|
|
基于MSRCR-拉普拉斯金字塔方法的低照度图像增强
|
Abstract:
针对传统Retinex图像增强算法存在的纹理细节保留差、过度增强和色调突变等不足，文中提出了一种基于MSRCR (带色彩恢复的多尺度Retinex算法)的拉普拉斯金字塔方法，用于弱光图像增强。该方法由三个重要部分组成：照度颜色校正、反射成分细节增强和线性加权融合。首先，将伽马校正后的照度加回反射中，实现色彩增强。然后，通过拉普拉斯金字塔处理反射分量来实现细节增强。最后，细节增强的图像和颜色校正的图像通过加权融合重构出增强后的输出图像。主观与客观的性能评估表明，相较于对比算法，文中所提出的方法可以更加有效地增强暗区图像的细节和全局对比度，使得输出图像具备更好的视觉效果。因此，该方法是一种有效的弱光图像增强方法，并具有一定的工程应用价值。
To address the shortcomings of traditional Retinex image enhancement algorithms such as poor texture detail retention, over-enhancement and tonal mutation, a Laplace pyramid method based on MSRCR (Multiscale Retinex algorithm with color recovery) is proposed in the paper for low light image enhancement. The method consists of three important parts: illumination color correction, reflection component detail enhancement, and linear weighted fusion. First, the gamma-corrected illumination is added back into the reflection to achieve color enhancement. Then, the detail enhancement is achieved by processing the reflection components through Laplace pyramids. Finally, the detail-enhanced image and the color-corrected image are reconstructed by weighted fusion to produce the enhanced output image. The subjective and objective performance evaluations show that the proposed method in the paper can enhance the details and global contrast of the dark area images more effectively compared to the contrast algorithm, making the output image with better visual effects. Therefore, the method is an effective method for low light image enhancement and has certain engineering application value.
| [1] | Cheng, H.D. and Shi, X.J. (2004) A Simple and Effective Histogram Equalization Approach to Image Enhancement. Digital Signal Processing, 14, 158-170. https://doi.org/10.1016/j.dsp.2003.07.002 |
| [2] | Reza, A.M. (2004) Realization of the Contrast Limited Adaptive Histogram Equalization (CLAHE) for Real-Time Image Enhancement. Journal of VLSI Signal Processing Systems for Signal, Image and Video Technology, 38, 35-44.
https://doi.org/10.1023/B:VLSI.0000028532.53893.82 |
| [3] | Chen, S.D. and Ramli, A.R. (2003) Contrast Enhancement Using Recursive Mean-Separate Histogram Equalization for Scalable Brightness Preservation. IEEE Transactions on Consumer Electronics, 49, 1301-1309.
https://doi.org/10.1109/TCE.2003.1261233 |
| [4] | Land, E.H. (1977) The Retinex Theory of Color Vision. Scientific American, 237, 108-129.
https://doi.org/10.1038/scientificamerican1277-108 |
| [5] | Jobson, D.J., Rahman, Z. and Woodell, G.A. (1997) A Multiscale Retinex for Bridging the Gap between Color Images and the Human Observation of Scenes. IEEE Transactions on Image Processing, 6, 965-976.
https://doi.org/10.1109/83.597272 |
| [6] | Jiang, B., Woodell, G.A. and Jobson, D.J. (2015) Novel Multi-Scale Retinex with Color Restoration on Graphics Processing Unit. Journal of Real-Time Image Processing, 10, 239-253. https://doi.org/10.1007/s11554-014-0399-9 |
| [7] | Guo, X.J., Li, Y. and Ling, H.B. (2016) LIME: Low-Light Image Enhancement via Illumination Map Estimation. IEEE Transactions on Image Processing, 26, 982-993. https://doi.org/10.1109/TIP.2016.2639450 |
| [8] | Priyadarshini, R. Bharani, A., Rahimankhan, E. and Rajendran, N. (2021) Low-Light Image Enhancement Using Deep Convolutional Network. In: Raj, J.S., Iliyasu, A.M., Bestak, R. and Baig, Z.A., Eds., Innovative Data Communication Technologies and Application, Springer, Singapore, 695-705. https://doi.org/10.1007/978-981-15-9651-3_57 |
| [9] | Zhang, Y., Di, X., Zhang, B., et al. (2020) Self-Supervised Image Enhancement Network: Training with Low Light Images Only. arXiv:2002.11300. |
| [10] | Jung, C., Yang, Q., Sun, T., et al. (2017) Low Light Image Enhancement with Dual-Tree Complex Wavelet Transform. Journal of Visual Communication and Image Representation, 42, 28-36. https://doi.org/10.1016/j.jvcir.2016.11.001 |
| [11] | Lore, K.G., Akintayo, A. and Sarkar, S. (2017) LLNet: A Deep Autoencoder Approach to Natural Low-Light Image Enhancement. Pattern Recognition, 61, 650-662. https://doi.org/10.1016/j.patcog.2016.06.008 |
| [12] | Wei, C., Wang, W., Yang, W. and Liu, J. (2018) Deep Retinex Decomposition for Low-Light Enhancement. arXiv:1808.04560. |
| [13] | Dabov, K., Foi, A., Katkovnik, V., et al. (2007) Image Denoising by Sparse 3-D Transform-Domain Collaborative Filtering. IEEE Transactions on Image Processing, 16, 2080-2095. https://doi.org/10.1109/TIP.2007.901238 |
| [14] | Zhang, Y.H., Zhang, J.W. and Guo, X.J. (2019) Kindling the Darkness: A Practical Low-Light Image Enhancer. Proceedings of the 27th ACM International Conference on Multimedia, Nice, 21-25 October 2019, 1632-1640.
