• Journal of Information Processing Systems
• /
• v.18 no.1
• /
• pp.12-25
• /
• 2022

In recent years, deep convolutional neural networks have made significant progress in the research of single image super-resolution. However, it is difficult to be applied in practical computing terminals or embedded devices due to a large number of parameters and computational effort. To balance these problems, we propose CSRNet, a lightweight neural network based on channel split residual learning structure, to reconstruct highresolution images from low-resolution images. Lightweight refers to designing a neural network with fewer parameters and a simplified structure for lower memory consumption and faster inference speed. At the same time, it is ensured that the performance of recovering high-resolution images is not degraded. In CSRNet, we reduce the parameters and computation by channel split residual learning. Simultaneously, we propose a double-upsampling network structure to improve the performance of the lightweight super-resolution network and make it easy to train. Finally, we propose a new evaluation metric for the lightweight approaches named 100_FPS. Experiments show that our proposed CSRNet not only speeds up the inference of the neural network and reduces memory consumption, but also performs well on single image super-resolution.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.12 no.10
• /
• pp.5039-5055
• /
• 2018

The quality of natural outdoor images captured by visible camera sensors is usually degraded by the haze present in the atmosphere. In this paper, a fast image dehazing method based on visible image and near-infrared fusion is proposed. In the proposed method, a visible and a near-infrared (NIR) image of the same scene is fused based on the dual-tree complex wavelet transform (DT-CWT) to generate a dehazed color image. The color of the fusion image is regulated through haze concentration estimated by dark channel prior (DCP). The experiment results demonstrate that the proposed method outperforms the conventional dehazing methods and effectively solves the color distortion problem in the dehazing process.

• Journal of Korea Multimedia Society
• /
• v.20 no.2
• /
• pp.101-107
• /
• 2017

LabVIEW coding for video dehazing was developed. The dark channel prior proposed by K. He was applied to remove fog based on a single image, and K. B. Gibson's median dark channel prior was applied, and implemented in LabVIEW. In other words, we improved the image processing speed by converting the existing fog removal algorithm, dark channel prior, to the LabVIEW system. As a result, we have developed a real-time fog removal system that can be commercialized. Although the existing algorithm has been utilized, since the performance has been verified real - time, it will be highly applicable in academic and industrial fields. In addition, fog removal is performed not only in the entire image but also in the selected area of the partial region. As an application example, we have developed a system that acquires clear video from the long distance by connecting a laptop equipped with LabVIEW SW that was developed in this paper to a 100~300 times zoom telescope.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.29 no.2C
• /
• pp.272-282
• /
• 2004

This paper introduces a regularized mixed norm multi-channel image restoration algorithm using both within-and between- channel deterministic information. For each channel a functional which combines the least mean squares (LMS), the least mean fourth (LMF), and a smoothing functional is proposed. We introduce a mixed norm parameter that controls the relative contribution between the LMS and the LMF, and a regularization parameter defining the degree of smoothness of the solution, where both parameters are updated at each iteration according to the noise characteristics of each channel. The novelty of the proposed algorithm is that no knowledge of the noise distribution for each channel is required and that the parameters mentioned above are adjusted based on the partially restored image.

• Journal of the Korea Computer Industry Society
• /
• v.5 no.5
• /
• pp.737-746
• /
• 2004

Two-channel multiwavelet system is investigated for image compression application in this paper. Generally, multiwavelets are known for their superb capability of compressing non-stationary signals like voice. However, multivavelet system have a critical problem in processing and compressing image data due to mesh-grid visual artifacts. In our two-channel multiwavelet system we have investigated incorporation of pre and post filtering to the multiwavelet transform and compression system for alleviating those ingerent visual artifacts due to multiwavelet effect. In addition, to quantify the image data compression performance of proposed multiwavelet system, computer simulations have been performed using various image data. For bit allocation and quantization, the Lagrange multiplier technique considering data rate vs. distortion rate along with a nonlinear companding method are applied equallly to all systems considered, here. The simulation results have yielded 1 ~ 2 dB compression enhancement over the scalar savelet systems. If the more advanced compression methods like SPIHT and run-length channel coding were adopted for the proposed multiwavelet system, a much higher compression gain could be obtained.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.37 no.7A
• /
• pp.545-551
• /
• 2012

