首页 > 论文 > 激光与光电子学进展 > 56卷 > 2期(pp:21005--1)

基于粗糙数据推理的Criminisi图像修复算法

Criminisi Image Inpainting Algorithm Based on Rough Data-Deduction

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

摘要

Criminisi算法作为优秀的图像修复算法代表, 在修复部分破损图像时可获得较好的视觉效果, 但该算法在进行匹配块搜寻时, 待修复块提供的信息量较少, 因此可匹配范围小。针对这一问题, 提出了一种基于粗糙数据推理理论的改进Criminisi图像修复算法, 粗糙数据推理可以扩展搜索空间, 增加搜索数据, 扩大搜索范围, 加深搜索深度。该算法在搜索规则上有以下改进:通过图像结构信息将图像内容划分为一个数据集, 再通过粗糙数据推理扩充待修复块信息量, 扩大匹配块可寻范围, 以此搜索匹配块, 修复破损图像。结果表明, 与经典的Criminisi算法相比, 改进后的算法能够扩展匹配块的数据量, 可搜索到更多数据, 获得较好的视觉效果, 提高了图像的峰值信噪比。

Abstract

The Criminisi algorithm, as one representative of excellent image inpainting algorithms, can used to obtain a better visual effect when partially damaged images are inpainted, but when this algorithm is used to perform the matching block search, the matching range is too small because the amount of information provided by the blocks to be repaired is less during the matching block search. For this problem, an improved Criminisi image inpainting algorithm based on rough data-deduction is proposed, in which rough data-deduction can be used to expand the search space, increase the search data, expand the search scope, and deepen the search depth. The proposed algorithm has some improvements in the search rules. The image content is divided into a dataset according to the structural information of images. The amount of pending repairing information is extended by rough data-deduction. The matching block search range is expanded. Based on these, the matching blocks are searched and the broken images are repaired. The results show that compared with the traditional Criminisi algorithm, the improved algorithm can be used to expand the matching block data sizes, search more data, obtain better visual effects, and improve the peak signal-to-noise ratio of images.

Newport宣传-MKS新实验室计划
补充资料

中图分类号:TP301.6

DOI:10.3788/lop56.021005

所属栏目:图像处理

基金项目:国家自然科学基金(61650207,61741113)

收稿日期:2018-07-05

修改稿日期:2018-07-23

网络出版日期:2018-08-03

作者单位    点击查看

周宁:兰州交通大学电子与信息工程学院, 甘肃 兰州 730070
朱昭昭:兰州交通大学电子与信息工程学院, 甘肃 兰州 730070

联系人作者:周宁(zhouning@mail.lzjtu.cn)

【1】Bertalmio M, Sapiro G, Caselles V, et al. Image inpainting[C]∥SIGGRAPH′00 Proceedings of the 27th Annual Conference on Computer Graphics and Interactive Techniques, July 23-28, 2000, Louisiana. New York: ACM Press, 2000: 417-424.

【2】Fan Q. Image inpainting based on FMM algorithm[D]. Yangzhou: Yangzhou University, 2014: 23-30.
范谦. 基于FMM算法的图像修复[D]. 扬州: 扬州大学, 2014: 23-30.

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

【4】Zhou Y T, Li L, Xia K W. Research on weighted priority of exemplar-based image inpainting[J]. Journal of Electronics (China), 2012, 29(1/2): 166-170.

【5】Li A J, Niu W L. Image inpainting based on improved Criminisi algorithm[J]. Computer Engineering and Applications, 2014, 50(18): 167-170.
李爱菊, 钮文良. 基于改进Criminisi算法的图像修复[J]. 计算机工程与应用, 2014, 50(18): 167-170.

【6】Li Z D, He H J, Yin Z K, et al. Adaptive image inpainting algorithm based on patch structure sparsity[J]. Acta Electronica Sinica, 2013, 41(3): 549-554.
李志丹, 和红杰, 尹忠科, 等. 基于块结构稀疏度的自适应图像修复算法[J]. 电子学报, 2013, 41(3): 549-554.

