Skip to main content
Springer Nature Link
Log in

A Method for Face Image Inpainting Based on Autoencoder and Generative Adversarial Network

  • Conference paper
  • First Online:
Image and Video Technology (PSIVT 2022)

Part of the book series: Lecture Notes in Computer Science ((LNCS,volume 13763))

Included in the following conference series:

  • 438 Accesses

Abstract

Face image inpainting has great value in the fields of computer vision and digital image processing. In this paper, we propose a face image inpainting method based on autoencoder and Generative Adversarial Network (GAN). The neural network for image inpainting consists of two parts, a generator and a discriminator. The autoencoder is used twice in the discriminator part, after the final inpainted image is generated by local discriminator and global discriminator. The final loss function is obtained by combining Generative Adversarial Loss and Mean Squared Error (MSE) Loss [20]. We improve and implement an image inpainting model with two evaluation metrics, namely, Peak Signal-to-noise Ratio (PSNR) and Structural similarity index measure (SSIM) [27], respectively. The proposed model for image inpainting is much more suitable for face image inpainting.

This is a preview of subscription content, log in via an institution to check access.

Access this chapter

Log in via an institution

Subscribe and save

Springer+ Basic
$34.99 /Month
  • Get 10 units per month
  • Download Article/Chapter or eBook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

Similar content being viewed by others

References

  1. Bansal, M., Yan, W.Q., Kankanhalli, M.S.: Dynamic watermarking of images. In: International Conference on Information, Communications and Signal Processing and the Fourth Pacific Rim Conference on Multimedia, vol. 2, pp. 965–969. IEEE (2003)

    Google Scholar 

  2. Bertalmio, M., Sapiro, G., Caselles, V., Ballester, C.: Image inpainting. In: Annual Conference on Computer Graphics and Interactive Techniques, pp. 417–424 (2000)

    Google Scholar 

  3. Chen, Y., et al.: The improved image inpainting algorithm via encoder and similarity constraint. Vis. Comput. 37(7), 1691–1705 (2021)

    Article  Google Scholar 

  4. Creswell, A., White, T., Dumoulin, V., Arulkumaran, K., Sengupta, B., Bharath, A.A.: Generative adversarial networks: an overview. IEEE Signal Process. Mag. 35(1), 53–65 (2018)

    Article  Google Scholar 

  5. Cui, W., Yan, W.Q.: A scheme for face recognition in complex environments. Int. J. Digit. Crime Forensics (IJDCF) 8(1), 26–36 (2016)

    Article  Google Scholar 

  6. Ding, W., Yan, W.Q., Qi, D.X.: Digital image scrambling and digital watermarking technology based on Conway’s game. J. North China Univ. Technol. 12(1), 1–5 (2000)

    Google Scholar 

  7. Gao, X.: A method for face image inpainting based on generative adversarial networks (Masters thesis). Auckland University of Technology, New Zealand (2022)

    Google Scholar 

  8. Gao, X., Nguyen, M., Yan, W.Q.: Face image inpainting based on generative adversarial network. In: International Conference on Image and Vision Computing New Zealand (IVCNZ), pp. 1–6. IEEE (2021)

    Google Scholar 

  9. Givkashi, M.H., Hadipour, M., PariZanganeh, A., Nabizadeh, Z., Karimi, N., Samavi, S.: Image inpainting using AutoEncoder and guided selection of predicted pixels. arXiv preprint arXiv:2112.09262 (2021)

  10. Han, C., Wang, J.: Face image inpainting with evolutionary generators. IEEE Signal Process. Lett. 28, 190–193 (2021)

    Article  Google Scholar 

  11. Iizuka, S., Simo-Serra, E., Ishikawa, H.: Globally and locally consistent image completion. ACM Trans. Graph. (ToG) 36(4), 1–14 (2017)

    Article  Google Scholar 

  12. Le, H., Nguyen, M., Nguyen, Q., Nguyen, H., Yan, W.Q.: Automatic data generation for deep learning model training of image classification used for augmented reality on pre-school books. In: International Conference on Multimedia Analysis and Pattern Recognition (MAPR), pp. 1–5 (2020)

    Google Scholar 

  13. Liang, C., Lu, J., Yan, W.: Human action recognition from digital videos based on deep learning. In: ACM ICCCV 2022 (2022)

    Google Scholar 

  14. Liu, Z., Yan, W.Q., Yang, M.L.: Image denoising based on a CNN model. In: International Conference on Control, Automation and Robotics (ICCAR), pp. 389–393. IEEE (2018)

    Google Scholar 

  15. Liu, Z., Luo, P., Wang, X., Tang, X.: Large-scale celebfaces attributes (CelebA) dataset. Retrieved August, 15(2018), 11 (2018)

    Google Scholar 

  16. Lu, J., Nguyen, M., Yan, W.Q.: Sign language recognition from digital videos using deep learning methods. In: Nguyen, M., Yan, W.Q., Ho, H. (eds.) ISGV 2021. CCIS, vol. 1386, pp. 108–118. Springer, Cham (2021). https://doi.org/10.1007/978-3-030-72073-5_9