https://doi.org/10.1145/3343031.3350926 |
| [15] | Jiang, Y.F., Gong, X.Y., Liu, D., et al. (2021) EnlightenGAN: Deep Light Enhancement without Paired Supervision. IEEE Transactions on Image Processing, 30, 2340-2349. https://doi.org/10.1109/TIP.2021.3051462 |
| [16] | Guo, C.L., Li, C., Guo, J., et al. (2020) Zero-Reference Deep Curve Estimation for Low-Light Image Enhancement. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, Seattle, 13-19 June 2020, 1777-1786. https://doi.org/10.1109/CVPR42600.2020.00185 |
| [17] | Wu, L.F., Zhou, P. and Xu, X. (2013) An Illumination Invariant Face Recognition Scheme to Combining Normalized Structural Descriptor with Single Scale Retinex. Chinese Conference on Biometric Recognition, Jinan, 16-17 November 2013, 34-42. https://doi.org/10.1007/978-3-319-02961-0_5 |
| [18] | Lin, H.N. and Shi, Z.W. (2014) Multi-Scale Retinex Improvement for Nighttime Image Enhancement. Optik, 125, 7143-7148. https://doi.org/10.1016/j.ijleo.2014.07.118 |
| [19] | Rahman, Z., Jobson, D.J. and Woodell, G.A. (2011) Investigating the Relationship between Image Enhancement and Image Compression in the Context of the Multi-Scale Retinex. Journal of Visual Communication and Image Representation, 22, 237-250. https://doi.org/10.1016/j.jvcir.2010.12.006 |
| [20] | Liu, Y.H., Yan, H.M., Gao, S.B. and Yang, K.F. (2018) Criteria to Evaluate the Fidelity of Image Enhancement by MSRCR. IET Image Processing, 12, 880-887. https://doi.org/10.1049/iet-ipr.2017.0171 |
| [21] | Deswal, S., Gupta, S. and Bhushan, B. (2015) A Survey of Various Bilateral Filtering Techniques. International Journal of Signal Processing, Image Processing and Pattern Recognition, 8, 105-120.
https://doi.org/10.14257/ijsip.2015.8.3.10 |
| [22] | Choudhury, P. and Tumblin, J. (2005) The Trilateral Filter for High Contrast Images and Meshes. ACM SIGGRAPH 2005 Courses, Los Angeles, 31 July-4 August 2005, 5-es. https://doi.org/10.1145/1198555.1198565 |
| [23] | Garnett, R., Huegerich, T., Chui, C., et al. (2005) A Universal Noise Removal Algorithm with an Impulse Detector. IEEE Transactions on Image Processing, 14, 1747-1754. https://doi.org/10.1109/TIP.2005.857261 |
| [24] | Chang, H.H. (2010) Entropy-Based Trilateral Filtering for Noise Removal in Digital Images. 2010 3rd International Congress on Image and Signal Processing, Yantai, 16-18 October 2010, 673-677.
https://doi.org/10.1109/CISP.2010.5647219 |
| [25] | Vaudrey, T. and Klette, R. (2009) Fast Trilateral Filtering. International Conference on Computer Analysis of Images and Patterns, Münster, 2-4 September 2009, 541-548. https://doi.org/10.1007/978-3-642-03767-2_66 |
| [26] | Li, S.T., Hao, Q.B., Kang, X.D., et al. (2018) Gaussian Pyramid Based Multiscale Feature Fusion for Hyperspectral Image Classification. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 11, 3312-3324. https://doi.org/10.1109/JSTARS.2018.2856741 |
| [27] | Adelson, E.H., Anderson, C.H., Bergen, J.R., et al. (1984) Pyramid Methods in Image Processing. RCA Engineer, 29, 33-41. |
