灰度图像相似性匹配是图像检索系统的一个重要组成部分。为了把多尺度分析和通用傅里叶描述子相结合来得到多尺度通用傅里叶描述子，并将其用于灰度图像检索系统对。实验结果表明，多尺度通用傅里叶描述子具有多尺度分析效果，不仅能较好地克服图像灰度噪声带来的干扰，并且具有旋转、比例不变性，在灰度图像检索中能取得较好的结果。

A large number of gray image are created and available on the Web, since more and more gray images and digitizing tools are developed for different applications. The techniques for content-based gray image retrieval is necessary. In gray image retrieval system, we propose multiscale generic Fourier descriptor(MGFD), which integrates generic fourier descriptor with multiscale anslysis.The experimental results show that MGFD is not only capable of multiscale anslysis, but robust against noise and other changes of image and it is also invariant to rotation and scale. It have a precise result in gray image retrieval.