自动化学报2009，Vol.35Issue(5)：505-508,4.DOI:10.3724/SP.J.1004.2009.00505
基于平移不变性类Contoutlet变换的图像分割
The Translation Invariant Contourlet-like Transform for Image Denoising
摘要
Abstract
The contourlet transform with anisotropy and directionality is a new extension to the wavelet transform.Because of its filter bank structure,the contourlet transform is not translation-invariant.In this paper,we propose the translation-invariant contourlet-like transform(TICLT)with lower redundancy than both the noILsubsampled co.ourlet transform(NSCT)and the translation invariant contourlet transform (TICT).The TICLT is constructed by combining the translation invariant Laplacian pyramid and undecimated directional filter banks.The undecimated directionaI filter banks.which satisfy the perfect reconstruction condition.are designed by the mapping approach using one-dimensional fractional splines orthogonal filter banks as prototype filters. We evaluate the performance of the TICLT in image denoising.Some comparisons with the state-of-the-art denoising methods are giyen to illustrate the potential of the TICLT.关键词
Contourlet transform/translation invariant/Laplacian pyramid(LP)/image denoisingKey words
Contourlet transform/translation invariant/Laplacian pyramid(LP)/image denoising分类
信息技术与安全科学引用本文复制引用
练秋生,陈书贞..基于平移不变性类Contoutlet变换的图像分割[J].自动化学报,2009,35(5):505-508,4.基金项目
Supported by National Natural Science Foundation of China (60772079) （60772079）
