A Multi-Cues Fusion Method for Low Illumination Image Enhancement
1
조회
0
다운로드
0
인용
0
참고문헌
키워드
초록
To improve the visual perception of low-illumination images, image enhancement is usually required aftercapturing low-illumination images. Although some popular image enhancement methods can obtain someadvantages such as high pixel value, high denoising performance, and fast response time, it is not enough forthem to achieve good visual effects overall. In this paper, a multi-cues fusion method is presented, which canget a better image enhancement result with limited time consumption. After undergoing homomorphic filtering,guided filtering and Retinex enhancement, three basic fusion source images for multi-cues fusion processingare shown clearly provided by the original low-illuminance color image. Then, components with similarfrequency and orientation decomposition properties are fused together to reconstruct and eventually form anenhanced image after discrete wavelet decomposition and principal component analysis. In conclusion,experimental results obtained in the paper show clearly that the proposed method can improve the visualperception and hold the visual consistence in different illumination conditions. By qualitative and quantitativetests, the proposed method has many better advantages than those state-of-the-art algorithms.
Abstract
To improve the visual perception of low-illumination images, image enhancement is usually required aftercapturing low-illumination images. Although some popular image enhancement methods can obtain someadvantages such as high pixel value, high denoising performance, and fast response time, it is not enough forthem to achieve good visual effects overall. In this paper, a multi-cues fusion method is presented, which canget a better image enhancement result with limited time consumption. After undergoing homomorphic filtering,guided filtering and Retinex enhancement, three basic fusion source images for multi-cues fusion processingare shown clearly provided by the original low-illuminance color image. Then, components with similarfrequency and orientation decomposition properties are fused together to reconstruct and eventually form anenhanced image after discrete wavelet decomposition and principal component analysis. In conclusion,experimental results obtained in the paper show clearly that the proposed method can improve the visualperception and hold the visual consistence in different illumination conditions. By qualitative and quantitativetests, the proposed method has many better advantages than those state-of-the-art algorithms.
참고문헌 (18)
- X. Liu, "Survey of natural image enhancement techniques : classification, evaluation, challenges, and perspectives", Digital Signal Processing, 127 (2022)[DOI]
- M. Veluchamy, "Image contrast and color enhancement using adaptive gamma correction and histogram equalization", Optik, 183, pp.329~337 (2019)[DOI]
- C. Li, "Color correction based on CFA and enhancement based on Retinex with dense pixels for underwater images", IEEE Access, 8, pp.155732~155741 (2020)[DOI]
- J. L. Lisani, "Analyzing center", surround Retinex, 2020, pp.512, 741~759
- S. Liu, "Recognition of road cracks based on multi-scale Retinex fused with wavelet transform", Array, 15 (2022)[DOI]
- F. Wang, "Low-light image joint enhancement optimization algorithm based on frame accumulation and multi-scale Retinex", Ad Hoc Networks, 113 (2021)[DOI]
- R. Sharma, "A versatile medical image enhancement algorithm based on wavelet transform", Journal of Information Processing Systems, 17(6), pp.1170~1178 (2021)[DOI]
- M. Luo, "An effective underwater image enhancement method based on CLAHE-HF", Journal of Physics: Conference Series, 1237(3) (2019)
- L. Huang, "Obstacle distance measurement under varying illumination conditions based on monocular vision using a cable inspection robot", IEEE Access, 9, pp.55955~55973 (2021)[DOI]
- K. Lu, "TBEFN : a two-branch exposure-fusion network for low-light image enhancement", IEEE Transactions on Multimedia, 23, pp.4093~4105 (2021)[DOI]
- Y. Jiang, "EnlightenGAN : deep light enhancement without paired supervision", IEEE Transactions on Image Processing, 30, pp.2340~2349 (2021)[DOI]
- Y. Wu, "Non-uniform low-light image enhancement via non-local similarity decomposition model", Signal Processing: Image Communication, 93 (2021)[DOI]
- S. Bhat, "Multi-focus image fusion using neutrosophic based wavelet transform", Applied Soft Computing, 106 (2021)[DOI]
- N. Y. Tiuftiakov, "Digital color analysis for colorimetric signal processing : towards an analytically justified choice of acquisition technique and color space", Sensors and Actuators B: Chemical, 344 (2021)[DOI]
- O. S. Faragallah, "PCA based SVD fusion for MRI and CT medical images", Journal of Intelligent & Fuzzy Systems, 41(2), pp.4021~4033 (2021)[DOI]
- J. Liu, "Learning full-reference quality-guided discriminative gradient cues for lane detection based on neural networks", Journal of Visual Communication and Image Representation, 65 (2019)[DOI]
- M. S. Treder, "Quality assessment of anatomical MRI images from generative adversarial networks : human assessment and image quality metrics", Journal of Neuroscience Methods, 374 (2022)[DOI]
- H. Rahman, "Tripartite sub-image histogram equalization for slightly low contrast gray-tone image enhancement", Pattern Recognition, 134 (2023)[DOI]