何永波

• 1:云南工商学院

摘要(Abstract)：

针对当前较多图像修复方法仅通过对像素点之间的相似差异度进行度量来实现对图像中破损区域的修复、忽略了图像块之间的强度特征、导致修复图像中存在振铃以及不连续等问题,本文设计了一种基于区域结构因子耦合强度特征约束的图像修复方法.首先,通过引导滤波将待修复图像中的噪声进行滤除,以克服图像中噪声干扰引起的错误修复,再根据像素点的梯度特征来构造区域结构因子,以建立优先权函数,测量待修复块优先权,从而确定优先修复块;然后,构造强度特征约束项,将其与误差平方和函数(Sum of Squared Differences,SSD)联合,建立最佳匹配块搜索函数,从相似差异度与强度特征两方面来搜索最佳匹配块;最后,利用像素点之间的差异值,构造置信度更新函数,对其进行更新,进而完成图像修复.实验结果表明,与当前图像修复技术相比,所提方法具有更强的鲁棒性,修复的图像具有更好的视觉效果.

关键词(KeyWords)： 图像修复;区域结构因子;强度特征约束;误差平方和函数;最佳匹配块;置信度更新函数

Abstract:

Keywords:

基金项目(Foundation): 云南省自然科学基金项目(2017FB09)

作者(Author): 何永波

DOI: 10.13568/j.cnki.651094.2018.04.009

参考文献(References)：

• [1]卫星,周瑜龙,焦蓬蓬.基于置信特征与结构相似度约束的图像修复算法[J].新疆大学学报(自然科学版),2018,35(2):203-208.
• [2]Prananta Edwin.GPU CUDA Accelerated Image Inpainting Using Fourth Order PDE Equation[J].TELKOMNIKATelecommunication,Computing,Electronics and Control,2016,14(3):1009-1015.
• [3]Liu Ying,Liu Chanjuan,Zou Hailin.A New Structure Tensor Based Image Inpainting Algorithm[J].International Journal of Grid and Utility Computing,2016,7(4):294-303.
• [4]Chen Daiqiang,Zhou Yan.Inexact Alternating Direction Method Based on Proximity Projection Operator for Image Inpainting in Wavelet Domain[J].Neurocomputing,2016,189(12):145-159.
• [5]屠昕,钮圣虓,陈更生.一种基于分水岭分割的快速图像修复算法[J].复旦学报(自然科学版),2017,56(1):57-70.
• [6]Muhannad Tariq.Rician Noise Reduction in Magnetic Resonance Images Using Adaptive Non-local Mean and Guided Image Filtering[J].Optical Review,2016,23(3):460-469.
• [7]Liu Shuaiqi,Shi Mingzhu,Zhu Zhihui.Image Fusion Based on Complex-shearlet Domain with Guided Filtering[J].Multidimensional Systems and Signal Processing,2017,28(1):207-224.
• [8]Kuo Pinchen,Lin Jhihming.High Efficiency Depth Image-Based Rendering with Simplified Inpainting-Based Hole Filling[J].Multidimensional Systems and Signal Processing,2016,27(3):623-645.
• [9]郑玉婷,吴谨.基于蚁群算法的Criminisi图像修复[J].红外技术,2017,39(3):221-225.
• [10]Lee Jungsan,Wei Kuojui,Wen Kairui.Image Structure Rebuilding Technique Using Fractal Dimension on the Best Match Patch Searching[J].Multimedia Tools and Applications,2017,76(2):1875-1899.
• [11]Anam Akbar,Muhammad Sarim.Coherent Spatial and Color Blended Exemplar Inpainting[J].Mehran University Research Journal of Engineering and Technology,2017,36(2):225-232.
• [12]胡导林,蔡述庭,罗斌玲.基于灰度熵的样本块图像修复算法研究[J].自动化技术与应用,2017,36(3):59-63.
• [13]He Kai,Gao Junqiao,Lu Wenxia.Image Inpainting Algorithm Based on Improved Confidence Function and Matching Criterion[J].Journal of Tianjin University,2017,50(4):399-404.
• [14]FranciscoJ Ibarrolaruben.A Two-step Mixed Inpainting Method with Curvature-Based Anisotropy and Spatial Adaptively[J].Inverse Problems and Imaging,2017,11(2):247-262.
• [15]Wang Haixia,Jiang Li,Liang Ronghua.Exemplar-Based Image Inpainting Using Structure Consistent Patch Matching[J].Neurocompting,2017,269(20):90-96.
• [16]唐利明,谭艳婷,方壮.基于结构分量和信息熵的Criminisi图像修复算法[J].光电子·激光,2017,28(1):108-116.
• [17]Dai Lei,Jiang Daihong,Ding Bin.Improved Digital Image Restoration Algorithm Based on Criminisi[J].Journal of Digital Information Management,2016,14(5):302-310.
• [18]Li Shuaijie,Yang Xiaohui.Novel Image Inpainting Algorithm Based on Adaptive Fourth-Order Partial Differential Equation[J].IET Image Processing,2017,11(10):870-879.
• [19]Vadim Fedorov,Pablo Arias,Gabriele Facciolo.Exemplar-Based Image Inpainting Using an Affine Invariant Similarity Measure[J].Computer Vision,Imaging and Computer Graphics Theory and Applications,2017,693(2):454-474.
• [20]王文霞,王春红,葛少磊.基于广义回归神经网络的图像修复算法[J].计算机工程与设计,2017,38(11):3125-3130.