计算机工程与应用 ›› 2011, Vol. 47 ›› Issue (8): 211-214.

• 工程与应用 • 上一篇    下一篇

木材缺陷识别新方法——改进C-V模型与小波变换

王阿川,仇逊超   

  1. 东北林业大学 信息与计算机工程学院,哈尔滨 150040
  • 收稿日期:1900-01-01 修回日期:1900-01-01 出版日期:2011-03-11 发布日期:2011-03-11

New method of lumber recognition using improved C-V model and wavelet transform

WANG Achuan,QIU Xunchao   

  1. Information and Computer Engineering College,Northeast Forestry University,Harbin 150040,China
  • Received:1900-01-01 Revised:1900-01-01 Online:2011-03-11 Published:2011-03-11

摘要: 分析了木材缺陷、单板节子的特点,提出了一种基于改进的C-V模型、小波变换及背景填充技术的缺陷识别算法。采用symlet5小波,对原图像进行一级二维离散小波变换,分别得到低频分量和高频细节,对低频分量用背景填充技术进行处理得到新的低频图像,分别使用改进的C-V 模型对各子图像识别,利用二维离散小波重构图像,进行Gauss滤波,得到分割结果。

关键词: 木材缺陷, 改进的C-V模型, 小波变换, 多目标分割, 背景填充技术

Abstract: Through analysing the features of lumber defects and the wood veneer,this paper proposes an algorithm of lumber recognition based on improved C-V model,wavelet transform and technique of painting background.The symlet5 wave is used to transform the original image into the primary two-dimension image which can get the high frequency details and the low component.The technique of painting background is used on the low component to make a new image,the improved C-V model is used respectively on the components.It uses the two-dimension wavelet to recover the image and the Gauss filtering on the image which can get the result.

Key words: lumber defects, improved C-V model, wavelet transform, multi-object segmentation, technique of painting background