• Journal of Information Processing Systems
• /
• v.19 no.6
• /
• pp.858-869
• /
• 2023

As one of the pivotal techniques of image restoration, single-channel blind source separation (SCBSS) is capable of converting a visual-only image into multi-source images. However, image degradation often results from multiple mixing methods. Therefore, this paper introduces an innovative SCBSS algorithm to effectively separate source images from a composite image in various mixed modes. The cornerstone of this approach is a novel triple generative adversarial network (TriGAN), designed based on dual learning principles. The TriGAN redefines the discriminator's function to optimize the separation process. Extensive experiments have demonstrated the algorithm's capability to distinctly separate source images from a composite image in diverse mixed modes and to facilitate effective image restoration. The effectiveness of the proposed method is quantitatively supported by achieving an average peak signal-to-noise ratio exceeding 30 dB, and the average structural similarity index surpassing 0.95 across multiple datasets.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.15 no.1
• /
• pp.41-50
• /
• 1997

This study is aimed to suggest the method, color channel seperation, can match the common points in real-time automatically. Image coordinates which was calculated from the acquired image with CCDcamera in this study is checked with two methods; check the accuracy of image coordinate and common point matching through correct sort. In conclusion of check, The RMSE of object coordinate which is calculated by photogrammetry program with image coordinate is in the expect RMSE of close-range photogrammetry, and Match-ing of common point is also performed correctly by using sort. For these reason, this color channel separation method is adequate for the acquisition of accurate image coordinates and the matching of the common points. I think that this method will be useful for the fields of industry which need fast-correct processing with acquired information in real-time.

• Journal of Korean Ophthalmic Optics Society
• /
• v.10 no.1
• /
• pp.1-8
• /
• 2005

Color vision of color vision deficiency is possible using Color space's conversion of color image. Color vision of the RG-Color vision deficiency is possible by the case to maximize the G channel(+100), the case to minimize the G channel(-100), the case to maximize the R channel(+100), the case to convert the R channel to the yellow(Y) channel that is the value of $(-)b^*$ coordinate in CIE $L^*a^*b^*$ color space, the case to separate with only the B channel and the G channel and to appear by the light and darkness difference again, and the case to receive the image only by the light and darkness after separation of saturation and conversion of RGB channel.

• Journal of Information Display
• /
• v.11 no.1
• /
• pp.24-27
• /
• 2010

A novel stereo 3D LCD for passive interference filter glasses is presented. A demonstrator based on a standard 120Hz LCD was set up. Stereoscopic image separation was realized in a time-sequential mode using a LED-based scanning backlight with two complementary spectra. A stereo brightness of 3 cd/$m^2$ and a channel separation of 30:1 were achieved.

• Journal of Korea Water Resources Association
• /
• v.39 no.4 s.165
• /
• pp.313-320
• /
• 2006

In this study, hydraulic characteristics of thalweg line occurred near the single groyne and recirculation zone around downstream of the structure were discussed from the experiments which conducted in fixed flat-bed channel flume. The thalweg line is the stream line where the maximum velocity occurs and flow separation appeared at the tip of groyne changes the thalweg alignment. In this study, the variations in flow fields which were caused by different length and permeability of groyne were measured by LSPIV(Large Scale Particle Image Velocimetry), and also the characteristics of thalweg line and separation area were analyzed. From these results, it is found that length to thalweg line from the channel wall $T_{CL}$ and height of separation area $S_h$ vary the channel width up to 75%, 50% in the change of length and permeability of groyne, however the Froude number does not affect on $T_{CL}$ and $S_h$. Velocity along the thalweg $U_{CL}$ Increased by twice the mean velocity, and the maximum velocity occurred in downstream where the distance $5{\sim}6$ times of groyne length away from the groyne, which does not get affected by length and permeability of groyne and Froude number.

