首页 > 论文 > 激光与光电子学进展 > 57卷 > 22期(pp:221006--1)

基于信息熵和梯度因子的改进Criminisi图像修复方法

An Improved Criminisi Image Inpainting Method Based on Information Entropy and Gradient Factor

  • 摘要
  • 论文信息
  • 参考文献
  • 被引情况
  • PDF全文
分享:

摘要

针对传统Criminisi算法中优先权值很快趋于零,且修复时间较长等缺点,提出一种改进的基于信息熵和梯度因子的图像修复算法。首先,将图像信息熵与梯度因子拟合为权重因子,采用优化优先权的计算方式找到最优修复块;其次,利用可度量像素块复杂度的信息熵对匹配块的搜索区域进行调整,建立搜索区域的动态法则;然后,借助于梯度因子建立匹配块模板尺寸的自适应模型,完善最优匹配块搜索策略;最后,引入序贯相似性检测算法从源区域中选取最优匹配块,实现图像的修复。实验结果表明,与传统Criminisi算法相比,所提算法无论在客观方面还是在主观方面都获得了较满意的图像修复结果,修复效果更加真实,修复图像具有更好的视觉效果。

Abstract

In order to solve the shortcomings of the traditional Criminisi algorithm which the priority value tends to zero quickly and costs much inpainting time, an improved image inpainting algorithm is proposed based on information entropy and gradient factor. Firstly, the information entropy and the gradient factor for the image are fitted as weight factors, and the priority calculation method is optimized to find the optimal inpainting block. Secondly, the information entropy which can measure the complexity of the pixel block is used to adjust the search area of the matching block to establish a dynamic rule of the search area. Then, an adaptive model of the template size for the matching block is established with the help of the gradient factor to improve the optimal matching block search strategy. Finally, the sequential similarity detection algorithm is introduced to select the optimal matching block from the source region to achieve image inpainting. The experimental results show that compared with the traditional Criminisi algorithm, the proposed algorithm is effective both at the objective level and the subjective level. Moreover, the effectiveness of the image inpainting is more real, and the restored image has better visual effects.

广告组1 - 空间光调制器+DMD
补充资料

中图分类号:TP391.4

DOI:10.3788/LOP57.221006

所属栏目:图像处理

基金项目:安徽省自然科学基金、安徽高校省级自然科学研究重点项目;

收稿日期:2020-02-11

修改稿日期:2020-03-31

网络出版日期:2020-11-01

作者单位    点击查看

王凤随:教育部高端装备先进感知与智能控制重点实验室, 安徽 芜湖 241000安徽省电气传动与控制重点实验室, 安徽 芜湖 241000安徽工程大学电气工程学院, 安徽 芜湖 241000
刘正男:教育部高端装备先进感知与智能控制重点实验室, 安徽 芜湖 241000安徽省电气传动与控制重点实验室, 安徽 芜湖 241000安徽工程大学电气工程学院, 安徽 芜湖 241000
付林军:教育部高端装备先进感知与智能控制重点实验室, 安徽 芜湖 241000安徽省电气传动与控制重点实验室, 安徽 芜湖 241000安徽工程大学电气工程学院, 安徽 芜湖 241000

联系人作者:王凤随(fswang@ahpu.edu.cn)

备注:安徽省自然科学基金、安徽高校省级自然科学研究重点项目;

【1】Zhang S Y, Li C L. Thick cloud restoration of aerial images based on improved criminisi algorithm [J]. Laser & Optoelectronics Progress. 2018, 55(12): 121012.
张思雨, 李从利. 基于改进Criminisi算法的航拍图像厚云修复 [J]. 激光与光电子学进展. 2018, 55(12): 121012.

【2】Zhang Q B, Zhang X H, Han H W. Backscattered light repairing method for underwater laser image based on improved generative adversarial network [J]. Laser & Optoelectronics Progress. 2019, 56(4): 041004.
张清博, 张晓晖, 韩宏伟. 基于改进生成对抗网络的水下激光图像后向散射光修复方法 [J]. 激光与光电子学进展. 2019, 56(4): 041004.

【3】Zeng J X, Wang C. Image completion based on redefined priority and image Division [J]. Journal of Image and Graphics. 2017, 22(9): 1183-1193.
曾接贤, 王璨. 基于优先权改进和块划分的图像修复 [J]. 中国图象图形学报. 2017, 22(9): 1183-1193.
Zeng J X, Wang C. Image completion based on redefined priority and image Division [J]. Journal of Image and Graphics. 2017, 22(9): 1183-1193.
曾接贤, 王璨. 基于优先权改进和块划分的图像修复 [J]. 中国图象图形学报. 2017, 22(9): 1183-1193.

