超声TOFD焊接缺陷识别方法. 基于几何声学理论,根据所需主轴声线折射角度及聚焦深度,设计线聚焦超声TOFD法所用的声楔块. 通过铝合金板人工缺陷试件的检测,研究线聚焦法的检测灵敏度;通过铝合金板搅拌摩擦焊试件的检测,验证线聚焦法的有效性. 结果表明,和常规方法相比较,相同测试条件下线聚焦超声TOFD法的检测灵敏度更高,采集的图像具有更好的对比度,同时能较好地保持图像边缘. 所提新方法在改善缺陷分辨力、提高缺陷检出率及降低漏检等方面具有很好的使用价值. 相似文献
18.
Research on segmentation and distribution features of small defects in precision weldments with complex structure 总被引:2,自引:0,他引:2
In order to study the segmentation and quantitative problem of small defects in precision weldments with complex structure, an automated image processing system was setup based on the Visual Basic 6.0 development environment. The weld zones were extracted by adopting the method of twice automatic threshold, and the small defects were segmented successfully by using sharpen, smoothing processing and background subtraction in the extracted weld zones. To determine the spatial distribution features of small defects, calculation formula of defects depth and deviation were deduced individually, and the projection distance of small defects can be extracted automatically also. The image processing system can achieve the goal of small defects segmentation and automatic extraction of projection distance. The depth and deviation of small defects can be obtained through the above deduced formula, and the longitudinal distribution of small defects can be obtained from the detection image, then the spatial distribution features of small defects can be determined. 相似文献