To address the issues of low brightness, low contrast, color distortion, and noise in low-light images, a multi-scale fusion-based low-light image enhancement method is proposed. Firstly, a fast and efficient algorithm is employed to enhance the image brightness. Subsequently, the enhanced RGB image is transformed into the image in HSV color space, the luminance components are processed by the improved contrast limited adaptive histogram equalization(CLAHE), guided filtering, and sharp-smoothing filtering, respectively, and three luminance components are obtained. Finally, the three processed luminance components and corresponding weights are fused by multi-scale fusion, and the obtained HSV image is transformed into the image in RGB color space, and the ultimate enhanced image is attained. The experimental results show that the proposed algorithm is superior in the evaluation index and has better information entropy, natural image quality, and average gradient values. The algorithm improves image brightness, enhances details, eliminates noise significantly, processes images more comprehensively, and improves the visual quality and clarity of images significantly.
SHEETS S M, TANT S, AS’ARIM A, et al. Retinal disease identification using upgraded CLAHE filter and transfer convolution neural network[J]. ICT Express, 2022, 8(1): 142-150.
[2]
PRINCEH, T B. An effective underwater image enhancement based on the fusion of CLAHE and image constancy sharpening technique[J]. Earth Science Informatics, 2024, 17(2): 1359-1372.
[3]
LANDE H, MCCANNJ J. Lightness and retinex theory[J]. Journal of the Optical Society of America, 1971, 61(1): 1-11.
[4]
JOBSOND J, RAHMANZ, WOODELLG A. Properties and performance of a center/surround retinex[J]. IEEE Transactions on Image Processing, 1997, 6(3): 451-462.
[5]
JOBSOND J, RAHMANZ, WOODELLG A. A multiscale retinex for bridging the gap between color images and the human observation of scenes[J]. IEEE Transactions on Image Processing, 1997, 6(7): 965-976.
[6]
TANGH, LIUG, QIANY, et al. EgeFusion: towards edge gradient enhancement in infrared and visible image fusion with multi-scale transform[J]. IEEE Transactions on Computational Imaging, 2024, 10: 385-398.
[7]
YANGS, ZHOUD, CAOJ, et al. LightingNet: an integrated learning method for low-light image enhancement[J]. IEEE Transactions on Computational Imaging, 2023, 9: 29-42.
[8]
WEIX, LINX, LIY. DA-DRN: a degradation-aware deep Retinex network for low-light image enhancement[J]. Digital Signal Processing, 2024, 144: 104256.
DENGG, GALETTOF, AL–NASRAWIM, et al. A guided edge-aware smoothing-sharpening filter based on patch interpolation model and generalized gamma distribution[J]. IEEE Open Journal of Signal Processing, 2021, 2: 119-135.
[11]
DONGX, WANGG, PANGY, et al. Fast efficient algorithm for enhancement of low lighting video[C]//2011 IEEE International Conference on Multimedia and Expo, 2011: 1-6.
[12]
HEK, SUNJ, TANGX. Guided image filtering[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2013, 35(6): 1397-1409.
[13]
FUX, ZENGD, HUANGY, et al. A fusion-based enhancing method for weakly illuminated images[J]. Signal Processing, 2016, 129: 82-96.
[14]
PARTHASARATHYS, SANKARANP. An automated multi scale retinex with color restoration for image enhancement[C]//2012 National Conference on Communications (NCC), 2012: 1-5.
[15]
HAOS, HANX, GUOY, et al. Low-light image enhancement with semi-decoupled decomposition[J]. IEEE Transactions on Multimedia, 2020, 22(12): 3025-3038.
[16]
XUZ, WANGW, CUIZ, et al. A low-light image enhancement algorithm based on optimized multi-illumination fusion[C]//2022 7th International Conference on Image, Vision and Computing (ICIVC), 2022: 549-554.
[17]
LIUR, MAL, ZHANGJ, et al. Retinex-inspired unrolling with cooperative prior architecture search for low-light image enhancement[C]//2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2021: 10556-10565.
[18]
LIC, GUOC, LOYC C. Learning to enhance low-light image via zero-reference deep curve estimation[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2022, 44(8): 4225-4238.
GUONiu, GUIZhiguo, LIUYi, et al. Local contrast stretch enhancement algorithm for X-ray images based on fuzzy entropy[J]. Journal of Test and Measurement Technology, 2023, 37(1): 29-36. (in Chinese)
[21]
MITTALA, SOUNDARARAJANR, BOVIKA C. Making a “completely blind” image quality analyzer[J]. IEEE Signal Processing Letters, 2013, 20(3): 209-212.
ZHANGWenlu, LIUYi, ZHANGPengcheng, et al. A X-ray image enhancement algorithm based on a simple radiographic scattering model[J]. Journal of North University of China (Natural Science Edition), 2021, 42(5): 441-448. (in Chinese)