摘要
在总结以往研究的基础上,结合图像分块理论,提出一种新的木材颜色特征提取方法。该方法基于提升小波变换提取木材表面的颜色信息,最终形成12个特征参数。为了验证特征提取的有效性,采用了径向基函数神经网络、概率神经网络和支持向量机三种分类器,最终实验仿真的分类效果很好,验证了这种新的颜色特征提取方法的有效性。
A new wood color feature extraction method combining image block theory was given on the basis of the previous studies. The method was based on lifting wavelet transform to extract the wood surface color information and 12 characteristic parameters were formed eventually. In order to verify the effectiveness of the feature extraction, simulation experiments used Radial Basis Function (RBF) neural network, Probabilistic Neural Network (PNN) and Support Vector Machine (SVM). The results of experiments validate the effectiveness of the new color feature extraction method.
出处
《计算机应用》
CSCD
北大核心
2009年第B12期218-219,255,共3页
journal of Computer Applications
基金
黑龙江省自然科学基金资助项目(F200920
F200816)
哈尔滨市自然科学基金资助项目(2004AFXXJ020)
关键词
图像处理
提升小波变换
图像分块
颜色特征
木材分类
image processing
lifting wavelet transform
image block
color characteristic
wood classification