【4】Zhou N, Zhu Z Z. Criminisi image inpainting algorithm based on rough data-deduction [J]. Laser & Optoelectronics Progress. 2019, 56(2): 021005.
周宁, 朱昭昭. 基于粗糙数据推理的Criminisi图像修复算法 [J]. 激光与光电子学进展. 2019, 56(2): 021005.

【5】Wang P Y, Zhao D H, Li M F. Optical camouflage effect assessment based on digital image inpainting technology [J]. Laser & Optoelectronics Progress. 2018, 55(3): 031011.
王鹏烨, 赵德辉, 李明锋. 基于图像修复技术的目标可见光伪装效果评价 [J]. 激光与光电子学进展. 2018, 55(3): 031011.

【6】Bertalmio M, Sapiro G, Caselles V, et al. Image inpainting[C]∥Proceedings of the 27th annual conference on Computer graphics and interactive techniques - SIGGRAPH ''''00. Not Known. New York: , 2000, 417-424.

【7】Shen J, Chan T F. Mathematical models for local nontexture inpaintings [J]. Siam Journal on Applied Mathematics. 2002, 62(3): 1019-1043.

【8】Chan T F, Shen J J. Image processing and analysis [M]. Philadelphia: Society for Industrial and Applied Mathematics. 2005.

【9】Chan T F, Shen J H. Nontexture inpainting by curvature-driven diffusions [J]. Journal of Visual Communication and Image Representation. 2001, 12(4): 436-449.

【10】He K, Zhang T, Liang R. Improved image inpainting algorithm based on total variation model [J]. Journal of Optoelectronics.Laser. 2010, 21(12): 1890-1893.
何凯, 张涛, 梁然. 一种基于全变分模型的图像修复改进算法 [J]. 光电子.激光. 2010, 21(12): 1890-1893.

【11】Zhao Y W, Li X L. A rapid Image Inpainting algorithm based on TV model [J]. Microelectronics & Computer. 2009, 26(6): 253-256, 260.
赵颜伟, 李象霖. 一种基于TV模型的快速图像修复算法 [J]. 微电子学与计算机. 2009, 26(6): 253-256, 260.

【12】Zhao Y W, Li X L. A rapid image inpainting algorithm based on CDD model [J]. Computer Simulation. 2008, 25(10): 223-227.
赵颜伟, 李象霖. 基于CDD模型的快速图像修复算法 [J]. 计算机仿真. 2008, 25(10): 223-227.

【13】Lian X L, Xu Z Y, Feng L L, et al. Novel image inpainting based on partial differential equation [J]. Computer Engineering. 2009, 35(6): 234-236.
廉晓丽, 徐中宇, 冯丽丽, 等. 一种新的基于偏微分方程的图像修复 [J]. 计算机工程. 2009, 35(6): 234-236.

【14】Criminisi A, Perez P, Toyama K. Region filling and object removal by exemplar-based image inpainting [J]. IEEE Transactions on Image Processing. 2004, 13(9): 1200-1212.

【15】Zhao L, Zhang W, Sun Z G, et al. Brake pad image classification algorithm based on color segmentation and information entropy weighted feature matching [J]. Journal of Tsinghua University (Science and Technology). 2018, 58(6): 547-552.
赵磊, 张文, 孙振国, 等. 基于色彩分割及信息熵加权特征匹配的刹车片图像分类算法 [J]. 清华大学学报(自然科学版). 2018, 58(6): 547-552.

【16】Tian X, Li T, Tian J W, et al. Prediction method for image coding quality based on differential information entropy [J]. Entropy. 2014, 16(2): 990-1001.

【17】Liu X G, Chen X, Chen Z W, et al. Research on SSDA matching algorithm based on image greyscale [J]. Aeronautical Computing Technique. 2010, 40(1): 54-57.
刘晓光, 陈曦, 陈政伟, 等. 基于图像灰度的SSDA匹配算法 [J]. 航空计算技术. 2010, 40(1): 54-57.

【18】Biradar R L, Kohir V V. A novel image inpainting technique based on median diffusion [J]. Sadhana. 2013, 38(4): 621-644.

【19】Martínez-Noriega R, Roumy A, Blanchard G. Exemplar-. based image inpainting: , 2012, 1-6.

【20】Bugeau A, Bertalmío M, Caselles V, et al. A comprehensive framework for image inpainting [J]. IEEE Transactions on Image Processing. 2010, 19(10): 2634-2645.

引用该论文

Wang Fengsui,Liu Zhengnan,Fu Linjun. An Improved Criminisi Image Inpainting Method Based on Information Entropy and Gradient Factor[J]. Laser & Optoelectronics Progress, 2020, 57(22): 221006

王凤随,刘正男,付林军. 基于信息熵和梯度因子的改进Criminisi图像修复方法[J]. 激光与光电子学进展, 2020, 57(22): 221006

您的浏览器不支持PDF插件,请使用最新的(Chrome/Fire Fox等)浏览器.或者您还可以点击此处下载该论文PDF