GAN-Based Local Lightness-Aware Enhancement Network for Underexposed Images

Yong Chen,Meiyong Huang,Huanlin Liu,Jinliang Zhang,Kaixin Shao 한국정보처리학회 2022 Journal of information processing systems Vol.18 No.4

Uneven light in real-world causes visual degradation for underexposed regions. For these regions, insufficientconsideration during enhancement procedure will result in over-/under-exposure, loss of details and colordistortion. Confronting such challenges, an unsupervised low-light image enhancement network is proposed inthis paper based on the guidance of the unpaired low-/normal-light images. The key components in our networkinclude super-resolution module (SRM), a GAN-based low-light image enhancement network (LLIEN), anddenoising-scaling module (DSM). The SRM improves the resolution of the low-light input images beforeillumination enhancement. Such design philosophy improves the effectiveness of texture details preservationby operating in high-resolution space. Subsequently, local lightness attention module in LLIEN effectivelydistinguishes unevenly illuminated areas and puts emphasis on low-light areas, ensuring the spatial consistencyof illumination for locally underexposed images. Then, multiple discriminators, i.e., global discriminator, localregion discriminator, and color discriminator performs assessment from different perspectives to avoid over-/under-exposure and color distortion, which guides the network to generate images that in line with humanaesthetic perception. Finally, the DSM performs noise removal and obtains high-quality enhanced images. Bothqualitative and quantitative experiments demonstrate that our approach achieves favorable results, whichindicates its superior capacity on illumination and texture details restoration.

Variational framework for low-light image enhancement using optimal transmission map and combined @?₁ and @?₂-minimization

Ko, S.,Yu, S.,Park, S.,Moon, B.,Kang, W.,Paik, J. Elsevier 2017 Signal processing Image communication Vol.58 No.-

<P>This paper presents a novel variational framework for low-light image enhancement. The proposed enhancement algorithm simultaneously performs brightness enhancement and noise reduction using a variational optimization. An edge-preserved noise reduction is performed by minimizing the total variation constraint term in the energy function. In addition, the proposed method estimates the optimal transmission map to restore the low-light image by minimizing the l(2)-norm smoothness and data-fidelity terms. To minimize the proposed energy functional, the proposed method splits the l(1)-derivative term under the split Bregman iteration framework. The performance of the proposed method is evaluated using both simulated and natural low-light images. Experimental results show that the proposed enhancement method can significantly improve the quality of the low-light images without noise amplification. (C) 2017 Elsevier B.V. All rights reserved.</P>

Contrast Enhancement for Low-light Image Enhancement: A Survey

Seonhee Park,Kiyeon Kim,Soohwan Yu,Joonki Paik 대한전자공학회 2018 IEIE Transactions on Smart Processing & Computing Vol.7 No.1

In this paper, various contrast and low-light image enhancement methods are described and classified into three categories: i) histogram-based, ii) transmission map–based, and iii) retinexbased. The performance of the image enhancement algorithms is evaluated by comparing the resulting images using low-contrast and low-light images acquired under different illumination conditions. Various image enhancement algorithms are analyzed for both performance and efficiency. The described image enhancement algorithms can be applied to various visual surveillance or video analytics applications with low-light, low-contrast video input.

Recent Trends of Light-enhanced Metal Oxide Gas Sensors: Review

( Min Kyu Cho ),( In Kyu Park ) 한국센서학회 2016 센서학회지 Vol.25 No.2

Recent light-enhanced metal oxide gas sensors are reviewed in this article. The basic mechanisms of a light-enhanced metal oxide gas sensor are discussed. Many literatures reveal that the standalone sensitivity and the response/recovery time enhancements enabled by the exposing light are not as high as the performance enhancement provided by external heating. Therefore, both optimal amount of external heating and exposed light intensity are necessary to increase the performance of these light-enhanced gas sensors. The development of highly light sensitive materials and structures is important to lower the overall power consumptions of the sensors.

