Nakshatra-Drishti: A Supervised Learning Approach for Low Light Image Enhancement Using Convolutional Neural Networks

  • Nitesh Kumar
  • Shailendra verma
Keywords: Low-light image enhancement, Convolutional neural networks, Supervised learning, Image perception, Artificial intelligence, Decision-making

Abstract

Images captured under low-light conditions pose significant challenges for subsequent analysis due to degradation in quality, including noise, loss of scene content, inaccurate colour, and contrast information. In this paper, we propose a supervised learning-based convolutional neural network (CNN) model, Nakshatra-Drishti, specifically designed for enhancing low-light images, videos, and real-time camera feeds. The model is trained on paired datasets and extensively evaluated on various benchmarks, demonstrating remarkable results. We also introduce a user-friendly web-based software application that enhances image perception in poorly illuminated environments, facilitating more effective artificial intelligence analysis and decision-making processes.

References

[1] E. H. Land, "The retinex theory of color vision," Scientific American, vol. 237, no. 6, pp. 108–129, 1977.
[2] S. M. Pizer et al., "Adaptive histogram equalization and its variations," Computer Vision, Graphics, and Image Processing, vol. 39, no. 3, pp. 355–368, 1987.
[3] K. G. Lore, A. Akintayo, and S. Sarkar, "LLNet: A deep autoencoder approach to natural low-light image enhancement," Pattern Recognition, vol. 61, pp. 650–662, 2017.
[4] C. Wei et al., "Deep retinex decomposition for low-light enhancement," arXiv preprint arXiv:1808.04560, 2018.
[5] J. Kim, J. K. Lee, and K. M. Lee, "Accurate image super-resolution using very deep convolutional networks," in Proceedings of the IEEE conference on computer vision and pattern recognition, 2016, pp. 1646–1654.
[6] X. Guo, Y. Li, and H. Ling, "LIME: Low-light image enhancement via illumination map estimation," IEEE Transactions on Image Processing, vol. 26, no. 2, pp. 982–993, 2017.
[7] M. Zhu et al., "EEMEFN: Low-light image enhancement via edge-enhanced multi-exposure fusion network," in AAAI, 2020, pp. 13 106–13 113.
[8] C. Wei et al., "Deep retinex decomposition for low-light enhancement," arXiv preprint arXiv:1808.04560, 2018.
[9] C. Lee, C. Lee, and C.-S. Kim, "Contrast enhancement based on layered difference representation," in Image Processing (ICIP), 2012 19th IEEE International Conference on, 2012, pp. 965–968.
[10] D. J. Jobson et al., "A multiscale retinex for bridging the gap between color images and the human observation of scenes," IEEE Transactions on Image Processing, vol. 6, no. 7, pp. 965–976, 1997.
[11] S. Wang et al., "Naturalness preserved enhancement algorithm for non-uniform illumination images," IEEE Transactions on Image Processing, vol. 22, no. 9, pp. 3538–3548, 2013.
[12] X. Fu et al., "A weighted variational model for simultaneous reflectance and illumination estimation," in CVPR, 2016, pp. 2782–2790.
[13] X. Guo, Y. Li, and H. Ling, "LIME: Low-light image enhancement via illumination map estimation," IEEE Transactions on Image Processing, vol. 26, no. 2, pp. 982–993, 2017.
[14] X. Ren et al., "Joint enhancement and denoising method via sequential decomposition," in Circuits and Systems (ISCAS), 2018 IEEE International Symposium on, 2018, pp. 1–5.
[15] M. Li et al., "Structure-revealing low-light image enhancement via robust retinex model," IEEE Transactions on Image Processing, vol. 27, no. 6, pp. 2828–2841, 2018.
[16] M. Gharbi et al., "Deep bilateral learning for real-time image enhancement," ACM Transactions on Graphics (TOG), vol. 36, no. 4, p. 118, 2017.
[17] N. K. Kalantari and R. Ramamoorthi, "Deep high dynamic range imaging of dynamic scenes," ACM Trans. Graph, vol. 36, no. 4, p. 144, 2017.
[18] S. Wu et al., "Deep high dynamic range imaging with large foreground motions," in Proceedings of the European Conference on Computer Vision (ECCV), 2018, pp. 117–132.
[19] J. Cai, S. Gu, and L. Zhang, "Learning a deep single image contrast enhancer from multi-exposure images," IEEE Transactions on Image Processing, vol. 27, no. 4, pp. 2049–2062, 2018.
[20] C. Chen et al., "Learning to see in the dark," arXiv preprint arXiv:1805.01934, 2018.
[21] I. Goodfellow et al., "Generative adversarial nets," in Advances in neural information processing systems, 2014, pp. 2672–2680.
[22] X. Gong et al., "AutoGAN: Neural architecture search for generative adversarial networks," in Proceedings of the IEEE International Conference on Computer Vision, 2019, pp. 3224–3234.
[23] Y. Jiang et al., "EnlightenGAN: Deep light enhancement without paired supervision," IEEE Transactions on Image Processing, vol. 30, pp. 2340–2349, 2021.
[24] C. Guo et al., "Zero-reference deep curve estimation for low-light image enhancement," in CVPR, 2020, pp. 1780–1789.
[25] C. Li, C. Guo, and C. C. Loy, "Learning to enhance low-light image via zero-reference deep curve estimation," TPAMI, 2021.
[26] C. Wei, W. Wang, W. Yang, and J. Liu, “Deep retinex decomposition for low-light enhancement,” in Proceedings of the British Machine Vision Conference (BMVC), 2018.
[27] Y. Zhang, K. Li, K. Li, L. Wang, B. Zhong, and Y. Fu, “Image super-resolution using very deep residual channel attention networks,” in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2018.
[28] X. Zhang, X. Chen, X. Huang, and J. Gao, "Learning to See in the Dark via Wavelet Domain Attention Networks," in Proceedings of the European Conference on Computer Vision (ECCV), 2020.
[29] Y. Zhao, H. Guo, and J. Zhang, "Low-Light Image Enhancement Using a Conditional Generative Adversarial Network," IEEE Access, vol. 8, pp. 147744-147756, 2020.
[30] S. Li, Y. Huang, and Q. Tian, "Rethinking of Learning-based Low-light Image Enhancement: A Data-driven Perspective," in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, 2020.
Published
2023-12-30
How to Cite
Kumar, N., & verma, S. (2023). Nakshatra-Drishti: A Supervised Learning Approach for Low Light Image Enhancement Using Convolutional Neural Networks. Asian Journal For Convergence In Technology (AJCT) ISSN -2350-1146, 9(3), 65-70. https://doi.org/10.33130/AJCT.2023v09i03.011

Most read articles by the same author(s)

Obs.: This plugin requires at least one statistics/report plugin to be enabled. If your statistics plugins provide more than one metric then please also select a main metric on the admin's site settings page and/or on the journal manager's settings pages.