    Chapter  Google Scholar 

  17. Lu, J., Yan, W.Q., Nguyen, M.: Human behaviour recognition using deep learning. In: IEEE International Conference on Advanced Video and Signal Based Surveillance (AVSS), pp. 1–6. IEEE (2018)

    Google Scholar 

  18. Mehtab, S., Yan, W.Q.: Flexible neural network for fast and accurate road scene perception. Multimedia Tools Appl. 81(5), 7169–7181 (2022)

    Article  Google Scholar 

  19. Nguyen, M., Yan, W.Q.: Temporal colour-coded facial-expression recognition using convolutional neural network. In: Paiva, S., et al. (eds.) Smart City 360\(^{\circ }\) 2021. LNICST, vol. 442, pp. 41–54. Springer, Cham (2022). https://doi.org/10.1007/978-3-031-06371-8_4

    Chapter  Google Scholar 

  20. Pajot, A., de Bezenac, E., Gallinari, P.: Unsupervised adversarial image inpainting. arXiv preprint arXiv:1912.12164 (2019)

  21. Qin, Z., Yan, W.Q.: Traffic-sign recognition using deep learning. In: Nguyen, M., Yan, W.Q., Ho, H. (eds.) ISGV 2021. CCIS, vol. 1386, pp. 13–25. Springer, Cham (2021). https://doi.org/10.1007/978-3-030-72073-5_2

    Chapter  Google Scholar 

  22. Sara, U., Akter, M., Uddin, M.S.: Image quality assessment through FSIM, SSIM, MSE and PSNR- a comparative study. J. Comput. Commun. 7(3), 8–18 (2019)

    Article  Google Scholar 

  23. Shen, D., Nguyen, M., Yan, W.Q.: Flame detection using deep learning. In: International Conference on Control, Automation and Robotics (ICCAR), pp. 389–393. IEEE (2018)

    Google Scholar 

  24. Shen, Y., Yan, W.Q.: Blind spot monitoring using deep learning. In: International Conference on Image and Vision Computing New Zealand (IVCNZ), pp. 1–5. IEEE (2018)

    Google Scholar 

  25. Siavelis, P.-R., Lamprinou, N., Psarakis, E.Z.: An improved GAN semantic image inpainting. In: Blanc-Talon, J., Delmas, P., Philips, W., Popescu, D., Scheunders, P. (eds.) ACIVS 2020. LNCS, vol. 12002, pp. 443–454. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-40605-9_38

    Chapter  Google Scholar 

  26. Siddavatam, I., Dalvi, A., Pawade, D., Bhatt, A., Vartak, J., Gupta, A.: A novel approach for video inpainting using autoencoders. Int. J. Inf. Eng. Electron. Bus. 13(6), 48–61 (2021)

    Google Scholar 

  27. Tiefenbacher, P., Bogischef, V., Merget, D., Rigoll, G.: Subjective and objective evaluation of image inpainting quality. In: 2015 IEEE International Conference on Image Processing (ICIP), pp. 447–451. IEEE (2015)

    Google Scholar 

  28. Velavan, T.P., Meyer, C.G.: The COVID-19 epidemic. Trop. Med. Int. Health 25(3), 278 (2020)

    Article  Google Scholar 

  29. Wang, H., Yan, W.Q.: Face detection and recognition from distance based on deep learning. In: Aiding Forensic Investigation Through Deep Learning and Machine Learning Frameworks, pp. 144–160. IGI Global (2022)

    Google Scholar 

  30. Wang, L., Yan, W.Q.: Tree leaves detection based on deep learning. In: Nguyen, M., Yan, W.Q., Ho, H. (eds.) ISGV 2021. CCIS, vol. 1386, pp. 26–38. Springer, Cham (2021). https://doi.org/10.1007/978-3-030-72073-5_3

    Chapter  Google Scholar 

  31. Wang, S.Y., Wang, O., Zhang, R., Owens, A., Efros, A.A.: CNN-generated images are surprisingly easy to spot... for now. In: IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 8695–8704 (2020)

    Google Scholar 

  32. Wang, X., Zhang, J., Yan, W.Q.: Gait recognition using multichannel convolution neural networks. Neural Comput. Appl. 32(18), 14275–14285 (2020)

    Article  Google Scholar 

  33. Wang, Y., Yan, W.Q.: Colorizing grayscale CT images of human lungs using deep learning methods. Multimedia Tools Appl. 81, 37805–37819 (2022)

    Article  Google Scholar 

  34. Wei, T., Li, Q., Liu, J., Zhang, P., Chen, Z.: 3D face image inpainting with generative adversarial nets. Math. Probl. Eng. 2020, 1–11 (2020)

    Google Scholar 

  35. Yan, W.Q.: Introduction to Intelligent Surveillance. TCS, Springer, Cham (2019). https://doi.org/10.1007/978-3-030-10713-0

