共查询到20条相似文献,搜索用时 203 毫秒
1.
2.
3.
4.
5.
6.
7.
将目标检测网络Faster-RCNN应用在船舶焊缝X射线缺陷图像检测中,探讨了Faster-RCNN在X射线焊缝缺陷检测中的效果。针对船舶工业中的X射线焊缝图像,首先采用CLAHE方法对焊缝X射线图像进行预处理,并将焊缝中存在的气孔、裂纹、未熔合等5种具有典型特征的缺陷作为识别目标进行标注并对数据进行增强。在目标识别上,采用ResNet-50作为主干网络来减少梯度弥散现象提高模型准确率,并针对焊缝缺陷目标小的特点对RPN网络锚点参数进行改进优化,同时引入FPN网络提取缺陷特征。最后与其他检测算法进行对比,试验结果表明,该数据集在模型上的mAP值达到96.33%,可以满足X射线焊缝缺陷自动化辅助检测要求。 相似文献
8.
针对射线检测图像的高噪声、低对比度、图像模糊等特点,提出了一种射线图像的自适应多尺度积阈值降噪算法,解决了常用射线检测图像降噪算法存在的降噪效果差、图像模糊、缺陷边缘和细节丢失等问题。该算法利用噪声估计、多尺度、积阈值、小波等方法对射线检测图像进行降噪处理,获得了高质量的降噪图像。以实际的工业焊缝射线检测图像为例,将所提算法与常用的小波降噪、中值滤波、维纳滤波、小波中值等算法进行降噪对比研究。试验结果表明,所提算法不仅具有优异的降噪性能,而且能够较好地保留缺陷图像边缘、细节等重要特征。 相似文献
9.
10.
11.
基于优化Gabor滤波器的铸坏表面缺陷检测应用研究 总被引:1,自引:0,他引:1
目的提高金属铸坯表面缺陷检测精度。方法由于金属铸坯表面上存在鱼鳞状构造,其亮度和背景区域纹理特征不一致,而且有缺陷和无缺陷的区域的灰度值极其相似,使得缺陷非常难以准确检测出来。为解决上述问题,以便更有效地检测表面缺陷,通过详细分析金属铸坯表面缺陷特征,将该类零件表面缺陷分为两种类型,提出一种基于优化Gabor滤波器的金属表面缺陷检测算法,该算法通过设计两种评价函数,利用评价函数最大限度地提高无缺陷和缺陷区域之间的能量差,以选取Gabor滤波器四个最佳参数,同时使用双阈值滤波方法,以减少由于噪声和伪缺陷引起的测量误差。结果利用3种滤波算法对四十幅带有缺陷的图像进行试验,实验表明该算法在角部裂纹、细裂纹和伪裂纹检测精度分别达到92.50%、92.50%和95.50%。结论 Opt-Gabor算法能根据已分类的两种不同类型的裂纹较为准确地检测出铸坏表面缺陷,在测量精度上略优于其他几种算法。 相似文献
12.
针对现有人工目检方法对精加工硬质合金微型喷嘴产品表面检测存在速度慢、缺陷漏检率和误检率高等问题,提出一种基于机器视觉的喷嘴图像缺陷检测方法。分析了喷嘴缺陷图像类型和喷嘴结构,重点研究了喷嘴缺损圆边缘拟合、疤料边缘增强、极坐标变换和缺陷灰度值差异统计等。该方法避免了喷嘴的复杂结构对缺陷定位和检测造成的大量计算。通过对合格和不合格喷嘴进行检测,验证了该方法缺陷检测准确率达到98.6%,每件产品检测时间为0.834 s,而目视检测准确率为91.2%,每件产品检测时间为5.213 s。因此该算法有效提高了检测精度和速度,满足工业生产线对喷嘴检测准确性和实时性的要求。 相似文献
13.
In this paper, an automatic inspection system for weld surface appearance using machine vision has been developed to recognize weld surface defects such as porosities, cracks, etc. It can replace conventional manual visual inspection method, which is tedious, time-consuming, subjective, experience-depended, and sometimes biased. The system consists of a CCD camera, a self-designed annular light source, a sensor controller, a frame grabbing card, a computer and so on. After acquiring weld surface appearance images using CCD, the images are preprocessed using median filtering and a series of image enhancement algorithms. Then a dynamic threshold and morphology algorithms are applied to segment defect object. Finally, defect features information is obtained by eight neighborhoods boundary chain code algorithm. Experimental results show that the developed system is capable of inspecting most surface defects such as porosities, cracks with high reliability and accuracy. 相似文献
14.
15.
17.
18.
19.
Recently, there has been an increase in the demand for quality control in the steel making industry. This paper proposes a vision-based method for detection of defects in the surfaces of scale-covered steel billets. Scales are formed on the surface of billets owing to the deposition of oxidized substances that are produced during manufacturing. Because of the presence of scales on the billet surface, its characteristics such as brightness and texture in the background region are inconsistent. Moreover, the similarities in the gray-levels of the defect and defect-free regions make it very difficult to accurately detect defects. In order to solve the abovementioned problems and to detect defects more effectively, we propose a new defect detection algorithm, which is based on Gabor filters. The Gabor filters are optimized using a new optimization algorithm known as univariate dynamic encoding algorithm for searches (uDEAS). The algorithm finds the minimum value of the cost function related to the energy separation criteria between the defect and the defect-free regions. Finally, the experimental results conducted on billet surface images from actual steel production line show the effectiveness of the proposed algorithm. 相似文献