Abstract
Soil images collected under different illumination conditions can be enhanced with a brightness-controlled enhancement algorithm, so that the result image is similar to the real image of the same soil photographed under specific natural light. It can improve the accuracy of soil species identification with machine vision because the image features of distinct soil species are described with a uniform brightness benchmark. To address it, a nonlinear mapping algorithm based on conic curve is proposed to realize the brightness-controlled enhancement of soil image. Firstly, a weighted quadric curve is derived in theory to reconstruct the brightness mapping according to the brightness relation between a pair of soil images with different brightness. Then, the brightness transformation range and the bending degree of brightness mapping curve are searched by the idea of binary search and gradual approximation to meet the given target brightness. The enhanced image is finally obtained by weighting and fusing the results of curve mapping in RGB space and HSV space. Extensive experiment results demonstrate that the proposed method is superior to comparison methods for brightness migration. Our algorithm can improve the accuracy of CNN models by up to 4.94%. Subjective evaluation shows that the effective range of soil image brightness enhancement with the proposed method is plus or minus 30 gray levels of brightness. The simulation result proves its effectiveness in brightness-controlled enhancement of soil image.
Similar content being viewed by others
Code availability
Code Availability underlying the results presented in this paper is not publicly available at this time but may be obtained from the authors upon reasonable request.
References
Kim, M., Chung, M.G.: Recursively separated and weighted histogram equalization for brightness preservation and contrast enhancement. IEEE Trans. Consum. Electron. 54(3), 1389–1397 (2008)
Reza, A.M.: Realization of the contrast limited adaptive histogram equalization (CLAHE) for real-time image enhancement. J. VLSI Signal Process. Syst. Signal Image Video Technol. 38(1), 35–44 (2004)
Lu, X.M., Zhu, X.Y., Li, Z.W., et al.: A brightness-scaling and detail-preserving tone mapping method for high dynamic range images. Acta Automatica Sinica 41(6), 1080–1092 (2015)
Veluchamy, M., Subramani, B.: Fuzzy dissimilarity color histogram equalization for contrast enhancement and color correction. Appl. Soft Comput. 89, 106077 (2020)
Mishro, P.K., Agrawal, S., Panda, R., et al.: A novel brightness preserving joint histogram equalization technique for contrast enhancement of brain MR images. Biocybern. Biomed. Eng. 41(2), 540–553 (2021)
Simi, V.R., Edla, D.R., Joseph, J., et al.: Parameter-free fuzzy histogram equalisation with illumination preserving characteristics dedicated for contrast enhancement of magnetic resonance images. Appl. Soft Comput. 93, 106364 (2020)
Cheng, H., Long, W., Li, Y.: Two low illuminance image enhancement algorithms based on grey level mapping. Multimed. Tools Appl. 80, 7205–7228 (2021)
Li, P.L., Liang, J.L., Zhang, M.H.: A degradation model for simultaneous brightness and sharpness enhancement of low-light image. Signal Process. 189, 108298 (2021)
Chaudhry, A.M., Riaz, M.M., Ghafoor, A.: Model-assisted content adaptive detail enhancement and quadtree decomposition for image visibility enhancement. SIViP (2022)
Huang, S.C., Cheng, F.C., Chiu, Y.-S.: Efficient contrast enhancement using adaptive gamma correction with weighting distribution. IEEE Trans. Image Process. 22(3), 1032–1041 (2012)
Yuan, L., Sun, J.: Automatic exposure correction of consumer photographs. Eur. Confer. Comput. Vis. 7575, 771–785 (2012)
Land, E.H.: The retinex theory of color vision. Sci. Am. 237(6), 108–129 (1977)
Wang, S., Zheng, J., Hu, H., et al.: Naturalness preserved enhancement algorithm for non-uniform illumination images. IEEE Trans. Image Process. 22(9), 3538–3548 (2013)
Guo, X., Li, Y., Hu, H., et al.: LIME: Low-light image enhancement via illumination map estimation. IEEE Trans. Image Process. 26(2), 982–993 (2016)
Li, M., Liu, J., Yang, W., et al.: Structure-revealing low-light image enhancement via robust retinex model. IEEE Trans. Image Process. 27(6), 2828–2841 (2018)
Ren, X., Yang, W., Cheng, W., et al.: LR3M: Robust low-light enhancement via low-rank regularized retinex model. IEEE Trans. Image Process. 29, 5862–5876 (2020)
Guo, C., Li, C., Guo, J., et al.: Zero-reference deep curve estimation for low-light image enhancement. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 1780–1789 (2020)
Jiang, Y., Gong, X., Liu, D., et al.: EnlightenGAN: Deep light enhancement without paired supervision. IEEE Trans. Image Process. 30, 2340–2349 (2021)
Kim, H., Choi, S.M., Kim, C.S., et al.: Representative color transform for image enhancement. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 4459–4468 (2021)
Wang, S., Luo, G.: Naturalness preserved image enhancement using a priori multi-layer lightness statistics. IEEE Trans. Image Process. 27(2), 938–948 (2018)
Sahnoun, M., Kallel, F., Dammak, M., et al.: Spinal cord MRI contrast enhancement using adaptive gamma correction for patient with multiple sclerosis. SIViP 14, 377–385 (2020)
Xiao, B., Tang, H., Jiang, Y., et al.: Brightness and contrast controllable image enhancement based on histogram specification. Neurocomputing 275, 2798–2809 (2018)
Brizuela Pineda, I.A., Medina Caballero, R.D., Cáceres Silva, J.J., et al.: Quadri-histogram equalization using cutoff limits based on the size of each histogram with preservation of average brightness. SIViP 13, 843–851 (2019)
Zeng, S., Zhao, B., Wang, S., et al.: Controllable brightness enhancement of the soil image based on weighted gaussian subtraction fitting. Acta Photonica Sinica 51(4), 0410005 (2022)
Wang, S., Xie, D., Qu, M., et al.: DB50T 796-2017 Classification and Codes for Chongqing Soil, Chongqing Bureau of Technical Supervision (2017)
Chen, S.-D., Ramli, A.R.: Minimum mean brightness error bi-histogram equalization in contrast enhancement. IEEE Trans. Consum. Electron. 49(4), 1310–1319 (2003)
He, K., Zhang, X., Ren, S., et al.: Deep Residual Learning for Image Recognition. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 770–778 (2016)
Tan, M., Le, Q.: Efficientnet: Rethinking model scaling for convolutional neural networks. In: Proceedings of the 36th International Conference on Machine Learning (PMLR), vol. 97, pp. 6105–6114 (2019)
Acknowledgements
This work supported by Key Science and Technology Research Program (No. KJZD-K201900505) of Chongqing, China; Chongqing University Innovation Research Group funding (No. CXQT20015) of Chongqing Municipal Education Commission, China; Technology Foresight and Institutional Innovation (CSTB2022TFII-OFX0043) of Chongqing, China; Graduate Student Research and Innovation Program (CYS22564) of Chongqing, China.
Author information
Authors and Affiliations
Contributions
SZ and WW wrote the main manuscript text. YX provides many useful advices. SW and GL provide the dataset. All authors reviewed the manuscript
Corresponding author
Ethics declarations
Conflict of interest
The authors declare no conflicts of interest.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
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
Zeng, S., Wu, W., Xia, Y. et al. Brightness-controlled enhancement for soil image based on conic curve. SIViP 18, 1493–1506 (2024). https://doi.org/10.1007/s11760-023-02858-8
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11760-023-02858-8