Damaged region filling and evaluation by symmetrical exemplar-based image inpainting for Thangka

被引:9
|
作者
Wang, Weilan [1 ]
Jia, Yanjun [1 ]
机构
[1] Northwest Univ Nationalities, Sch Math & Comp Sci, 1 Xibei Xincun, Lanzhou 730030, Gansu, Peoples R China
基金
中国国家自然科学基金;
关键词
Symmetrical exemplar-based; Symmetrical similarity; Image inpainting; Objective evaluation; PARALLEL FRAMEWORK; OBJECT REMOVAL; ALGORITHM;
D O I
10.1186/s13640-017-0186-1
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
Exemplar-based image inpainting, as proposed by Criminisi et al. (IEEE Trans Image Process 13(9): 1200-1212, 2004), fills missing regions by using a similar exemplar. However, when the missing region is a unique texture patch, an incorrect texture is filled in the missing region because a similar exemplar of damaged patch could not be found. A new image inpainting method based on an eight-direction or arbitrary direction symmetrical exemplar is proposed, suitable for damaged images containing local symmetry. The following three steps are the keys of this method. (1) According to certain similarity criteria, the symmetrical exemplars of damaged regions in eight directions or arbitrary directions are found. (2) The most similar symmetrical exemplar is selected from eight-direction or arbitrary-direction symmetrical exemplars. (3) Finally, the damaged region is filled using the most similar symmetrical exemplar. It is shown that the results of image inpainting are good when missing image regions have similar symmetry. Image inpainting is a single, efficient method. In addition, a new evaluation method of image restoration results based on similar exemplars is proposed for the inpainting effect, which is closely related to the repair algorithm. Therefore, the methods can more objectively measure the inpainting effect.
引用
收藏
页数:13
相关论文
共 50 条
  • [21] An improved image quality algorithm for exemplar-based image inpainting
    Alan Anwer Abdulla
    Mariwan Wahid Ahmed
    Multimedia Tools and Applications, 2021, 80 : 13143 - 13156
  • [22] Image inpainting using layered fusion and exemplar-based
    Wang, Keke
    Ma, Ran
    Bo, Dezhi
    An, Ping
    OPTOELECTRONIC IMAGING AND MULTIMEDIA TECHNOLOGY VI, 2019, 11187
  • [23] RESEARCH ON WEIGHTED PRIORITY OF EXEMPLAR-BASED IMAGE INPAINTING
    Zhou Yatong Li Lin Xia Kewen School of Information Engineering Hebei University of Technology Tianjin China
    JournalofElectronics(China), 2012, 29(Z1) (China) : 166 - 170
  • [24] Application of Exemplar-Based Inpainting in Depth Image Based Rendering
    AshaJayachandran
    Preetha, V. H.
    2016 IEEE INTERNATIONAL CONFERENCE ON RECENT TRENDS IN ELECTRONICS, INFORMATION & COMMUNICATION TECHNOLOGY (RTEICT), 2016, : 1117 - 1121
  • [25] ANALYSIS OF A VARIATIONAL FRAMEWORK FOR EXEMPLAR-BASED IMAGE INPAINTING
    Arias, P.
    Caselles, V.
    Facciolo, G.
    MULTISCALE MODELING & SIMULATION, 2012, 10 (02): : 473 - 514
  • [26] Temporal extension to exemplar-based inpainting applied I to scratch correction in damaged image -sequences
    Forbin, G
    Besserer, B
    Boldys, J
    Tschumperlé, D
    PROCEEDINGS OF THE FIFTH IASTED INTERNATIONAL CONFERENCE ON VISUALIZATION, IMAGING, AND IMAGE PROCESSING, 2005, : 62 - 66
  • [27] Exemplar-Based Image Inpainting Based on Pixel Inhomogeneity Factor
    Fan, Qinhui
    Liu, Hongsheng
    Fu, Zhizhong
    Li, Xiaofeng
    2017 ASIA-PACIFIC SIGNAL AND INFORMATION PROCESSING ASSOCIATION ANNUAL SUMMIT AND CONFERENCE (APSIPA ASC 2017), 2017, : 1164 - 1168
  • [28] Improvement of the exemplar-based inpainting
    Huang, Weijie
    Zhang, Guoshan
    JOURNAL OF ELECTRONIC IMAGING, 2016, 25 (05)
  • [29] A novel patch matching algorithm for exemplar-based image inpainting
    Fan, Qian
    Zhang, Lifeng
    MULTIMEDIA TOOLS AND APPLICATIONS, 2018, 77 (09) : 10807 - 10821
  • [30] Exemplar-Based Inpainting Driven by Feature Vectors and Region Segmentation
    Park, Jinki
    Park, Jaehwa
    Kwon, Young-Bin
    Lee, Chan-Gun
    Park, Ho-Hyun
    IEICE TRANSACTIONS ON INFORMATION AND SYSTEMS, 2015, E98D (04): : 972 - 975