开孔泡沫铝表面缺陷的图像检测法

为提高开孔泡沫铝表面缺陷检测精度,提出基于傅里叶逆变换的检测法。制备开孔泡沫铝样品,采集样品表面图像,用自适应中值滤波算法预处理;用傅里叶逆变换分割缺陷区域,滤波后进行缺陷区定位,提取其特征,完成表面缺陷检测。结果表明:本方法可明显突出缺陷孔洞位置,无黑白点噪声干扰;识别表面缺陷时,误检率最高为1.4%,漏检率最高为2.8%,缺陷检测精度较高,具有一定的实用性。

Image detection method for surface defects of open cell aluminum foam

In order to improve the accuracy of surface defect detection of aluminum foam with openings,a detection method based on inverse Fourier transform was proposed. A sample of open cell aluminum foam was prepared,the sample surface images were collected,pre-processed it with adaptive median filter algorithm. Inverse Fourier transform was used to segment the defect region. The defect area was located after filtering. The feature was extracted and the surface defect was detected. The results show that this method can obviously highlight the location of defective holes,and there is no black-and-white noise interference. When identifying surface defects,the highest false detection rate is 1.4%,the highest missed detection rate is 2.8%. The defect detection accuracy is high,and it has certain practicability.