In this paper, K-band multi-channel receiver was designed and fabricated for low noise amplification and down conversion to L-band. The fabricated multi-channel receiver incorporates GaAs-HEMT LNA(Low noise amplifier) which provides less than a 2 dB noise figure, IR(Image Rejection) Filter for rejection of image frequency, IR(Image rejection) mixer to reject a image frequency and improve an IMD(Intermodulation Distortion) characteristic. Test results of the fabricated multi-channel receiver show less than a 3.8 dB noise figure, conversion gain of more than 27dB, and IP1dB(Input 1dB Gain Compression Point) of -9.5 dB and over.

• Journal of Contemporary Eastern Asia
• /
• v.16 no.1
• /
• pp.1-21
• /
• 2017

The Jakarta Provincial Government utilizes the YouTube channel to interact with citizens and enhance transparency. The purpose of this study is to explore online perceptions of local government image perceived by online audiences through the YouTube platform. The concepts of organizational image and credibility in the political image are adapted to analyze online public perceptions on the Jakarta Provincial Government image. Using the video summarization approach on Three hundred and forty-six official YouTube videos, which were uploaded from 1 March 2016 to 31 May 2016, and content analysis of Eight thousand two hundred and thirty-seven comments, this study shows both political and bureaucratic image emerge concurrently in the Jakarta Provincial Government case. The typology model is proposed to describe and explain the four image variations that occurred in the case study. Practical recommendations are suggested to manage YouTube channel as one of the social media used in the local government context.

• Proceedings of the KIEE Conference
• /
• 2005.05a
• /
• pp.179-181
• /
• 2005

There is asymmetric in horizontal and vertical side of PDP cell. Every vertical line has BM(Black Mask) to improve luminance contrast. When error diffusion is processed in PDP system, these problems make an error bigger. In 4 inch PDP system, every red, green, blue color of test pattern is presented and each luminance is measured. That is called horizontal(H), diagonal right(R), diagonal left(L) and vertical(V). In red channel, high luminance descending order is V-H-R-L. In green channel, V-H-L-R. In blue channel, V-M-R=L. After average luminance of each direction is calculated. new weighted error diffusion(Weighted ED) is proposed. In digital image signal processing, the error in weighted ED is differ from ED's. The image of weighted ED is more less error compare to conventional ED and close to original image. As the gray level linearity and big size panel is adopted, weighted ED could produce good image.

• Proceedings of the Korea Electromagnetic Engineering Society Conference
• /
• 2000.11a
• /
• pp.12-15
• /
• 2000

In this paper, we have evaluated the performance of an OFDM system using hierarchical 16QAM (OFDM/HL-16QAM) for achieving high quality and high speed data and image transmission in multipath fading channel. The wireless channel for performance evaluation is assumed to include AWGN and two ray multipath fading. Through simulation we have obtained the BER performance of the system according to $E_{b}$, $N_{0}$, then compared the received image quality of proposed system with that of conventional system. From the result, it is shown that the OFDM/HL-16QAM system is more effective for data and image transmission.n.n.

• Journal of the Institute of Convergence Signal Processing
• /
• v.15 no.3
• /
• pp.80-84
• /
• 2014

Dark channel prior means that, for undistorted outdoor images, at least one color channel of a pixel or its neighbors have values close to 0, and thus the prior can be used to estimate the amount of distortion for given distorted images. In other words, if an image is distorted by blur, its dark channel values are averaged with neighbor pixel values and thus increase. This paper proposes a method that estimates blur strengths by analyzing the variation of dark channel values caused by blur. Through experiments with images distorted by Gaussian and horizontal motion blur with given strengths, the usefulness of the proposed method is verified.