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

基于关联度分析的图像分割性能评估
引用本文:李保洲,王建琦,邓雁萍.基于关联度分析的图像分割性能评估[J].上海交通大学学报,2000,34(6):824-826.
作者姓名:李保洲  王建琦  邓雁萍
作者单位:上海交通大学,图像处理与模式识别研究所,上海,200030
摘    要:针对图像分割的性能分析问题,运用关联度分析技术建立了一种多层次的综合评估方法,运用此方法评估既可以在整体性能上进行,又可以从某个侧面性能。该方法所采用的评估指标具有多层次的特点,评估结果的离散性高,便于区分不同分割算法的性能。应用实例表明,该方法较好地克服了以往评估中存在的不灵敏性和奇异性,可更有效地分析图像分割算法的性能。

关 键 词:图像分割  性能评估  关联度  综合评价  图像处理

Synthetic Performance Evaluation of Image Segmentation Algorithms
LI Bao-zhou,WANG Jian-qi,DENG Yan-ping.Synthetic Performance Evaluation of Image Segmentation Algorithms[J].Journal of Shanghai Jiaotong University,2000,34(6):824-826.
Authors:LI Bao-zhou  WANG Jian-qi  DENG Yan-ping
Abstract:To the performance analyses of image segmentation, a hierarchical synthetic evaluation method was proposed based on the relational grade. Using the method, the performance evaluation can be performed from both the global or local aspects. The metrics for evaluation is hierarchically determined. With the properties of high discreteness, the new method can distinguish the performances from different segmentation algorithms easily. The experiments show that the method has higher sensitivity and lower singularity than other methods, and it can be more effectively used to analyse the performance of segmentation algorithms.
Keywords:image segmentation  performance evaluation  relational grade
本文献已被 CNKI 维普 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