基于曲线拟合的金属磨粒识别  

IDENTIFICATION OF METAL WEAR DEBRIS BASED ON CURVE FITTING

作　　者：桂婷[1] 胡同森[2] 林晓敏[2] 

机构地区：[1]浙江工业大学之江学院,浙江杭州310024 [2]浙江工业大学计算机科学与技术学院,浙江杭州310014

出　　处：《计算机应用与软件》2011年第6期269-270,298,共3页Computer Applications and Software

摘　　要：提出一种基于曲线拟合的方法,进行铁谱图像中金属磨粒的识别。在铁谱图像中选取一定数量的金属磨粒像素点,依据所选取像素点的颜色信息,通过曲线拟合的方法找出相似像素点的分布位置。算法的算法复杂度取决于选取像素点的个数(一般远少于图像像素点总数),计算速度较快,识别效率较高。The proposed approach,in this paper,is concerned with the recognition of metal wear debris in ferrographic image based on curve fitting.A certain number of metal wear debris pixels are selected from the image,according to their colour information,the distribution position of similar pixels can be found using the method of curve fitting.The computation complexity of this algorithm depends on the number of the pixels selected（usually far less than the total number of image pixels）,it has a fast calculation speed and is efficient in identification.

关 键 词：曲线拟合 拉格朗日插值 金属磨粒 铁谱图像 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]