论文部分内容阅读
为了提高放射图像的焊接缺陷检测精度,引入了功率倒谱技术,并设计焊接区域定位机制,提出了基于高阶统计的放射图像自动焊接缺陷检测方法。首先,利用自适应直方图均衡技术增强放射图像;并使用均值维纳滤波器对增强后的图像进行滤波处理;然后通过设计焊接区域定位机制,从放射图像中确定焊接缺陷所在的区域;再引入功率倒谱技术,从高阶频谱(三阶谱)中提取放射图像的倒谱特征信息;并利用神经网络技术对提取信息进行特征匹配。仿真结果显示,与当前缺陷检测方法相比,本文方法的检测率要高于其他方法。
In order to improve the detection accuracy of welding defects in radiographic images, a power cepstrum technique was introduced and the welding area localization mechanism was designed. A method of automatic welding defect detection based on high-order statistics was proposed. First, the adaptive histogram equalization technique is used to enhance the radiological image; the mean value Wiener filter is used to filter the enhanced image; and then the welding area locating mechanism is used to determine the area where the welding defect is located from the radiological image; Power cepstrum technique to extract the cepstrum feature information of the radiological image from the high-order spectrum (third-order spectrum); and the feature extraction of the information is performed by using the neural network technology. The simulation results show that compared with the current defect detection method, the detection rate of this method is higher than other methods.