作者投稿和查稿 主编审稿 专家审稿 编委审稿 远程编辑

计算机工程 ›› 2011, Vol. 37 ›› Issue (22): 19-23. doi: 10.3969/j.issn.1000-3428.2011.22.005

• 专栏 • 上一篇    下一篇

基于显著小波子带的轮廓结构不规则性检测

余光光,马 莉,李庆奇   

  1. (杭州电子科技大学生命信息与仪器工程学院,杭州 310018)
  • 收稿日期:2011-06-10 出版日期:2011-11-18 发布日期:2011-11-20
  • 作者简介:余光光(1987-),男,硕士研究生,主研方向:模式识别,人工智能;马 莉,教授、博士;李庆奇,硕士研究生
  • 基金资助:

    国家自然科学基金资助项目(60775016)

Irregularity Detection for Contour Structure Based on Significant Wavelet Sub-band

YU Guang-guang, MA Li, LI Qing-qi   

  1. (College of Life Information and Instrument Engineering, Hangzhou Dianzi University, Hangzhou 310018, China)
  • Received:2011-06-10 Online:2011-11-18 Published:2011-11-20

摘要:

为解决皮肤肿瘤轮廓结构的不规则性表达和特征提取问题,提出一种在重构肿瘤轮廓结构分量上利用局部分形维(LFD)提取轮廓不规则特征的方法。在神经网络中实现肿瘤分类,使用小波分解和Hausdroff Distance确定肿瘤轮廓结构分量所处的频带(显著小波子带),根据重构轮廓结构分量、LFD派生轮廓的不规则性特征对黑色素瘤进行分类。实验结果表明,该方法具有较高的分类准确率、敏感度和特异度。

关键词: 显著小波子带, 结构不规则性, 局部分形维, 肿瘤轮廓, 小波分解, 轮廓重构

Abstract:

With respect to visual character descriptions and extractions of boundary structural irregularity, a novel method is proposed in the paper on a reconstructed structural component of a tumour contour using Local Fractal Dimension(LFD). A neural network is utilized to implement skin tumour classifications on boundary structural irregularity, then by using wavelet decomposition and Hausdroff Distance analysis, frequency bands for structural components of tumour boundaries(significant wavelet sub-bands) are determined, and based on the structural components of reconstructed boundaries, features of irregularity which are extracted from LFD are used for melanomas classification. Experimental results show that the method proposed in the paper has advantages in classification accuracy, specialty and sensitivity.

Key words: significant wavelet sub-band, structural irregularity, local fractal dimension, tumour contour, wavelet decomposition, contour reconstitution

中图分类号: