• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.15 no.5
• /
• pp.1814-1828
• /
• 2021

Low-light image enhancement is a key technique to overcome the quality degradation of photos taken under scotopic vision illumination conditions. The degradation includes low brightness, low contrast, and outstanding noise, which would seriously affect the vision of the human eye recognition ability and subsequent image processing. In this paper, we propose an approach based on deep learning and Retinex theory to enhance the low-light image, which includes image decomposition, illumination prediction, image reconstruction, and image optimization. The first three parts can reconstruct the enhanced image that suffers from low-resolution. To reduce the noise of the enhanced image and improve the image quality, a super-resolution algorithm based on the Laplacian pyramid network is introduced to optimize the image. The Laplacian pyramid network can improve the resolution of the enhanced image through multiple feature extraction and deconvolution operations. Furthermore, a combination loss function is explored in the network training stage to improve the efficiency of the algorithm. Extensive experiments and comprehensive evaluations demonstrate the strength of the proposed method, the result is closer to the real-world scene in lightness, color, and details. Besides, experiments also demonstrate that the proposed method with the single low-light image can achieve the same effect as multi-exposure image fusion algorithm and no ghost is introduced.

• Proceedings of the Korean Society for Technology of Plasticity Conference
• /
• 2009.10a
• /
• pp.209-212
• /
• 2009

It has been widely reported that carbide-free bainitic steels or super-bainite WP (SB-TRIP) steels for the automotive industry are a new family of steels offering a unique combination of high strength and ductility. Hence, it is important to exactly evaluate the volume fraction of RA and to identify the 3-D morphology of constituent phases, because it plays a crucial role in mechanical properties. Recently, as electron back-scattered diffraction (EBSD) equipped with focused ion beam (FIB) has been developed, 3-D EBSD technique for materials science are used to these steels. Moreover, newly developed atom probe tomography (APT) technique can provide the exact distribution and chemical concentration of alloying elements in a sub-nm scale. The APT analysis results indicate exactly the distribution and composition of alloying elements in the austenite and bainite phases of SB-TRIP steels with the atomic-scale resolution. And thus, no partitioning of aluminum and manganese atoms was showed between the austenite containing $7.73{\pm}0.39$ at% C and the bainitic ferrite associated with $0.22{\pm}0.06$ at% C in the SB-TRIP steel.

• Transactions of Materials Processing
• /
• v.19 no.1
• /
• pp.44-49
• /
• 2010

It has been widely reported that carbide-free bainitic steels or super-bainite TRIP (SB-TRIP) steels for the automotive industry are a new family of steels offering a unique combination of high strength and ductility. Hence, it is important to exactly evaluate the volume fraction of RA and to identify the 3-D morphology of constituent phases, because it plays a crucial role in mechanical properties. Recently, as electron back-scattered diffraction (EBSD) equipped with focused ion beam (FIB) has been developed, 3-D EBSD technique for materials science are used to these steels. Moreover, newly developed atom probe tomography (APT) technique can provide the exact distribution and chemical concentration of alloying elements in a sub-nm scale. The APT analysis results indicate exactly the distribution and composition of alloying elements in the austenite and bainite phases of SB-TRIP steels with the atomic-scale resolution. And thus, no partitioning of aluminum and manganese atoms was showed between the austenite containing $7.73{\pm}0.39$ at% C and the bainitic ferrite associated with $0.22{\pm}0.06$ at% C in SB-TRIP steel.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.51 no.3
• /
• pp.105-111
• /
• 2014

Image resolution enhancement is a technique to generate high-resolution image through improving resolution of low-resolution obtained image. It is important to estimate correctly missing pixel value in low-resolution obtained image for image resolution enhancement. In this paper, multiple shortfall estimation method for image resolution enhancement is proposed. The proposed method estimate separate multiple shortfall by predictive degradation-restoration processing in sub-images of obtained image, and generate result image combining the estimated shortfall and interpolated obtained-image. Lastly, final reconstruction image is generated by deblurring of the result image. The experimental results demonstrate that the proposed method has the best results of all compared methods in objective image quality index: PSNR, SSIM, and FSIM. The quality of reconstructed image is superior to all compared methods, and the proposed method has better lower computational complexity than compared methods. The proposed method can be useful for image resolution enhancement.

• Journal of Korea Multimedia Society
• /
• v.16 no.10
• /
• pp.1180-1188
• /
• 2013

Interpolation or super-resolution is used in order to restore degradation of image quality that appears after various transform of image. The method on subjective or objective image resolution improvement having low computation complexity has been being researched in many different ways. In this paper, image enhancement method using improved self degradation restoration(ISDR) method is proposed. The proposed method uses ISDR to estimate pixel value of missed coordinate in the process of image scaling, and combines the estimated loss information and interpolated image to generate enhanced result image. The proposed method shows that PSNR increases by 1.8dB, and subjective image quality is superior to other compared methods. The proposed method can be applied as a basis technique in variety of applications which requires image scale transform.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.23 no.4
• /
• pp.93-98
• /
• 2023

Recently, as the size of display devices tends to increase and taking pictures with smart phones has become commonplace, the need for taking high-resolution pictures with smart phones is increasing. However, when the lens size of a camera is limited, such as in a smartphone, there is a physical limit to increasing the resolution of a photo. This paper is about a technique for increasing the resolution of a picture even when using a small-sized lens like a smartphone camera. It is to take multiple pictures while moving the smartphone, and to increase the resolution by combining these pictures into one picture. First of all, two pictures were taken while moving the smartphone horizontally for the 2D picture. Processes such as camera matrix estimation, and homograph inverse transformation were performed using OpenCV, and the resolution was improved by synthesizing one picture. It was confirmed that the resolution was improved in parts such as oblique lines or arcs on several test pictures.

• The Journal of Korean Institute of Electromagnetic Engineering and Science
• /
• v.30 no.4
• /
• pp.275-281
• /
• 2019

A synthetic aperture radar(SAR) satellite is more effective than an optical satellite for target analysis because an SAR satellite can provide two-dimensional electromagnetic scattering distribution of a target during all-weather and day-and-night operations. To conduct target analysis while considering the earth observation interval of an SAR satellite, observing a specific area as wide as possible would be advantageous. However, wider the observation area, worse is the resolution of the associated SAR satellite image. Although conventional methods for improving the resolution of radar images can be employed for addressing this issue, few studies have been conducted for improving the resolution of SAR satellite images and analyzing the performance. Hence, in this study, the applicability of conventional methods to SAR satellite images is investigated. SAR target detection was first applied to Korea Multipurpose Satellite-5(KOMPSAT-5) SAR images provided by Korea Aerospace Research Institute for extracting target responses. Extrapolation, RELAX, and MUSIC algorithms were subsequently applied to the target responses for improving the resolution, and the corresponding performance was thereby analyzed.

• Journal of Broadcast Engineering
• /
• v.24 no.5
• /
• pp.775-784
• /
• 2019

Image stitching is a technique for solving the problem of narrow field of view of a camera by composing multiple images. Recently, as the use of content such as Panorama, Super Resolution, and 360 VR increases, the need for faster and more accurate image stitching technology is increasing. So far, many algorithms have been proposed to satisfy the required performance, but the objective evaluation method for measuring the accuracy has not been standardized. In this paper, we present the problems of PSNR and SSIM(Structural similarity index method) measurement methods and propose a Local Differential Pixel Mean method. The LDPM evaluation method that includes geometric similarity and brightness measurement information is proved through a test, and the advantages of the evaluation method are revealed through comparison with SSIM.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2020.07a
• /
• pp.656-659
• /
• 2020

초해상화 딥러닝 기법은 학습 시 수렴하기까지 최소 수백 번의 에폭을 필요로 하며 오랜 시간이 걸린다. 최근, 영상 인식용 딥러닝 모델에서는 학습 수렴 속도를 향상시키기 위해 픽셀, 채널간 불필요한 상호연관 정보를 제거하는 Deconvolution 기술이 제안되었다. 본 논문에서는 최초로 Deconvolution 기술을 초해상화 딥러닝 방법에 적용하여 학습 수렴 속도 증가를 시도했다. 영상 인식 딥러닝 기법과 다르게 초해상화 딥러닝 기법은 이미지 특성 추출 부분과 이미지 복원 부분의 정보를 보존하는 것이 중요하기 때문에, EDSR을 Baseline 모델로 사용하여 양쪽 끝의 레이어는 기존의 Convolution 연산을 그대로 유지하고, 중간 레이어의 ResBlock 내의 Convolution 연산만 Deconvolution 연산으로 바꿔서 구성하였다. 초해상화 벤치마크 데이터셋을 사용한 실험 결과, 수렴속도가 빨라지지 않는 결과를 도출했다. 본 논문에서는 Deconvolution 기술이 Baseline 모델의 성능을 개선하지 못하는 이유를 초해상화 분야에서 기본적으로 적용되는 Residual Learning 기법 때문으로 분석했다.

• Journal of Mechanical Science and Technology
• /
• v.17 no.11
• /
• pp.1704-1713
• /
• 2003

Point contact film thickness in elastohydrodynamic lubrication (EHL) is analyzed by image processing method for the images from an optical interferometer with monochromatic incident light. Interference between the reflected lights both on half mirror Cr coating of glass disk and on super finished ball makes circular fringes depending on the contact conditions such as sliding velocity, applied load, viscosity-pressure characteristics and viscosity of lubricant under ambient pressure. In this situation the film thickness is regarded as the difference of optical paths between those reflected lights, which make dark and bright fringes with monochromatic incident light. The film thickness is computed by numbering the dark and bright fringe orders and the intensity (gray scale image) in each fringe regime is mapped to the corresponding film thickness. In this work, we developed a measuring technique for EHL film thickness by dividing the image patterns into two typical types under the condition of monochromatic incident light. During the image processing, the captured image is converted into digitally formatted data over the contact area without any loss of the image information of interferogram and it is also interpreted with consistency regardless of the observer's experimental experience. It is expected that the developed image processing method will provide a valuable basis to develop the image processing technique for color fringes, which is generally used for the measurement of relatively thin films in higher resolution.