摘要
提出了基于对数极坐标变化、离散傅里叶变换和Contourlet变换的结合方法来实现尺度不变图像检索。首先,对图像进行对数极坐标变换和离散傅里叶变换。然后,应用Contourlet变换提取低频子带特征向量。最后,采用欧氏距离作为相似性度量方式。实验结果表明该方法具有良好的旋转、尺度不变性和抗噪性。
In the paper,we present a method based on log- polar transform,Discrete Fourier transform and Contourlet transform to solve the problem of scale in the image retrieval. Firstly,each image was transform by using log-polar transform and Discrete Fourier transform. Secondly,Contourlet transform is usually used to extract the low frequency feature vector. At last,we use the Euclidean Distance as the similarity measurement. The experimental results show that the method has good rotation,scale invariance and anti-noise.
出处
《自动化与仪器仪表》
2016年第6期196-197,200,共3页
Automation & Instrumentation
