首页 | 本学科首页   官方微博 | 高级检索  
     检索      

基于骨架特征的层次化识别算法在异形纤维识别中的应用
引用本文:龚有平,姚砺,万燕,宋锟.基于骨架特征的层次化识别算法在异形纤维识别中的应用[J].东华大学学报(自然科学版),2011,37(3):356-361.
作者姓名:龚有平  姚砺  万燕  宋锟
作者单位:东华大学计算机科学与技术学院,上海,201620
基金项目:中央高校基本科研业务费专项资金资助项目(B073)
摘    要:针对基于骨架的单一特征的算法在异形纤维图像识别方面的不足,提出一种基于骨架特征并融合其他几何特征的层次化识别算法.首先采用轮廓跟踪算法将骨架信息映射到一种骨架树结构中,然后构造骨架特征邻接矩阵并求出该矩阵特征值,以特征值对异形纤维图像进行大类识别,再结合骨架周长统计特征和异形纤维图像轮廓的凹凸特征对每一大类异形纤维图像...

关 键 词:异形纤维  骨架  骨架树  邻接矩阵  矩阵特征值  凹凸点

The Profiled Fiber Image Hierarchical Recognition Based on Skeleton Feature
GONG You-ping,YAO Li,WAN Yan,SONG Kun.The Profiled Fiber Image Hierarchical Recognition Based on Skeleton Feature[J].Journal of Donghua University,2011,37(3):356-361.
Authors:GONG You-ping  YAO Li  WAN Yan  SONG Kun
Institution:GONG You-ping,YAO Li,WAN Yan,SONG Kun(College of Computer Science and Technology,Donghua University,Shanghai 201620,China)
Abstract:A hierarchical and skeleton-based algorithm which also combines with other geometrical features was proposed to improve the performance of profiled fiber image recognizer which use single skeleton feature.Firstly,the skeleton information was mapped to a skeleton tree structure by contour tracking algorithm.Then,a skeleton tree's adjacency matrix was constructed and eigenvalues of the matrix was worked out and the profiled fiber image was divided into several categories according to the eigenvalues.Finally,e...
Keywords:profiled fiber  skeleton  skeleton tree  adjacency matrix  eigenvalues  convex-concave point  
本文献已被 CNKI 万方数据 等数据库收录!
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号