局部特定空间关系统计特征的RVIN噪声检测器  

Random-valued impulse noise detector using local spatial structure statistics

作　　者：于海雯[1] 易昕炜 徐少平[1] 林珍玉 刘蕊蕊 Yu Haiwen;Yi Xinwei;Xu Shaoping;Lin Zhenyu;Liu Ruirui(School of Information Engineering,Nanchang University,Nanchang 330031,China)

机构地区：[1]南昌大学信息工程学院,南昌330031

出　　处：《中国图象图形学报》2020年第12期2494-2504,共11页Journal of Image and Graphics

基　　金：国家自然科学基金项目(61662044,61163023,51765042);江西省自然科学基金项目(20171BAB202017)。

摘　　要：目的随机脉冲噪声(random-valued impulse noise,RVIN)检测器将局部图像统计值(local image statistics,LIS)作为图块中心像素点是否为噪声的判断依据,但LIS的描述能力较弱在不同程度上制约了RVIN检测器的检测正确率,影响了后续开关型降噪模块的修复效果。为此提出了一种基于局部特定空间关系统计特征的RVIN噪声检测器。方法以局部中心像素点的8个邻域像素对数差值排序值(rank-ordered logarithmic difference,ROLD)并结合1个最小方向对数差值(minimum orientation logarithmic difference,MOLD)共9个反映局部特定空间关系的LIS统计值构成描述中心像素点是否为RVIN的噪声感知特征矢量,并通过在大量样本图块数据上提取的RVIN噪声感知特征矢量及其对应的噪声标签作为训练对(training pairs),训练获得一个基于多层感知网络(multi-layer perception,MLP)的RVIN噪声检测器。结果对比实验从检测正确率和实际应用效果2个方面检验所提出的RVIN检测器的有效性,分别在10幅常用图像和50幅BSD(Berkeley segmentation data)纹理图像上进行测试,并与经典的脉冲噪声降噪算法中包含的噪声检测器以及MLPNNC(MLP neural network classifier)噪声检测器相比较,以漏检数、误检数和错检总数作为评价噪声检测正确率的指标。在常用图像集上本文所提RVIN检测器的漏检数和误检数较为平衡在错检总数上排名处于所有对比算法中的前2名,为后续的降噪模块打下了很好的基础。在BSD纹理图像集上将本文提出的RVIN检测器和GIRAF(generic iteratively reweighted annihilating filter)算法组合构成一种RVIN噪声降噪算法(proposed-GIRAF),proposed-GIRAF算法在50幅BSD图像上的峰值信噪比(peak signal-to-noise ratio PSNR)均值在各个噪声比例下均取得了最优结果,与排名第2的对比算法相比,提升了0.47~1.96 dB。实验数据表明所提出的RVIN噪声检测器的检测正确率优于现有的检测器,与Objective Random-valued impulse noise(RVIN)is a common cause of image degradation that is frequently observed in images captured by digital camera sensors.In addition to degrading image quality,this type of noise also leads to pixel failure and inaccurate storage location or transmission.The presence of impulse noise may also introduce difficulties in feature extraction,target tracking,image classification,and subsequent image processing and analysis works.For RVIN,the noise value of a corrupted pixels uniformly distributed between 0 and 255.In this case,detecting the RVIN is very difficult.The available local image statistics for RVIN detection,which are used to determine whether the center pixel of an image patch is corrupted by RVIN noise or not,have are latively weak description ability,thereby restricting their accuracy to some extent and affecting the restoration performance of subsequent switching RVIN denoising modules.Method Nine local image statistics,including eight neighbor rank-ordered logarithmic difference(ROLD)statistics and one minimum orientation logarithmic difference(MOLD)statistics,were used to construct a highly sensitive RVIN noise-aware feature vector that can describe the RVIN likeness of the center pixel of a given patch.Based on this vector,RVIN noiseaware feature vectors extracted from numerous noisy patches,their corresponding noise labels were formed as a set of training pairs for a multi-layer perception(MLP)network,and the MLP-based RVIN detector was trained.Result Comparative experiments were performed to test the estimation accuracy and denoising effect of the proposed RVIN detector.The proposed detector was compared with several state-of-the-art image denoising methods,including progressive switching median filter(PSMF),ROLD-edge preserving regularization(ROLD-EPR),adaptive switching median(ASWM),robust outlyingness ratio nonlocal means(ROR-NLM),MLP-edge preserving regularization(MLP-EPR),convolutional neural network based(CNN-based),blind convolutional neural network(BCNN),and

关 键 词：图像降噪 随机脉冲噪声 局部空间结构关系 8邻域对数差值排序值 最小方向对数差值 多层感知网络 检测正确率 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]