Image Enhancement and Denoising in Extreme Low-Light Conditions
Utsav Krishnan1, Ayush Agarwal2, Avinash Senthil3, Pratik Chattopadhyay4

1Utsav Krishnan, Department of Computer Science and Engineering, Indian Institute of Technology (Banaras Hindu University), Varanasi.
2Ayush Agarwal, Department of Electronics and Communication Engineering, Motilal Nehru National Institute of Technology Allahabad.
3Avinash Senthil, Department of Electrical and Electronics Engineering, National Institute of Technology, Tiruchirappalli.
4Pratik Chattopadhyay, Department of Computer Science and Engineering, Indian Institute of Technology (Banaras Hindu University), Varanasi

Manuscript received on October 16, 2019. | Revised Manuscript received on 25 October, 2019. | Manuscript published on November 10, 2019. | PP: 5259-5264 | Volume-9 Issue-1, November 2019. | Retrieval Number: A9243119119/2019©BEIESP | DOI: 10.35940/ijitee.A9243.119119
Open Access | Ethics and Policies | Cite | Mendeley | Indexing and Abstracting
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC-BY-NC-ND license (

Abstract: Image noise refers to the specks of false colors or artifacts that diminish the visual quality of the captured image. It has become our daily experience that with affordable smart-phone cameras we can capture high clarity photos in a brightly illuminated scene. But using the same camera in a poorly lit environment with high ISO settings results in images that are noisy with irrelevant specks of colors. Noise removal and contrast enhancement in images have been extensively studied by researchers over the past few decades. But most of these techniques fail to perform satisfactorily if the images are captured in an extremely dark environment. In recent years, computer vision researchers have started developing neural network-based algorithms to perform automated de-noising of images captured in a low-light environment. Although these methods are reasonably successful in providing the desired de-noised image, the transformation operation tends to distort the structure of the image contents to a certain extent. We propose an improved algorithm for image enhancement and de-noising using the camera’s raw image data by employing a deep U-Net generator. The network is trained in an end-to-end manner on a large training set with suitable loss functions. To preserve the image content structures at a higher resolution compared to the existing approaches, we make use of an edge loss term in addition to PSNR loss and structural similarity loss during the training phase. Qualitative and quantitative results in terms of PSNR and SSIM values emphasize the effectiveness of our approach.
Keywords: Image Noise, PSNR, ISO, Illumination, Network based Algorithms.
Scope of the Article: Algorithm Engineering