Pixel-Wise Polynomial Estimation Model for Low-Light Image Enhancement

Muhammad Tahir Rasheed,Daming Shi 한국인터넷정보학회 2023 KSII Transactions on Internet and Information Syst Vol.17 No.9

Most existing low-light enhancement algorithms either use a large number of training parameters or lack generalization to real-world scenarios. This paper presents a novel lightweight and robust pixel-wise polynomial approximation-based deep network for low-light image enhancement. For mapping the low-light image to the enhanced image, pixel-wise higher-order polynomials are employed. A deep convolution network is used to estimate the coefficients of these higher-order polynomials. The proposed network uses multiple branches to estimate pixel values based on different receptive fields. With a smaller receptive field, the first branch enhanced local features, the second and third branches focused on medium-level features, and the last branch enhanced global features. The low-light image is downsampled by the factor of 2b-1 (b is the branch number) and fed as input to each branch. After combining the outputs of each branch, the final enhanced image is obtained. A comprehensive evaluation of our proposed network on six publicly available no-reference test datasets shows that it outperforms state-of-the-art methods on both quantitative and qualitative measures.

다중필터와 이방성 확산을 이용한 극 저조도 조건에서의 미광증폭장비 영상 개선

문진규(Jin-Kyu Moon) 한국산학기술학회 2018 한국산학기술학회논문지 Vol.19 No.7

미광증폭장비는 밤과 같이 어두운 환경에서 주로 가시광선 대역의 약한 빛을 증폭시켜 육안으로 관측할 수 있을 정도의 밝기로 만들어주는 장비이다. 이러한 방식은 어느 정도의 약한 빛이 존재하는 환경에서는 그 증폭 효과를 제대로 발휘하여 선명한 영상을 얻을 수 있지만, 달빛조차 존재하지 않는 극 저조도 환경에서는 기본적으로 증폭시킬 빛이 부족하여 출력 영상에 많은 노이즈로 인하여 화면의 선명도가 저하된다. 본 연구에서는 이러한 극 저조도 환경에서 발생하는 미광증폭장비의 출력 노이즈를 다중 필터와 이방성 확산을 이용하여 화질을 개선하는 방법을 제안하였다. 실험을 위하여 극 저조도조건에 맞는 환경을 구성한 상태에서 미광증폭장비의 출력 영상을 촬영한 후, 화질 개선을 위한 신호처리를 하였다. 신호처리를 위한 필터의 구성은 영상에 나타나는 주된 노이즈인 점 노이즈 제거와 가우시안 노이즈의 효과적인 제거를 위하여 메디안 필터, 위너 필터를 적용시킨 후 이방성 확산을 이용하였다. 실험 결과 화질이 개선됨을 육안으로 확인할 수 있었고, 정량지표인 PSNR 및 SSIM으로 비교하여 측정한 방법에서도 모두 개선된 값을 보여주었다. An image intensifying device is equipment that makes weak objects visible in a dark environment, such as making nighttime bright enough to let objects be visually observed. It is possible to obtain a clear image by amplifying the light in the presence of a certain amount of weak light. However, in an extremely low-light environment, where even moonlight is not present, there is not enough light to amplify anything, and the sharpness of the screen deteriorates. In this paper, a method is proposed to improve image quality by using multiple filters and anisotropic diffusion for output noise of the image-intensifying device in extreme low-light environments. For the experiment, the output of the image-intensifying device was obtained under extremely low-light conditions, and signal processing for improving the image quality was performed. The configuration of the filters for signal processing uses anisotropic diffusion after applying a median filter and a Wiener filter for effective removal of salt-and-pepper noise and Gaussian noise, which constitute the main noise appearing in the image. Experimental results show that the improvement visually enhanced image quality. Both peak signal-to-noise ratio (PSNR) and SSIM, which are quantitative indicators, show improved values.

Single-Shot Light-Field Microscopy: An Emerging Tool for 3D Biomedical Imaging

김기수 한국바이오칩학회 2022 BioChip Journal Vol.16 No.4

3D microscopy is a useful tool to visualize the detailed structures and mechanisms of biomedical specimens. In particular, biophysical phenomena such as neural activity require fast 3D volumetric imaging because fluorescence signals degrade quickly. A light-field microscope (LFM) has recently attracted attention as a high-speed volumetric imaging technique by recording 3D information in a single-snapshot. This review highlighted recent progress in LFM techniques for 3D biomedical applications. In detail, various image reconstruction algorithms according to LFM configurations are explained, and several biomedical applications such as neuron activity localization, live-cell imaging, locomotion analysis, and single-molecule visualization are introduced. We also discuss deep learning-based LFMs to enhance image resolution and reduce reconstruction artifacts.