    Book  Google Scholar 

  36. Yan, W.Q.: Computational Methods for Deep Learning: Theoretic Practice and Applications. Springer, Heidelberg (2021). https://doi.org/10.1007/978-3-030-61081-4

    Book  MATH  Google Scholar 

  37. Yan, W.Q., Kankanhalli, M.S.: Erasing video logos based on image inpainting. In: IEEE International Conference on Multimedia and Expo, vol. 2, pp. 521–524. IEEE (2002)

    Google Scholar 

  38. Yan, W.Q., Kankanhalli, M.S.: Face search in encrypted domain. In: Bräunl, T., McCane, B., Rivera, M., Yu, X. (eds.) PSIVT 2015. LNCS, vol. 9431, pp. 775–790. Springer, Cham (2016). https://doi.org/10.1007/978-3-319-29451-3_61

    Chapter  Google Scholar 

  39. Yan, W., Kieran, D.F., Rafatirad, S., Jain, R.: A comprehensive study of visual event computing. Multimedia Tools Appl. 55(3), 443–481 (2011)

    Article  Google Scholar 

  40. Yu, J., Lin, Z., Yang, J., Shen, X., Lu, X., Huang, T.S.: Generative image inpainting with contextual attention. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 5505–5514 (2018)

    Google Scholar 

  41. Yu, J., Lin, Z., Yang, J., Shen, X., Lu, X., Huang, T.S.: Free-form image inpainting with gated convolution. In: IEEE/CVF International Conference on Computer Vision, pp. 4471–4480 (2019)

    Google Scholar 

  42. Yu, Z., Yan, W.Q.: Human action recognition using deep learning methods. In: International Conference on Image and Vision Computing New Zealand (IVCNZ), pp. 1–6. IEEE (2020)

    Google Scholar 

  43. Zeng, Y., Fu, J., Chao, H., Guo, B.: Learning pyramid-context encoder network for high-quality image inpainting. In: IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 1486–1494 (2019)

    Google Scholar 

  44. Zhang, H., Li, T.: Semantic face image inpainting based on generative adversarial network. In: Youth Academic Annual Conference of Chinese Association of Automation (YAC), pp. 530–535. IEEE (2020)

    Google Scholar 

  45. Zhang, Q., Yan, W.Q.: Currency detection and recognition based on deep learning. In: IEEE International Conference on Advanced Video and Signal Based Surveillance (AVSS), pp. 1–6. IEEE (2018)

    Google Scholar 

  46. Zhang, Q., Yan, W.Q., Kankanhalli, M.: Overview of currency recognition using deep learning. J. Banking Financ. Technol 3(1), 59–69 (2019)

    Article  Google Scholar 

  47. Zhang, Z., Cui, P., Zhu, W.: Deep learning on graphs: a survey. IEEE Trans. Knowl. Data Eng. 34, 249–270 (2020)

    Article  Google Scholar 

  48. Zhao, G., Liu, J., Jiang, J., Wang, W.: A deep cascade of neural networks for image inpainting, deblurring and denoising. Multimedia Tools Appl. 77(22), 29589–29604 (2018)

    Article  Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Auckland University of Technology, Auckland, 1010, New Zealand

    Xinyi Gao, Minh Nguyen & Wei Qi Yan

Authors
  1. Xinyi Gao
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Minh Nguyen
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Wei Qi Yan
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Wei Qi Yan .

Editor information

Editors and Affiliations

  1. Xiamen University Malaysia, Sepang, Malaysia

    Han Wang

  2. Singapore Institute of Manufacturing Technology, Singapore, Singapore

    Wei Lin

  3. Charles Sturt University, Bathurst, NSW, Australia

    Paul Manoranjan

  4. Minjiang University, Fuzhou, China

    Guobao Xiao

  5. Yau Lee Holdings Ltd., Hong Kong, Hong Kong

    Kap Luk Chan

  6. Tsinghua University, Beijing, China

    Xiaonan Wang

  7. Nanyang Technological University, Singapore, Singapore

    Guiju Ping

  8. Nanyang Technological University, Singapore, Singapore

    Haoge Jiang

Rights and permissions

Reprints and permissions

Copyright information

© 2023 Springer Nature Switzerland AG

About this paper

Check for updates. Verify currency and authenticity via CrossMark

Cite this paper

Gao, X., Nguyen, M., Yan, W.Q. (2023). A Method for Face Image Inpainting Based on Autoencoder and Generative Adversarial Network. In: Wang, H., et al. Image and Video Technology. PSIVT 2022. Lecture Notes in Computer Science, vol 13763. Springer, Cham. https://doi.org/10.1007/978-3-031-26431-3_3

Download citation

  • DOI: https://doi.org/10.1007/978-3-031-26431-3_3

  • Published:

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-031-26430-6

  • Online ISBN: 978-3-031-26431-3

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics