A neural network method was used to process image of welding pool and the result of detecting the edge of binary image with BP neural network was excellent.
探索了将神经网络用于焊接熔池图像处理的方法，采用BP神经网络对二值化熔池图像进行边缘提取，取得了理想的效果。
The process of image treatment is as follow: filter, enhance, making binary image by adaptive threshold, edge detection and so on.
本文所采用的图像处理主要步骤为：滤波、增强、自适应阈值二值化、边缘提取等预处理。
The whole process is the morphology processing based on the gray-level image and binary mask, and is simple and easy to implement.
整个过程基本是对灰度图像和二值模板的形态处理，简单易行。
To get a clear weld image, iterative threshold method is developed to process the image binary.
采用迭代的阀值化方法对图像进行二值处理，可以获得清晰的焊缝图像。
It includes edge detection, making binary image, vertex recognition in this process. It is necessary to eliminate the exceptional points, which lessens error rate.
利用数字图像处理技术检测锯齿工件顶点，对图像进行了边缘检测、二值化、顶点识别处理。
Thinning binary images is an important process in image analysis.
两值图象的细化是图象分析的重要环节。
Thinning binary images is an important process in image analysis.
两值图象的细化是图象分析的重要环节。
应用推荐