精密金属焊接坏点的视觉识别方法研究与仿真  

Research and Simulation on the Visual Identification Method for Bad Point of Precision Metal Welding

作　　者：赵海燕[1,2] 钮文良[1] 刘琨[1] 

机构地区：[1]北京联合大学应用科技学院,北京102200 [2]中国石油大学地球物理与信息工程学院,北京102249

出　　处：《计算机仿真》2014年第8期204-208,共5页Computer Simulation

基　　金：北京联合大学自然科学类新起点计划项目(ZK201219);北京市教委科研计划项目(SQKM201211417008;KM201311417001)

摘　　要：研究高精密金属焊接坏点准确视觉识别的问题。由于高精密金属焊接坏点的颜色特征与金属本身特征相似,而在坏点很小并且与外部环境过于类似的干扰下,传统的基于像素差异的识别结果不精确,一旦焊接坏点分布的过于集中,干扰将更大,导致焊接坏点识别准确性降低。为解决上述问题,提出一种新的计算机视觉的高精密金属焊接坏点识别方法。采集高精密金属焊接坏点计算机视觉图像,针对金属图像进行特征提取,并对提取的特征进行离散小波变换处理,获取增强处理后的视觉图像。根据增强处理后的视觉图像特征值,获取高精密金属焊接坏点的分布密度,计算焊接坏点的空间位置,实现高精密金属焊接坏点识别。实验结果表明,利用改进算法进行高精密金属焊接坏点识别,能够提高识别的准确率,并且获取焊接坏点在高精密金属制品中的分布位置,为高精密金属制品的生产质量提供保障。The accurate visual recognition problem of bad pointof high - precision metal weldingis studied. Be- cause the color characteristics of the bad point of high precision metal weldingand metal itself are very similar. With the disturbance of small bad point and similar external environment, traditional identification methods based on pixel differences are inaccurate. Once the bad point of welding are over - concentrated, interference will be greater, resul- ting in reduced accuracy of welding bad point＇s recognition. This study presents a new recognition method for bad point of high - precision metal welding based on computer vision. Through the acquisition of computer vision image of bad point ofhigh -precision metal welding, features of metal image can be extracted. Then, discrete wavelet trans- form is used to process the extracted feature to obtain the enhanced visual image. The enhanced visual characteristics of the image can be utilized to obtain the distribution density of bad point of high - precision metal welding and calculate the spatial position of the welding bad point, so as to achieve recognition of bad point. The experimental results show that this method can improve the recognition accuracy, and obtain the accurate position of welding bad point in high - precision metal products, in order to provide protection for the production of high quality precision metal products.

关 键 词：计算机视觉 高精密金属制品 焊接坏点识别 

分 类 号：F127[经济管理—世界经济]