Enhancement of picture quality on ultra-low brightness by optimizing the electrical potential required for OLED charging in the AMOLED displays

Na Se Hwan,Min Won Kyung,Kim Do Hyung,Hwang Han Wook,Ha Yong Min,Kim Hyun Jae 한국정보디스플레이학회 2021 Journal of information display Vol.22 No.4

The principal causes of the poor picture quality on active matrix organic light-emitting diode (AMOLED) displays, operating under extremely low brightness and gray-scale conditions, were analyzed and verified by measuring and modelling of the electrical simulations. Through the analysis, it was found that the deteriorated picture quality was induced by a delayed saturation voltage, which means the electric potential difference between the initial voltage applied to the anode of the OLED (Vinit) and the OLED saturated voltage (Vsat) for emission. This is because the deviations of pico-ampere-level currents and delayed OLED charging prior to light emission increased the saturation voltage when there were low driving currents. Thus, we optimized the voltage by increasing Vinit from −4.5 to −2.7 V, effectively eliminating image deterioration by reducing the OLED charging delay. Thus, the proposed approach opens up advancements of obtaining superior picture quality with ultra-low luminance, even in the dark illuminance environments.Wediscusshow OLED picture quality may be enhanced under low brightness, including the driving methods, design considerations, and processes involved.

Design and Analysis of Diffractive Grating Imprinted Light-guide Plate for LCD Illumination

Choi, Hwan-Young,Park, Young-Pil The Korean Infomation Display Society 2004 Journal of information display Vol.5 No.1

A highly simplified backlight unit mainly composed of diffractive grating in sub-micron order imprinted light-guide plate (LGP) is proposed for edge-lit backlight unit. Optical characteristics of the imprinted LGP are examined by RCWA and the performance is verified through Monte Carlo simulation. Results show that the diffraction efficiency, luminous flux and its uniformity over the area are significantly affected by the angle of incident ray. Consequently couples of design considerations are additionally proposed to enhance luminous flux. In terms of peak luminance and out-coupling luminous flux, the experimental results are agreed well with the performance simulation. Finally, compared with optical characteristics of conventional backlight unit, we could conclude that the proposed simplified backlight unit made of diffractive grating imprinted light-guide plate is a good substitute for the conventional backlight unit.

Thermally Evaporated SiO Thin Films As a Versatile Interlayer for Plasma-Based OLED Passivation

Yun, Won Min,Jang, Jaeyoung,Nam, Sooji,Kim, Lae Ho,Seo, Sang Joon,Park, Chan Eon American Chemical Society 2012 ACS APPLIED MATERIALS & INTERFACES Vol.4 No.6

<P>Silicon monoxide (SiO) thin films were introduced as an efficient interlayer for achieving plasma-based organic light-emitting diode (OLED) surface passivation. The SiO thin films could be consecutively formed via thermal evaporation, without breaking the vacuum, after deposition of the OLED cathode. The plasma resistivity and UV-blocking characteristics of the SiO interlayer protected the OLED devices against electrical and optical degradation during the plasma-enhanced atomic layer deposition (PEALD) and plasma-enhanced chemical vapor deposition (PECVD) passivation processes. In addition, the nonconformal deposition and hydroxyl group-rich surface characteristics of the SiO thin films yielded enhanced surface pinhole coverage and a higher initial film density in the subsequently deposited PEALD-based Al<SUB>2</SUB>O<SUB>3</SUB> barrier film. As a result, the OLEDs with a SiO/Al<SUB>2</SUB>O<SUB>3</SUB> bilayer passivation layer displayed a remarkably increased device shelf life compared to devices prepared using Al<SUB>2</SUB>O<SUB>3</SUB>-only passivation. A MOCON test showed that the water vapor transmission rate (WVTR) of the SiO/Al<SUB>2</SUB>O<SUB>3</SUB> bilayer film was 0.0033 g/(m<SUP>2</SUP> day), 2.3 times lower than the rate of a single Al<SUB>2</SUB>O<SUB>3</SUB> barrier film. The results of our study demonstrated the multipurpose role of a SiO interlayer in plasma-based OLED passivation. The layer acted as a damage-free protective layer for the underlying OLED devices and an assistant layer to improve the upper barrier film performance.</P><P><B>Graphic Abstract</B> <IMG SRC='http://pubs.acs.org/appl/literatum/publisher/achs/journals/content/aamick/2012/aamick.2012.4.issue-6/am300600s/production/images/medium/am-2012-00600s_0006.gif'></P><P><A href='http://pubs.acs.org/doi/suppl/10.1021/am300600s'>ACS Electronic Supporting Info</A></P>