结合小波去噪的THz图像多尺度增强算法研究  

Study of Multi-Scale Enhancement Algorithm for THz Images Combining Wavelet Denoising

作　　者：徐英[1] 洪治[2] 

机构地区：[1]浙江大学光及电磁波研究中心,杭州310058 [2]中国计量学院太赫兹技术与应用研究所,杭州310018

出　　处：《传感技术学报》2011年第3期398-401,共4页Chinese Journal of Sensors and Actuators

基　　金：国家自然科学基金项目(60576042)

摘　　要：针对返波管获得的连续THz透射图像对比度低且噪声大的特点,提出了一种结合小波去噪的多尺度图像增强算法。该算法先用图像金字塔变换对THz图像进行多尺度分解,然后采用指数变换在空域对获得的细节图像进行增强。为减小放大噪声的影响,在重构增强图像的过程中对每一分解层次的近似图像采用小波软阈值方法进行去噪,并对小波图像采用非线性变换进一步增强图像细节。大量实验表明,提出的算法有效地减小了噪声,增强后的THz图像细节分明,边缘清晰,有利于后续的图像处理和识别。Due to low contrast and big noise in continuous-wave THz images obtained by backward-wave oscillator,a multi-scale image enhancement algorithm combining wavelet denoising is proposed.It performs multi-scale decomposition by building image pyramids first,and then enhances the detailed images by exponential transform in spatial domain.To remove the influences of enlarged noises,the wavelet soft-threshold method is adopted to denoise the approximation images in each level of the pyramid when rebuilding the enhanced image.Furthermore,nonlinear transform is also adopted for image enhancement in wavelet domain.Several experimental results demonstrate that,the proposed algorithm can remove noises efficiently,and the enhanced THz images have clear details and sharpened edges,which is useful for further image processing and recognition.

关 键 词：太赫兹图像 增强 多尺度分解 小波去噪 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]