Abstract
Daily a large amount of multimedia data is generated and transferred over the internet, and a significant sum of it is images. Images are captured by using which sensor, at what time, and in which lighting condition affects the quality of the image. Image exposure correction tries to regulate the inaccurate exposure setting of images by manipulating the under and over-exposed regions. This is done in post-processing when the data for those regions are limited in the raw image. We used a deep learning-based convolutional neural network to solve this problem to predict the missing detail in un-exposed images. The proposed coherent CNN architecture built on U-Net-like encoder-decoder architecture with skip connectivity. We conducted experiments to investigate the performance of our network and compared it with existing deep learning-based methods. Furthermore, we reported the findings and results of our investigations and our approach's potential to enhance the quality of the under or over-exposure images. Our method is simple and lightweight yet achieves decent outputs with results close to the state-of-the-art techniques without any qualitative deformation in the final image. We experimentally validated the study on a benchmark dataset for comparative evaluation of the model. We obtained a PSNR of 19.372 and SSIM of 0.835, which is superior to the existing state-of-the-art studies.
Similar content being viewed by others
References
Afifi M, Brown MS. Deep white-balance editing. arXiv. 2020. https://doi.org/10.48550/ARXIV.2004.01354.
Afifi M, Derpanis KG, Ommer B, Brown MS. Learning multi-scale photo exposure correction. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2021.
Bychkovsky V et al. Learning photographic global tonal adjustment with a database of input/output image Pairs. In: The Twenty-Fourth IEEE Conference on Computer Vision and Pattern Recognition, 2011.
Celik T, Tjahjadi T. Contextual and variational contrast enhancement. IEEE Trans Image Process. 2011;20(12):3431–41. https://doi.org/10.1109/TIP.2011.2157513.
Chen C, Chen Q, Xu J, Koltun V. Learning to see in the dark. arXiv. 2018. https://doi.org/10.48550/ARXIV.1805.01934.
Cheng G, Han J, Xiaoqiang Lu. Remote sensing image scene classification: benchmark and state of the art. Proc IEEE. 2017;105(10):1865–83. https://doi.org/10.1109/jproc.2017.2675998.
Eyiokur FI, Yaman D, Ekenel HK, Waibel A. Exposure correction model to enhance image quality. arXiv. 2022. https://doi.org/10.48550/arxiv.2204.10648.
Guo C, Li C, Guo J, Loy CC, Hou J, Kwong S, Cong R. Zero-reference deep curve estimation for low-light image enhancement. arXiv. 2020. https://doi.org/10.48550/ARXIV.2001.06826.
Guo X, Li Yu, Ling H. LIME: low-light image enhancement via illumination map estimation. IEEE Trans Image Process. 2017;26(2):982–93. https://doi.org/10.1109/TIP.2016.2639450.
Huber PJ. Robust estimation of a location parameter. Ann Math Stat. 1964;35(1):73–101.
Ingle PY, Kim YG. Real-time abnormal object detection for video surveillance in smart cities. Sensors. 2022;22(10):3862.
Isola P, Zhu J-Y, Zhou T, Efros AA. Image-to-image translation with conditional adversarial networks. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 5967–76, 2017. https://doi.org/10.1109/CVPR.2017.632.
Land EH. The retinex theory of color vision Scientific American. 2009.
Lee C, Lee C, Kim C-S. Contrast enhancement based on layered difference representation of 2D histograms. IEEE Trans Image Process. 2013;22(12):5372–84. https://doi.org/10.1109/TIP.2013.2284059.
Li C, et al. An underwater image enhancement benchmark dataset and beyond. IEEE Trans Image Process. 2020;29:4376–89. https://doi.org/10.1109/TIP.2019.2955241.
Lin M, Chen Q, Yan S. Network in network. ArXiv. 2013. https://doi.org/10.48550/ARXIV.1312.4400.
Lore KG, Akintayo A, Sarkar S. LLNet: a deep autoencoder approach to natural low-light image enhancement. arXiv 2017 https://arXiv.org/abs/1511.03995.
Loshchilov I, Hutter F. Decoupled weight decay regularization. arXiv. 2017. https://doi.org/10.48550/ARXIV.1711.05101.
Ma K, Duanmu Z, Zhu H, Fang Y, Wang Z. Deep guided learning for fast multi-exposure image fusion. IEEE Trans Image Process. 2020;29:2808–19. https://doi.org/10.1109/TIP.2019.2952716.
