基于动态结构元的药柱表面图像边缘检测  

Edge detection in grain surface image based on dynamic morphological structrual elements

作　　者：曾接贤[1,2] 徐芬[2] 龚勇[2] 

机构地区：[1]南昌航空大学计算机学院,江西南昌330063 [2]南昌航空大学无损检测技术教育部重点实验室,江西南昌330063

出　　处：《计算机工程与设计》2009年第19期4439-4442,共4页Computer Engineering and Design

基　　金：国家自然科学基金项目(60675022);无损检测技术教育部重点实验室开放基金项目(ZD200729006)

摘　　要：以某产品药柱表面图像边缘检测为例,提出了一种基于动态形态学结构元和SUSAN算子相结合的图像边缘检测算法。该算法采用动态形态学结构元得到梯度图像,根据梯度图像利用SUSAN算子进行边缘检测。采用动态形态学结构元得到的梯度图像服从统一分布,有利于边缘提取,克服了采用固定形态学结构元不能适应不同的梯度图像的不足。通过与So-bel和固定形态学结构元的边缘检测算子进行对比实验,实验结果表明,该方法具有较好的边缘提取能力,抗噪性能好,对药柱表面图像处理具有很好的实际应用价值。Taking detection of defects of a certain grain surface image for example, a edge detection method based on dynamic morphological structual elements and SUSAN operator is presented. Firstly, it is obtained gradient image by taking dynamic morphological structual elements, then detecting the edge with SUSAN operator according to gradient image. The gradient image obeys uniform distribution and is good for edge extraction, besides, it overcomes the disadvantage of taking fixed morphological structrual elements can not suit different gradient images. The experiment result shows that the method performs better in edge detection and anti-noise, which compared to Sobel and fixed morphological edge detection operator, and it has a good practical application in image processing of grain surface.

关 键 词：药柱表面图像 梯度图像 边缘检测 动态形态学结构元 SUSAN算子 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]