钢板缺陷特征的识别及提取算法研究  

Research on the Algorithm of Flaws Character Recognition and Obtainment for Armor-plate

作　　者：李小号[1] 黄英[1] 赵群超[1] 

机构地区：[1]东北大学机械工程与自动化学院,辽宁沈阳110004

出　　处：《机械与电子》2008年第4期68-70,共3页Machinery & Electronics

摘　　要：应用计算机图像处理理论与模式识别理论,对钢板图像缺陷特征的识别与提取算法进行了深入研究,利用VC++6.0计算机语言编制了相应的处理程序.用图像灰度理论编制了像素搜索算法,对钢板图像上各灰度级像素信息进行了提取,并进行相应的分布概率统计.根据统计结果,推导并利用基于二维直方图Fisher评价函数来处理该钢板图像,应用实践证明该算法程序能较好地满足钢板工业生产需求.The farther embedded research on the algorithm of flaws character recognition and obtainment for armor - plate, based on computer techniques of image processing and pattern recognition. This paper had accomplished the obtainment of armor - plate image pixels in terms of the different gradation value, and afforded the probability statistic of the gradation value distributing. In order to deal the armor- plate image better,the paper had researched and programmed the new algorithm using 2 - D histogram based on Fisher criterion function. Based on above, the paper had resolved the algorithm of flaws character recognition and obtainment of armor- plate, the result of practical application shows that the method can fit the industry production well.

关 键 词：图像处理 灰度直方图 FISHER评价函数 特征识别与提取 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]