连续小波变换与视觉不变性的局部化描述

CONTINUOUS WAVELET TRANSFORM AND A LOCAL DESCRIPTOR OF INVARIANCE

视觉不变性描述是计算机视觉的核心问题之一．经典的视觉不变性描述有傅里叶描述器、矩法不变性等，但是它们都是全局性描述，因而极易受局部遮挡与噪声的干扰．文中研究不同尺度的信号在连续小波变换下的性质，并在此基础上提出了一种基于连续小波变换的具有很好局部化性质的视觉不变性描述，解决了局部遮挡条件下的识别问题，并给出了有关实验结果．

Invariance is one of the basic problems in the field of computer vision. Such classical methods as the Fourier descriptors and moments are all global descriptions of objects. The wavelet transform is a vary useful tool in the analysis of the local behavior of signals and images. In this paper, an invariant descriptor based on continuous wavelet transform is presented .Experimental results prove that the new object descriptor has good local behavior as well as global one.