摘要
发电厂凝汽器胶球清洗系统对于胶球的更换往往仅凭借经验,使得胶球利用率不高,还会影响清洗效果.研究采用对胶球拍照、分析图像边缘来检测胶球合格率的方法.由于拍摄到的图像含有噪声,而且目标和背景灰度相近,仅仅采用传统的边缘检测算子往往不容易区分噪声和图像边缘.对此提出了一种基于小波包理论的边缘检测算法,利用小波包分解重构方法滤除噪声,然后利用RO-BERTS算子检测出准确的图像边缘.
The replacement of rubber ball of power plant＇s condenser rubber ball washing system traditionally depends on experience,which reduced the utilization rate of rubber ball and also affected the cleaning effect.This paper introduced a method which took photos for rubber ball and detects its edge to measure its percent of pass.Because of the mixed noise and the similarity of background and the target,it was difficult to separate edge from noise by using traditional edge detection operators.Thus,this paper proposed an algorithm based on wavelet packet,which utilized wavelet packet to decompose and reconstruct the image to suppress noise.The clear edge was detected using ROBERTS operator.
出处
《哈尔滨商业大学学报（自然科学版）》
CAS
2011年第1期92-93,116,共3页
Journal of Harbin University of Commerce：Natural Sciences Edition
