基于形状的小波变换系数广义高斯分布图像检索算法

Wavelet Coefficients Generalized Gaussian Distribution Image Retrieval Algorithm Based on Shape

本文提出一种基于小波变换系数的广义高斯密度分布形状检索算法 .该算法充分利用小波变换变换系数的统计特性 ,形成描述形状特征的特征矢量 .实验证明 ,算法提出的描述方式能够有效体现物体形状特征 .同时 ,算法对于形状的尺度变化 ,平移变化以及旋转变化有着很好的抑制能力 .该算法简单 ,有效 ,是一种有效的基于形状的图像检索算法 .

An image retrieval method based on shape was proposed by using wavelet coefficients Gaussian density distribution.This approach forms the feature vector of the shape by taking advantage of the statistical attribution of wavelet transformation coefficients.Experimental results show that the extracted feature vector can depict the shape outline accurately,and remain invariant to the image's scale and rotation.It is an efficient image retrieval method based on the shape content.