Ma L, Jin D, Liu R, Fan X, Luo Z. Joint over and under exposures correction by aggregated retinex propagation for image enhancement. IEEE Signal Process Lett. 2020;27:1210–4. https://doi.org/10.1109/LSP.2020.3008347.
Mao X-J, Shen C, Yang Y-B. Image restoration using convolutional auto-encoders with symmetric skip connections. ArXiv. 2016. https://doi.org/10.48550/ARXIV.1606.08921.
Odena, Augustus, Vincent Dumoulin, and Chris Olah. “Deconvolution and Checkerboard Artifacts.” Distill, 2016. https://doi.org/10.23915/distill.00003.
Ouyang, Hao, Zifan Shi, Chenyang Lei, Ka Lung Law, and Qifeng Chen. “Neural Camera Simulators.” In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 7700–7709, 2021.
Pizer, Stephen M., E. Philip Amburn, John D. Austin, Robert Cromartie, Ari Geselowitz, Trey Greer, Bart ter Haar Romeny, John B. Zimmerman, and Karel Zuiderveld. “Adaptive Histogram Equalization and Its Variations.” Computer Vision, Graphics, and Image Processing 39, no. 3 (1987): 355–68. https://doi.org/10.1016/S0734-189X(87)80186-X.
Qu L, Liu S, Wang M, Song Z. TransMEF: a transformer-based multi-exposure image fusion framework using self-supervised multi-task learning. arXiv. 2021. https://doi.org/10.48550/ARXIV.2112.01030.
Ruixing W et al. Underexposed photo enhancement using deep illumination estimation. In: 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2019, 6842–50, https://doi.org/10.1109/CVPR.2019.00701.
Schwartz E, Giryes R, Bronstein AM. DeepISP: toward learning an end-to-end image processing pipeline. IEEE Trans Image Process. 2019;28(2):912–23. https://doi.org/10.1109/TIP.2018.2872858.
Wang Z, Bovik AC, Sheikh HR, Simoncelli EP. Image quality assessment: from error visibility to structural similarity. IEEE Trans Image Process. 2004;13(4):600–12. https://doi.org/10.1109/TIP.2003.819861.
Wang S, Zheng J, Hai-Miao Hu, Li Bo. Naturalness preserved enhancement algorithm for non-uniform illumination images. IEEE Trans Image Process. 2013;22(9):3538–48. https://doi.org/10.1109/TIP.2013.2261309.
Xueyang F et al. A weighted variational model for simultaneous reflectance and illumination estimation. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2016, 2782–90, https://doi.org/10.1109/CVPR.2016.304
Yadav O, Ghosal K, Lutz S, Smolic A. Frequency-domain loss function for deep exposure correction of dark images. SIViP. 2021;15(8):1829–36. https://doi.org/10.1007/s11760-021-01915-4.
Yang K-F, Cheng C, Zhao S-X, Zhang X-S, Li Y-J. Learning to adapt to light. arXiv. 2022. https://doi.org/10.48550/ARXIV.2202.08098.
Yang H, Wang B, Vesdapunt N, Guo M, Kang SB. Personalized exposure control using adaptive metering and reinforcement learning. IEEE Trans Vis Comput Graph. 2019;25(10):2953–68. https://doi.org/10.1109/TVCG.2018.2865555.
Yang X, Xu K, Song Y, Zhang Q, Wei X, Lau RWH. Image correction via deep reciprocating HDR transformation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2018.
Zhang Q, Nie Y, Zheng W-S. Dual illumination estimation for robust exposure correction. Comput Graph Forum. 2019;38(7):243–52. https://doi.org/10.1111/cgf.13833.
Zuiderveld K. Contrast limited adaptive histogram equalization. In: Graphics gems IV. Academic Press Professional Inc; 1994. p. 474–85.
Funding
The authors did not receive support from any organization for the submitted work.
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of Interest
The authors declare that they have no conflict interests.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
This article is part of the topical collection “Advances in Computational Approaches for Artificial Intelligence, Image Processing, IoT and Cloud Applications” guest edited by Bhanu Prakash K N and M. Shivakumar.
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Parab, M., Bhanushali, A., Ingle, P. et al. Image Enhancement and Exposure Correction Using Convolutional Neural Network. SN COMPUT. SCI. 4, 204 (2023). https://doi.org/10.1007/s42979-022-01608-w
Received:
Accepted:
Published:
DOI: https://doi.org/10.1007/s42979-022-01608-w