融合卷积神经网络和双边滤波的相贯线焊缝提取算法

Fusion algorithm of convolution neural network and bilateral filtering for seam extraction

相贯线焊缝提取精度影响了工业焊接的精确度,是焊缝技术的重要步骤,也是工业领域研究的重点问题之一。传统的相贯线焊缝提取算法存在提取速度慢、提取精度不佳的问题,为了解决以上问题,提出融合卷积神经网络和双边滤波的相贯线焊缝提取算法。首先,通过轮廓波变换方法对相贯线焊缝图像进行灰度化处理及增强处理;其次,通过双边滤波方法对焊缝图像进行去噪处理;最后,通过全卷积神经网络完成相贯线焊缝提取。实验结果表明:本文方法的相贯线焊缝提取更加清晰、精度更高,整体应用效果更佳。

The extraction accuracy of intersecting line weld affects the accuracy of industrial welding,which is an important step of weld technology and one of the key issues in industrial research.In order to solve the problems existing in the traditional method,the intersection line weld extraction algorithm based on convolution neural network and bilateral filtering is proposed.Firstly,the weld image of the intersecting line is grayed and enhanced by the contour wave transformation method;Secondly,the weld image is denoised by bilateral filtering method;Finally,the intersecting line weld seam is extracted through the full convolution neural network.The experimental results show that the proposed method has higher accuracy,faster speed and better overall application effect.