基于离散度的药柱端面银丝位置视觉识别方法

Dispersion based visual recognition method for silver wire position of the grain end

对药柱端面银丝位置的准确识别并引导设备进行自动钻孔操作是内埋金属丝药柱自动化整形过程的关键技术之一,提出了一种基于离散度的视觉方法,用于准确识别药柱端面的银丝位置。该方法对图片进行降噪滤波后,根据图片特征生成自适应感兴趣区域,对感兴趣区域进行细分后,在该区域内设置搜索模板;旋转搜索模板计算各个细分位置的相关性,比较各个位置的相关性粗定位找到银丝所在的子区域;在粗定位得到的子区域内比较滑动窗口的离散度进行银丝位置的精定位,准确找到药柱端面的银丝位置,并引导设备进行钻孔操作。实验结果表明,所提出的算法能够准确得到银丝的位置,对银丝位置的识别率大于所需求的99%。综上,该方法可快速准确实现银丝位置的识别,满足自动化批量生产的要求。

It is one of the key technologies to identify the silver wire position on the end of the grain and guide the device to drill automatically,in this paper,a visual method based on dispersion is proposed to accurately identify the silver wire position of the grain.This method performs noise reduction filtering on pictures,generates adaptive regions of interest based on the characteristics of the pictures,subdivides the regions of interest,and sets a search template in the region;after calculating the correlation of each sub divided position by rotating the search template,comparing the correlation of each position,coarse positioning to find the sub region where the silver wire is located;within the sub region obtained by the coarse positioning,compares the dispersion of the sliding win dow to perform fine positioning of the silver wire position,and accurately find the position of the silver wire on the end of the grain,guides the equipment for drilling operations.Experimental results show that the proposed algorithm can accurately obtain the position of the silver wire,and the recognition rate of the position of the silver wire is greater than the required 99%.In summary,this method can quickly and accurately identify the position of silver wire and meets the requirements of automated mass production.