基于WLD的纹理分类研究

Texture Classification Based on Web Local Descriptor

提出了一种基于韦伯局部特征(WLD)的纹理分类方法。韦伯定律证明了人眼感知能力不仅与刺激的改变相关还与刺激的原始大小相关。而韦伯局部特征正是基于这个原理所设计的,能够很好的反映出纹理的特征。实验表明利用韦伯局部特征进行纹理分类效果明显好于利用其它的图像特征。

This paper proposed out a texture classification algorithm based on Web Local Descriptor （WLD）. WLD is based on the Weber’s Law that human perception of a pattern depends on not only the change of a stimulus but also the original intensity of the stimulus. Experimental results show that WLD impressively outperforms the other classical descriptors on texture classification.