Remoción de lluvia en imágenes por medio de una arquitectura de autoencoder

Contenido principal de artículos

Alberto Ceballos-Arroyo
Sergio Robles-Serrano
German Sanchez Torres https://orcid.org/0000-0002-9069-0732

Palabras clave

Image processing, noise removal, rain removal, autoencoder

Resumen

Objetivo: Usar técnicas computacionales para eliminar lluvia en imágenes. La motivación viene dada por el hecho de que, para muchos sistemas de visión por computadora, capturar correctamente la escena es clave, y si estos sistemas reciben imágenes degradadas por lluvia como entrada, su funcionamiento puede verse comprometido. Metodología: Se creó un conjunto de datos compuesto por 11000 imágenes sintéticas de lluvia. Estas fueron redimensionadas y normalizadas, para luego utilizar 9000 de ellas como conjunto de entrenamiento en la arquitectura autoencoder. El autoencoder genera una versión sin lluvia de la imagen, la cual es pasada a una etapa de corrección de iluminación para producir la imagen final sin lluvia. Resultados: Se encontró que el mejor desempeño lo tenía el autoencoder de 6 capas. Se evaluó con las 2000 imágenes restantes, lo que resultó en un error cuadrático medio de 0,61 y un índice de similitud estructural de 0,8493, lo que significa que el modelo fue capaz de recuperar una gran cantidad de información original de las imágenes degradadas por la lluvia. Conclusiones: Los resultados obtenidos son superiores a aquellos de la literatura que se basan en el dominio espacial / frecuencial. Se determinó, sin embargo, que es posible obtener mejores resultados si se considera el dominio de la frecuencia como parte de la arquitectura, debido a las propiedades de esta. Por lo tanto, se propone como trabajo futuro combinar enfoques basados en el aprendizaje de máquina con el procesamiento de imágenes basado en el dominio de la frecuencia.

Abstract 106 | PDF Downloads 66

Referencias

1. K. Park, S. Yu, and J. Jeong, “A contrast restoration method for effective single image rain removal algorithm,” 2018 Int. Work. Adv. Image Technol. IWAIT 2018, pp. 1–4, 2018. https://doi.org/10.1109/IWAIT.2018.8369644.

2. P. X. Minmin Shen, “A fast algorithm for rain detection and removal from videos,” Current, pp. 1–6, 2011. https://doi.org/10.1109/ICME.2011.6011963.

3. Y. Sun, X. Duan, H. Zhang, and Y. Zhijing, “A Removal Algorithm of Rain and Snow from Images Based on Fuzzy Connectedness,” in International Conference on Computer Application and System Modeling, , vol. 5, pp. 478–48 2010.

4. Y. Wang, S. Liu, C. Chen, and B. Zeng, “A Hierarchical Approach for Rain or Snow Removing in a Single Color Image,” IEEE Trans. Image Process., vol. 26, no. 8, pp. 3936–3950, 2017. https://doi.org/10.1109/TIP.2017.2708502.

5. H. Dong and X. Zhao, “Detection and removal of rain and snow from videos based on frame difference method,” Proc. 2015 27th Chinese Control Decis. Conf., pp. 5139–5143, 2015. https://doi.org/10.1109/CCDC.2015.7162843.

6. J. Xu, W. Zhao, P. Liu, and X. Tang, “Removing rain and snow in a single image using guided filter,” in 2012 IEEE International Conference on Computer Science and Automation Engineering, 2012, vol. 2, no. 2, pp. 304–307. https://doi.org/10.1109/CSAE.2012.6272780.

7. L. W. Kang, C. W. Lin, and Y. H. Fu, “Automatic single-image-based rain streaks removal via image decomposition,” IEEE Trans. Image Process., vol. 21, no. 4, pp. 1742–1755, 2012. https://doi.org/10.1109/TIP.2011.2179057.

8. X. Fu, J. Huang, D. Zeng, Y. Huang, X. Ding, and J. Paisley, “Removing rain from single images via a deep detail network,” in Proceedings - 30th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2017, 2017, vol. 2017-Janua, pp. 1715–1723. https://doi.org/10.1109/CVPR.2017.186.

9. K. He, X. Zhang, S. Ren, and J. Sun, “Deep Residual Learning for Image Recognition,” in 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2016, pp. 770–778. https://doi.org/10.1109/CVPR.2016.90.

10. L. Gondara, “Medical Image Denoising Using Convolutional Denoising Autoencoders,” in IEEE International Conference on Data Mining Workshops, ICDMW, 2016. https://doi.org/10.1109/ICDMW.2016.0041.

11. H. Zhang, V. Sindagi, and V. M. Patel, “Image De-raining Using a Conditional Generative Adversarial Network,” IEEE Trans. Circuits Syst. Video Technol., vol. PP, no. c, pp. 1–1, 2019. https://doi.org/10.1109/TCSVT.2019.2920407.

12. S. H. Sun, S. P. Fan, and Y. C. F. Wang, “Exploiting image structural similarity for single image rain removal,” in IEEE International Conference on Image Processing, pp. 4482–4486, 2014. https://doi.org/10.1109/ICIP.2014.7025909.

13. K. He, J. Sun, and X. Tang, “Guided Image Filtering,” IEEE Trans. Pattern Anal. Mach. Intell., vol. 35, 2012. https://doi.org/10.1109/TPAMI.2012.213.

14. X. Zheng, Y. Liao, W. Guo, X. Fu, and X. Ding, “Single-image-based rain and snow removal using multi-guided filter,” in ICONIP: International Conference on Neural Information Processing, vol. 8228 LNCS, no. PART 3, pp. 258–265, 2013. https://doi.org/10.1007/978-3-642-42051-1_33.

