Hybrid error concealment method combining exemplar-based image inpainting and spatial interpolation

被引:16
作者
Chung, Byungjin [1 ]
Yim, Changhoon [1 ]
机构
[1] Konkuk Univ, Dept Internet & Multimedia Engn, Seoul, South Korea
基金
新加坡国家研究基金会;
关键词
Image reconstruction; Error concealment; Image inpainting; Spatial interpolation; Video communication; OBJECT REMOVAL; VIDEO; FRAMEWORK;
D O I
10.1016/j.image.2014.09.009
中图分类号
TM [电工技术]; TN [电子技术、通信技术];
学科分类号
0808 ; 0809 ;
摘要
This paper proposes an efficient error concealment method for the reconstruction of pixels that are lost in video communication. The proposed method is developed by combining exemplar-based image inpainting for patch reconstruction and spatial interpolation for pixel reconstruction using adaptive threshold by local complexity. By exemplar-based image inpainting, regions with regular structures are reconstructed. For complex regions with irregular structures, just one pixel is reconstructed using the proposed spatial interpolation method. The proposed spatial interpolation method performs reconstruction by selecting adaptively directional interpolation or neighbor interpolation based on gradient information. Simulation results show that the proposed hybrid method performs reconstruction with significantly improved subjective quality compared with the previous spatial error concealment and image inpainting methods. The proposed method also gives substantial improvements of PSNR compared with the previous methods. (C) 2014 Elsevier B.V. All rights reserved.
引用
收藏
页码:1121 / 1137
页数:17
相关论文
共 50 条
[31]   An efficient forgery detection algorithm for object removal by exemplar-based image inpainting [J].
Liang, Zaoshan ;
Yang, Gaobo ;
Ding, Xiangling ;
Li, Leida .
JOURNAL OF VISUAL COMMUNICATION AND IMAGE REPRESENTATION, 2015, 30 :75-85
[32]   Damaged region filling and evaluation by symmetrical exemplar-based image inpainting for Thangka [J].
Weilan Wang ;
Yanjun Jia .
EURASIP Journal on Image and Video Processing, 2017
[33]   Exemplar-based image inpainting using angle-aware patch matching [J].
Zhang, Na ;
Ji, Hua ;
Liu, Li ;
Wang, Guanhua .
EURASIP JOURNAL ON IMAGE AND VIDEO PROCESSING, 2019, 2019 (1)
[34]   Pixel and Patch Reordering for Fast Patch Selection in Exemplar-Based Image Inpainting [J].
Kim, Baeksop ;
Kim, Jiseong ;
So, Jungmin .
IEICE TRANSACTIONS ON INFORMATION AND SYSTEMS, 2013, E96D (12) :2892-2895
[35]   A joint motion-image inpainting method for error concealment in video coding [J].
Chen, L. Y. ;
Chan, S. C. ;
Shum, H. Y. .
2006 IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING, ICIP 2006, PROCEEDINGS, 2006, :2241-+
[36]   A Fast Exemplar-Based Image Inpainting Method Using Bounding Based on Mean and Standard Deviation of Patch Pixels [J].
So, Jungmin ;
Kim, Baeksop .
IEICE TRANSACTIONS ON INFORMATION AND SYSTEMS, 2015, E98D (08) :1553-1561
[37]   Robust Exemplar-Based Image and Video Inpainting for Object Removal and Region Filling [J].
Pinjarkar, Ashvini V. ;
Tuptewar, D. J. .
COMPUTING, COMMUNICATION AND SIGNAL PROCESSING, ICCASP 2018, 2019, 810 :817-825
[38]   Exemplar-based image inpainting using angle-aware patch matching [J].
Na Zhang ;
Hua Ji ;
Li Liu ;
Guanhua Wang .
EURASIP Journal on Image and Video Processing, 2019
[39]   Exemplar-based inpainting using local binary patterns [J].
Voronin, V. V. ;
Marchuk, V. I. ;
Gapon, N. V. ;
Sizyakin, R. A. ;
Sherstobitov, A. I. ;
Egiazarian, K. O. .
IMAGE PROCESSING: ALGORITHMS AND SYSTEMS XII, 2014, 9019
[40]   Exemplar-based inpainting with rotation invariant patch matching [J].
Boldys, Jiri ;
Besserer, Bernard .
VISAPP 2006: PROCEEDINGS OF THE FIRST INTERNATIONAL CONFERENCE ON COMPUTER VISION THEORY AND APPLICATIONS, VOL 1, 2006, :115-+