• Journal of Korea Water Resources Association
• /
• v.41 no.7
• /
• pp.653-667
• /
• 2008

The hydraulic model test for the L-type Groynes with "ㄱ" shape were conducted to analyze flow characteristics around these groynes. The results of model tests should be used for the fundamental information to design the L-type Groyne constructed in the field. Main hydraulic factors such as the velocity and thalweg line changes in main channel and separation area were analyzed in this study. The thalweg line is stream line where the maximum velocity occurs, and the separation area is a boundary of main flow and recirculation zone. Model tests with 5 different arm-lengths of the L-type Groynes were conducted changing the velocity. The LSPIV(Large Scale Particle Image Velocimetry) technique was used to measure and analyze the flow variation around the L-type Groynes. The velocity in main channel was increased 1.5 times and there was no effects of different groyne arm-length on the velocity changes. The width of thalweg lines $(T_{CL})$ was changed to $55{\sim}58%$ of chanel width, and the Froude number did not affect on the thalweg line $(T_{CL})$ and separation line $(S_h)$ changes.

• Journal of Digital Policy
• /
• v.2 no.3
• /
• pp.1-7
• /
• 2023

In this paper, I proposes a method for performing single image super resolution by separating texture-spatial domains and then classifying features based on detailed information. In CNN (Convolutional Neural Network) based super resolution, the complex procedures and generation of redundant feature information in feature estimation process for enhancing details can lead to quality degradation in super resolution. The proposed method reduced procedural complexity and minimizes generation of redundant feature information by splitting input image into two channels: texture and spatial. In texture channel, a feature refinement process with step-wise skip connections is applied for detail restoration, while in spatial channel, a method is introduced to preserve the structural features of the image. Experimental results using proposed method demonstrate improved performance in terms of PSNR and SSIM evaluations compared to existing super resolution methods, confirmed the enhancement in quality.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.47 no.5
• /
• pp.18-24
• /
• 2010

In this paper, a new matrix decoding system using vector based Virtual Source Location Information (VSLI) is proposed as an alternative to the conventional Dolby Pro logic II/IIx system for reconstructing multi-channel output signals from matrix encoded two channel signals, Lt/Rt. This new matrix decoding system is composed of passive decoding part and active part. The passive part makes crude multi-channel signals using linear combination of the two encoded signals(Lt/Rt) and the active part enhances each channel regarding to the virtual source which is emergent in each inter channel. Since the virtual sources are related to the perceptual sound images in virtual sound field, the reconstructed multi-channel sound results in good dynamic perception and stable image localization. Moreover, the good channel separation is maintained with nonlinear trigonometric enhancing function.

• Composites Research
• /
• v.27 no.5
• /
• pp.183-189
• /
• 2014

Experimental considerations have been performed to obtain the clear optical microscopic images of graphene oxide which are useful to probe its quality and morphological information such as a shape, a size, and a thickness. In this study, we investigated the contrast enhancement of the optical images of graphene oxide after hydrazine vapor reduction on a Si substrate coated with a 300 nm-thick $SiO_2$ dielectric layer. Also, a green-filtered light source gave higher contrast images comparing to optical images under standard white light. Furthermore, it was found that a image channel separation technique can be an alternative to simply identify the morphological information of graphene oxide, where red, green, and blue color values are separated at each pixels of the optical image. The approaches performed in this study can be helpful to set up a simple and easy protocol for the morphological identification of graphene oxide using a conventional optical microscope instead of a scanning electron microscopy or an atomic force microscopy.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.18 no.5
• /
• pp.919-926
• /
• 2023

In this paper, we implemented the surveillance camera system capable of day and night shooting. To this end, it is designed to capture clear images even at night using a CMOS image sensor as well as an IR-LED. In addition, a relatively simple motion detection algorithm was proposed through color model separation. Motions can be detected by extracting only the H channel from the color model, dividing the image into blocks, and then applying the block matching method using the average color value between consecutive frames. When motions are detected during filming, an alarm sounds automatically and a day and night motion detection system is implemented that can capture and save the event screen to a PC.