Welcome to Francis Academic Press

Academic Journal of Engineering and Technology Science, 2022, 5(5); doi: 10.25236/AJETS.2022.050507.

Method for Correcting Low-illumination Images Based on Adaptive Two-dimensional Gamma Function

Author(s)

Lu Chen, Lingfei Chen

Corresponding Author:
Lu Chen
Affiliation(s)

College of Communication and Information Engineering, Shanghai University, Shanghai, 200444, China

Abstract

A two-dimensional gamma function-based color image correction method based on the illumination-reflection model and multi-scale theory is proposed. Firstly, the original image is histogram equalized, then converted to HSV color space, and the light components of the scene are extracted by multi-scale Gaussian function, and then the parameters of the 2D gamma function are adjusted by the distribution characteristics of the light components to construct a 2D gamma function to enhance the image. Finally, the images are fused. The comparison with the classical algorithm shows that the algorithm in this paper can better reduce the effect of uneven illumination on the image and improve the brightness and contrast of the image.

Keywords

Multiscale; Uneven illumination; Low illumination image; Two-dimensional gamma function

Cite This Paper

Lu Chen, Lingfei Chen. Method for Correcting Low-illumination Images Based on Adaptive Two-dimensional Gamma Function. Academic Journal of Engineering and Technology Science (2022) Vol. 5, Issue 5: 34-40. https://doi.org/10.25236/AJETS.2022.050507.

References

[1] T. Wang, Z. Ji, Q. Sun, et al., Label propagation and higher-order constraint-based segmentation of flfluid-associated regions in retinal SD-OCT images, Inform. Sci. 358(2016) 92–111. 

[2] T. Wang, J. Yang, Z. Ji, et al., Probabilistic diffusion for interactive image segmentation, IEEE Trans. Image Process. 28 (1) (2019) 330–342.

[3] W. Wang, X. Yuan, X. Wu, et al., Dehazing for images with large sky region, Neurocomputing 238 (5) (2017) 365–376 2017. 

[4] W. Wang, X. Yuan, X. Wu, et al., Fast Image dehazing method based on linear transformation, IEEE Trans. Multimedia 19 (6) (2017) 1142–1155. 

[5] D'yia Sarah Md Shukri, Asmuni H, Othman R M, et al. An improved multiscale Retinex algorithm for motionblurred iris images to minimize the intra-individual (2013): 1071-1077.

[6] Li Jia. Application of image enhancement method for digitalimages based on Retinex theory [J]. Optik, 2013, 124:5986-5988.

[7] T. Huynh-The, B. Le, S. Lee, et al., Using weighted dynamic range for histogram equalization to improve the image contrast, EURASIP J. Image Video Process. 1 (1) (2014) 44. 

[8] T. Kim, J. Paik, B. Kang, Contrast enhancement system using spatially adaptive histogram equalization with temporal fifiltering, IEEE Trans. Consum. Electron. 44 (1) (1998)82–87. 

[9] Y. Wang, Q. Chen, B. Zhang, Image enhancement based on equal area dualistic sub-image histogram equalization method, IEEE Trans. Consum. Electron. 45 (1) (1999)68–75.

[10] D. Jobson, Z. Rahman, G. Woodell, Properties and performance of a center/surround Retinex, IEEE Trans. Image Process. 6 (3) (1997) 451–462.