An Ancient Text Image Inpainting Algorithm via Edge Guide and Laplacian Pyramid Decomposition

被引：0
|
作者：
Liu, Chang [1 ,2 ,3 ]
Zhang, Ling [1 ,2 ,3 ]
He, Yinghao [1 ,2 ,3 ]
机构：
[1] School of Computer Science and Technology, Wuhan University of Science and Technology, Wuhan
[2] Institute of Big Data Science and Engineering, Wuhan University of Science and Technology, Wuhan
[3] Hubei Key Laboratory of Intelligent Information Processing and Real-Time Industrial System, Wuhan
来源：
Jisuanji Fuzhu Sheji Yu Tuxingxue Xuebao/Journal of Computer-Aided Design and Computer Graphics | 2024年 / 36卷 / 06期
关键词：
ancient text images; dual cross-coders; edge images; image inpainting; multiscale fusion blocks;
D O I：
10.3724/SP.J.1089.2024.19865
中图分类号：
学科分类号：
摘要：
Current image inpainting methods are often perform poorly on ancient text images, producing results with blurred textures or incomplete structural content. To address this problem, we propose an inpainting algorithm for ancient text images via edge guide and laplacian pyramid decomposition. We first use an edge restoration module to restore the edge structure for the damaged regions and construct an edge-guided map. Then, we employ the pre-trained text learning module to restore the local damaged regions and obtain a local inpainting image, which is decomposed into a content image and a detail map through laplacian pyramid transform. At last, in the Laplace pyramid restoration module, the content restoration module is used to progressively repair the image according to the low-level and high-level features of the image. The content restoration module introduces a dual cross-encoder and multi-scale fusion blocks to prompt the module to obtain more effective feature information and generate desirable image inpainting results. The superiority quantitative results on the benchmark dataset demonstrate the effectiveness and feasibility of the proposed method, that peak signal to noise ratio (PSNR) is 34.322dB, structural similarity (SSIM) is 0.970 and root mean square error (RMSE) is 5.203. © 2024 Institute of Computing Technology. All rights reserved.
引用
收藏
页码：884 / 894
页数：10
相关论文
共 27 条
  • [1] Zhou Feiyan, Jin Linpeng, Dong Jun, Review of convolutional neural network, Chinese Journal of Computers, 40, 6, pp. 1229-1251, (2017)
  • [2] Albawi S, Mohammed T A, Al-Zawi S., Understanding of a convolutional neural network, Proceedings of the International Conference on Engineering and Technology, pp. 1-6, (2017)
  • [3] Chen L C, Papandreou G, Kokkinos I, Et al., Semantic image segmentation with deep convolutional nets and fully connected CRFs
  • [4] Bertalmio M, Sapiro G, Caselles V, Et al., Image inpainting, Proceedings of the 27th Annual Conference on Computer Graphics and Interactive Techniques, pp. 417-424, (2000)
  • [5] Shen J H, Chan T F., Mathematical models for local nontexture inpaintings, SIAM Journal on Applied Mathematics, 62, 3, pp. 1019-1043, (2002)
  • [6] Tsai A, Yezzi A, Willsky A S., Curve evolution implementation of the Mumford-Shah functional for image segmentation, denoising, interpolation, and magnification, IEEE Transactions on Image Processing, 10, 8, pp. 1169-1186, (2001)
  • [7] Esedoglu S, Shen J H., Digital inpainting based on the Mumford– Shah–Euler image model, European Journal of Applied Mathematics, 13, 4, pp. 353-370, (2002)
  • [8] Potdar V M, Han S, Chang E., A survey of digital image watermarking techniques, Proceedings of the 3rd IEEE International Conference on Industrial Informatics, pp. 709-716, (2005)
  • [9] Zhao Lulu, Shen Ling, Hong Richang, Survey on image inpainting research progress, Computer Science, 48, 3, pp. 14-26, (2021)
  • [10] Criminisi A, Perez P, Toyama K., Region filling and object removal by exemplar-based image inpainting, IEEE Transactions on Image Processing, 13, 9, pp. 1200-1212, (2004)
123