【7】Wang X N, Wang Z, Wang Y. Improved Criminisi algorithm based on geometry distance[J]. Computer Engineering and Design, 2015, 36(7): 1835-1839, 1895.
王新年, 王哲, 王演. 基于几何距离的Criminisi图像修复算法[J]. 计算机工程与设计, 2015, 36(7): 1835-1839, 1895.

【8】Zhang D, Tang X H, Zhang S P, et al. Image inpainting based on combination of wavelet transform and texture synthesis[J]. Journal of Image and Graphics, 2015, 20(7): 882-894.
张东, 唐向宏, 张少鹏, 等. 小波变换与纹理合成相结合的图像修复[J]. 中国图象图形学报, 2015, 20(7): 882-894.

【9】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.

【10】Le Meur O, Gautier J, Guillemot C. Examplar-based inpainting based on local geometry[C]∥2011 18th IEEE International Conference on Image Processing(ICIP). IEEE, September 11-14, 2011, Brussels. New York: IEEE, 2011: 3401-3404.

【11】Huang C S, Wang M Q, Guo S M. Curvature-driven exemplar-based image inpainting technique[J]. Journal of Fuzhou University(Natural Science Edition), 2012, 40(3): 322-326.
黄陈思, 王美清, 郭淑敏. 曲率驱动的基于样本的图像修补技术[J]. 福州大学学报(自然科学版), 2012, 40(3): 322-326.

【12】Zheng X T, Yuan Y, Lu X Q. Single image super-resolution restoration algorithm fromexternal example to internal self-similarity[J]. Acta Optica Sinica, 2017, 37(3): 0318006.
郑向涛, 袁媛, 卢孝强. 自外而内的单幅图像超分辨率复原算法[J]. 光学学报, 2017, 37(3): 0318006.

【13】Liu J G, Wu Z P, Liu S Q, et al. A merging algorithm for images based on segmentation of feature regions[J]. Journal of Xidian University (Natural Science), 2002, 29(6): 768-771.
刘金根, 吴志鹏, 刘上乾, 等. 一种基于特征区域分割的图像拼接算法[J]. 西安电子科技大学学报(自然科学版), 2002, 29(6): 768-771.

【14】Wang H X, Jiang L, Liang R H, et al. Exemplar-based image inpainting using structure consistent patch matching[J]. Neurocomputing, 2017, 269: 90-96.

【15】Wang W L, Jia Y J. Damaged region filling and evaluation by symmetrical exemplar-based image inpainting for Thangka[J]. EURASIP Journal on Image and Video Processing, 2017: 38-51.

【16】Su J, Li B, Wang Y Z. Infrared image enhancement based on PCNN segmentation and fuzzy set theory[J]. Acta Optica Sinica, 2016, 36(9): 0910001.
苏娟, 李冰, 王延钊. 结合PCNN分割和模糊集理论的红外图像增强[J]. 光学学报, 2016, 36(9): 0910001.

【17】Pawlak Z. Rough sets: theoretical aspects of reasoning about data[M]. Boston: Kluwer Academic Publishers, 1991.

【18】Yan S. Rough data-deduction based on the upper approximation and its applications[D]. Beijing: Beijing Jiaotong University, 2017: 18-39.
闫硕. 基于上近似的粗糙数据推理研究及应用[D]. 北京: 北京交通大学, 2017: 18-39.

【19】Zhou C H, Wang Z L, Liu S K. Method of image restoration directly based on spatial varied point spread function[J]. Acta Optica Sinica, 2017, 37(1): 0110001.
周程灏, 王治乐, 刘尚阔. 基于空间变化点扩展函数的图像直接复原方法[J]. 光学学报, 2017, 37(1): 0110001.

【20】He F Y, Zhao W. Image registration of synthetic aperture radar including body of water[J]. Acta Optica Sinica, 2017,37(9): 0928001.
贺飞跃, 赵伟. 含水体的合成孔径雷达图像配准[J]. 光学学报, 2017, 37(9): 0928001.

引用该论文

Zhou Ning,Zhu Zhaozhao. 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

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