烧结矿矿相显微图像识别及系统开发

来源期刊:中南大学学报(自然科学版)2011年第10期

论文作者:范晓慧 赵忠花 陈许玲 甘敏 王祎

文章页码:2893 - 2897

关键词:烧结矿矿相;显微图像;图像识别;区域生长算法

Key words:sinter mineralogy; micrograph;image recognition; region growing algorithm

摘    要:为了快速、准确地获得烧结矿矿物组成,研究开发了烧结矿矿相显微图像识别系统。在分析不同碱度烧结矿矿相特征的基础上,确定了图像识别算法的原则;并研究对比分水岭、模糊C-均值(FCM)和区域生长这3种识别算法。研究结果表明:区域生长算法比较适合于烧结矿矿相显微图像的识别;应用VC++2003.net开发了烧结矿矿相显微图像识别系统,其识别结果与专家分析结果相比,相对误差小于5%,达到了烧结矿矿相识别的精度要求。

Abstract:

In order to calculate the mineral composition of sinter accurately and rapidly, the system for recognizing micrograph of sinter mineralogy was researched and developed. Principles for selecting the recognition algorithm were established based on the features of mineralogy micrographs of sinter with different basicities. Experiments for recognizing micrograph were taken out with watershed algorithm, fuzzy C-means algorithm, and region growing algorithm in order to study the method for recognizing micrograph of sinter mineralogy. The results indicate that the region growing algorithm is suitable for sinter micrograph recognition. The system for recognizing micrograph of sinter mineralogy is developed by VC++ 2003.net. The relative error of sinter mineralogy recognized by this system is less than 5%, compared with that tested which can meet the accuracy requirement of sinter mineralogy processing.

基金信息:教育部新世纪优秀人才支持计划基金资助项目

相关论文

  • 暂无!

相关知识点

  • 暂无!

有色金属在线官网  |   会议  |   在线投稿  |   购买纸书  |   科技图书馆

中南大学出版社 技术支持 版权声明   电话:0731-88830515 88830516   传真:0731-88710482   Email:administrator@cnnmol.com

互联网出版许可证:(署)网出证(京)字第342号   京ICP备17050991号-6      京公网安备11010802042557号