Structure revealing of low-light images using wavelet transform based on fractional-order denoising and multiscale decomposition

• Published in: The Visual computer Vol. 37; no. 5; pp. 865 - 880
• Main Authors: Rahman, Ziaur, Pu, Yi-Fei, Aamir, Muhammad, Wali, Samad
• Format: Journal Article
• Language: English
• Published: Berlin/Heidelberg Springer Berlin Heidelberg 01.05.2021; Springer Nature B.V
• Subjects: Algorithms; Artificial Intelligence; Color; Computer Graphics; Computer Science; Data loss; Decomposition; Illumination; Image enhancement; Image Processing and Computer Vision; Image quality; Image reconstruction; Light; Low visibility; Methods; Multimedia; Noise reduction; Original Article; Performance enhancement; Vision systems; Wavelet transforms; White balance; Fractional-order denoising; Multiscale decomposition; DT-CWT; Image enhancement
• ISSN: 0178-2789; 1432-2315
• DOI: 10.1007/s00371-020-01838-0

Images captured in low-light environment often lower its quality due to low illumination and high noise. Hence, the low visibility of images notably degrades the overall performance of multimedia and vision systems that are typically designed for high-quality inputs. To resolve this problem, numerous algorithms have been proposed in extant literature to improve the visual quality of low-light images. However, existing approaches are not good at improving overexposed portions and produce unnecessary distortion, which leads to poor visibility in images. Therefore, in this paper, a new model is proposed to prevent overenhancement, handle uneven illumination, and suppress noise in underexposed images. Firstly, the input image is converted into HSV color space. Then, the obtained V component is decomposed into high- and low-frequency subbands using the dual-tree complex wavelet transform. Secondly, a denoised model based on fractional-order anisotropic diffusion is applied on high-pass subbands. Thirdly, multiscale decomposition is used to extract more details from low-pass subbands, and inverse transformation is performed to compute final V. Next, sigmoid function and tone mapping are used on V-channel to prevent data loss and achieve robust results. Finally, the image is reconstructed and converted to RGB color space to achieve enhanced performance. Comparative experimental statistics show that the proposed method achieves high efficacy and outperforms the traditional approaches in terms of overall performance.