热态锻件的目标提取和边缘检测实验研究  

Experimental research on object extraction and edge detection of hot forging parts

作　　者：邢作常[1] 田素博[1] 刘思瑶[1] 林静[1] 张祖立[1] 

机构地区：[1]沈阳农业大学工程学院,辽宁沈阳110866

出　　处：《锻压技术》2016年第2期124-132,共9页Forging & Stamping Technology

基　　金：国家自然科学基金资助项目(51275318);公益性行业(农业)科研专项(201503116)

摘　　要：热态锻件的在线尺寸测量一直是困扰锻造工艺的难题。图像处理是有望解决这一难题的重要途径,而高温锻件的目标提取和边缘检测是其中的关键环节。针对辐射光的影响、氧化皮的影响和强光干扰等问题,研究了高温锻件在各种色彩空间中的的图像特征,提出了基于色彩空间转换和动态阈值分割的目标提取方案;针对传统边缘检测算子中固定结构元素的缺点,研究了形态学结构元素的形状、尺寸、方向、权重对热态锻件边缘提取效果的影响,构造了多元、多尺度形态学边缘检测算子。最后开发了高温锻件边缘检测系统。实验对象为一具有端面键槽的圆柱体。实验结果表明,该方法可以获得比较理想的轮廓边缘信息。On line measurement of hot forgings has been a problem in forging process. Image processing is one of the most important ways in solving this problem. The object extraction and edge detection are the keypoints in image processing. For the influences of light radiation, forging scale and strong light interference, it was studied the image feature of the high temperature forging parts in a variety of color space, and the object extraction scheme based on color space conversion and dynamic threshold segmentation was proposed. Considering the disadvantages of fixed structure elements in traditional edge detection operator, the influences of shape, size, direction, weights of the morphological structure elements on the edge extraction effect of hot forging parts were researched, and muhi-scale morphological edge detection operator was put forward. At last, the edge detection system of high temperature forging parts was developed and the experiment cylinder with the end face keyway was conducted. The results show that the methods can obtain ideal contour edge information.

关 键 词：边缘检测 目标提取 色彩空间 动态阈值 形态学 

分 类 号：TG316[金属学及工艺—金属压力加工]