首页    期刊浏览 2024年11月30日 星期六
登录注册

文章基本信息

  • 标题:Evaluation of single and multi-threshold entropybased algorithms for folded substrate analysis
  • 本地全文:下载
  • 作者:Magdolna Apro ; Szabolcs Pal ; Sandra Dedijer
  • 期刊名称:Journal of Graphic Engineering and Design
  • 印刷版ISSN:2217-379X
  • 电子版ISSN:2217-9860
  • 出版年度:2011
  • 卷号:2
  • 期号:2
  • 页码:1-9
  • 出版社:University of Novi Sad
  • 摘要:This paper presents a detailed evaluation of two variants of Maximum Entropy image segmentation algorithm (single and multi-thresholding) with respect to their performance on segmenting test images showing folded substrates. The segmentation quality was determined by evaluating values of four different measures: misclassification error, modified Hausdorff distance, relative foreground area error and positive-negative false detection ratio. New normalization methods were proposed in order to combine all parameters into a unique algorithm evaluation rating. The segmentation algorithms were tested on images obtained by three different digitalisation methods covering four different surface textures. In addition, the methods were also tested on three images presenting a perfect fold. The obtained results showed that Multi-Maximum Entropy algorithm is better suited for the analysis of images showing folded substrates.
国家哲学社会科学文献中心版权所有