方向场和频率场约束的结构光条纹图像增强算法  

Enhancement Algorithm for Structured-light Stripe Image Based on Orientation and Frequency Fields Constraint

作　　者：郑红波[1,2] 徐玲玲[1] 杜轶诚[1] 秦绪佳[1,2] 陈嵩辉 

机构地区：[1]浙江工业大学计算机科学与技术学院,杭州310032 [2]浙江省可视媒体智能处理技术研究重点实验室,杭州310032 [3]中国航天电子技术研究院,北京100094

出　　处：《计算机科学》2014年第6期299-303,共5页Computer Science

基　　金：国家自然科学基金(61075118)资助

摘　　要：条纹图像增强在指纹图像处理与识别、结构光三维重建中有重要应用。针对结构光三维重建的条纹图像处理,提出了一种基于图像方向场与频率场约束的条纹图像增强算法,设计了图像方向场与频率场的计算方法,构造了方向场与频率场的约束的Gabor滤波器。算法首先对条纹图像进行高斯滤波,去除图像亮度不均匀的影响;然后计算条纹图像的方向场与频率场;最后在图像方向场与频率场的约束下对图像进行Gabor滤波。实验结果表明,算法可有效消除图像光照不均匀的影响,较好地增强结构光图像的条纹信息。Stripe image enhancement has important applications in fingerprint image processing and recognition,structured light 3D reconstruction.This paper focused on stripe image processing of structured-light 3D reconstruction,presented an enhancement algorithm for stripe image based on orientation and frequency fields constraint,designed calculation methods of image orientation and frequency fields,and constructed a Gabor filter based on orientation and frequency fields constraint.The enhancement algorithm includes following steps：firstly uses Gaussian filter to remove the effect of uneven illumination of the image,then calculates the orientation and frequency fields of stripe image,finally uses the Gabor filter to filter the image constrained by orientation and frequency fields.The experimental results show that the algorithm can eliminate the effects of uneven illumination of image effectively and enhance the stripe information of structured-light image preferably.

关 键 词：结构光图像 条纹增强 方向场 频率场 GABOR滤波器 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]