粒子群优化的Contourlet域数字全息再现像增强  

Reconstructed Image Enhancement of Digital Holography in Contourlet Domain Based on Particle Swarm Optimization

作　　者：吴一全[1,2] 殷骏[1] 

机构地区：[1]南京航空航天大学电子信息工程学院,江苏南京210016 [2]瞬态光学与光子技术国家重点实验室,陕西西安710068

出　　处：《中国激光》2013年第8期185-191,共7页Chinese Journal of Lasers

基　　金：国家自然科学基金(60872065);瞬态光学与光子技术国家重点实验室开放基金(SKLST201007);江苏高校优势学科建设工程资助项目

摘　　要：对数字全息再现像存在对比度低、边缘纹理不清晰、含散斑噪声等问题,提出了基于均匀搜索粒子群优化的Contourlet域数字全息再现像自适应增强方法。利用中值滤波算法抑制再现像中的散斑噪声,经Contourlet分解后,对带通方向子带利用非线性增益函数进行边缘增强;低通子带系数的调整则依据基于灰度级变换和局部均值的增益函数,其中灰度级变换使图像暗区扩展,利用均匀搜索粒子群优化搜寻待定参数,适应度函数兼顾了图像的对比度、清晰度及峰值信噪比。大量实验结果表明,与现有的三种增强方法相比,该方法能更有效地提高数字全息再现像的对比度和清晰度,突出边缘纹理并抑制散斑噪声,提高数字全息术测量的准确度。Aiming at the problem of low contrast, blurred edges and textures, and speckle noise of reconstructed image in digital holography, an adaptive enhancement method for reconstructed image of digital holography in contourlet domain based on uniform searching particle swarm optimization is proposed. Median filtering algorithm is used to suppress speckle noise of the reconstructed image. After the contourlet decomposition, edge enhancement is performed for the band-pass directional subbands by a nonlinear gain function. While the coefficients of low-pass subbands are adjusted by the gain function based on a gray-scale transform and the local mean. The gray-scale transform aims to expand the dark areas of digital holographic image. The undetermined parameters are found by uniform searching particle swarm optimization. The fitness function takes into account the contrast, definition and peak signal-to-noise ratio of image. A large number of experimental results show that, compared with three existing enhancement methods, the proposed method can more effectively improve the contrast and definition of reconstructed image in digital holography, highlight edges and textures, and suppress speckle noise. As a result, the measurement accuracy of digital holography can be improved.

关 键 词：全息 图像自适应增强 CONTOURLET变换 灰度级变换 均匀搜索粒子群优化 散斑噪声 

分 类 号：O438.1[机械工程—光学工程] TN911.73[理学—光学]