15. J. Xu, W. Zhao, P. Liu, and X. Tang, “An Improved Guidance Image Based Method to Remove Rain and Snow in a Single Image,” Comput. Inf. Sci., vol. 5, no. 3, pp. 49–55, 2012. https://doi.org/10.5539/cis.v5n3p49.

16. S. C. Pei, Y. T. Tsai, and C. Y. Lee, “Removing rain and snow in a single image using saturation and visibility features,” in 2014 IEEE International Conference on Multimedia and Expo Workshops, ICMEW 2014, pp. 2–7, 2014. https://doi.org/10.1109/ICMEW.2014.6890551.

17. Z. Zeng, Y. Li, and I. King, “Content-Adaptive Rain and Snow Removal Algorithms for Single Image,” Lect. Notes Comput. Sci. (including Subser. Lect. Notes Artif. Intell. Lect. Notes Bioinformatics), pp. 439–448, 2014. https://doi.org/10.1007/978-3-319-12436-0_49.

18. C. Liu, Y. Pang, J. Wang, A. Yang, and J. Pan, “Frequency Domain Directional Filtering Based Rain Streaks Removal from a Single Color Image,” in International Conference on Intelligent Computing, pp. 415–424, 2014. https://doi.org/10.1007/978-3-319-09333-8_45.

19. Y. Li, R. T. Tan, X. Guo, J. Lu, S. Member, and M. S. Brown, “Rain Streak Removal Using Layer Priors,” vol. 26, no. 8, pp. 3874–3885, 2017. https://doi.org/10.1109/CVPR.2016.299.

20. L. J. Deng, T. Z. Huang, X. Le Zhao, and T. X. Jiang, “A directional global sparse model for single image rain removal,” Appl. Math. Model., vol. 59, pp. 662–679, 2018. https://doi.org/10.1016/j.apm.2018.03.001.

21. S. Du, Y. Liu, M. Ye, Z. Xu, J. Li, and J. Liu, “Single image deraining via decorrelating the rain streaks and background scene in gradient domain,” Pattern Recognit., vol. 79, pp. 303–317, 2018. https://doi.org/10.1016/j.patcog.2018.02.016.

22. Y. Luo, Y. Xu, and H. Ji, “Removing rain from a single image via discriminative sparse coding,” in Proceedings of the IEEE International Conference on Computer Vision, 2015. https://doi.org/10.1109/ICCV.2015.388.

23. R. Mondal, P. Purkait, S. Santra, and B. Chanda, “Morphological Networks for Image De-raining,” in International Conference on Discrete Geometry for Computer Imagery, pp. 262–275, 2019. https://doi.org/10.1007/978-3-030-14085-4_21.

24. I. Goodfellow, Y. Bengio, and A. Courville, Deep learning. The MIT Press, 2016. https://doi.org/10.1007/s10710-017-9314-z.

25. Q. Zhang, L. T. Yang, Z. Chen, and P. Li, “A survey on deep learning for big data,” Inf. Fusion, vol. 42, no. October 2017, pp. 146–157, 2018. https://doi.org/10.1016/j.inffus.2017.10.006.

26. K. Iqbal, M. Odetayo, and A. James, “Enhancing the low quality images using Unsupervised Colour Correction Method,” 2010, pp. 1703–1709. https://doi.org/10.1109/ICSMC.2010.5642311.

27. Adobe, “PDF Blend Modes : Addendum,” 2006.

28. A. E. Dirik and N. Nemon, “Image tamper detection based on demosaicing artifacts,” Comput. Eng., pp. 1497–1500, 2009. https://doi.org/10.1109/ICIP.2009.5414611.

29. P. Arbeláez, M. Maire, C. Fowlkes, and J. Malik, “Contour detection and hierarchical image segmentation,” IEEE Trans. Pattern Anal. Mach. Intell., vol. 33, no. 5, pp. 898–916, 2011. https://doi.org/10.1109/TPAMI.2010.161.

30. G. Schaefer and M. Stich, “UCID: an uncompressed color image database,” in Proceedings of SPIE 5307, 2003. https://doi.org/10.1117/12.525375.

31. X. Fu, J. Huang, X. Ding, Y. Liao, and J. Paisley, “Clearing the skies: A deep network architecture for single-image rain removal,” IEEE Trans. Image Process., vol. 26, no. 6, pp. 2944–2956, 2017. https://doi.org/10.1109/TIP.2017.2691802.

32. X. Glorot and Y. Bengio, “Understanding the difficulty of training deep feedforward neural networks,” Proc. Thirteen. Int. Conf. Artif. Intell. Stat., vol. 9, pp. 249–256, 2010. https://doi.org/ 10.1.1.207.2059

33. S. Khirirat, H. R. Feyzmahdavian, and M. Johansson, “Mini-batch gradient descent: Faster convergence under data sparsity,” 2017 IEEE 56th Annu. Conf. Decis. Control. CDC 2017, vol. 2018-January, no. Cdc, pp. 2880–2887, 2018. https://doi.org/10.1109/CDC.2017.8264077.

34. K. Yuan, B. Ying, J. Liu, and A. H. Sayed, “Variance-Reduced Stochastic Learning by Networked Agents under Random Reshuffling,” IEEE Trans. Signal Process., vol. 67, no. 2, pp. 351–366, 2019. https://doi.org/10.1109/TSP.2018.2872003.

35. D. P. Kingma and J. Ba, “Adam: A Method for Stochastic Optimization,” in International Conference on Learning Representations, 2015.