• IEMEK Journal of Embedded Systems and Applications
• /
• v.15 no.2
• /
• pp.61-70
• /
• 2020

Convolutional Neural Networks (CNN) have been used extensively in recent times to solve image classification and segmentation problems. However, the use of CNNs in image super-resolution problems remains largely unexploited. Filter interpolation and prediction model methods are the most commonly used algorithms in super-resolution algorithm implementations. The major limitation in the above named methods is that images become totally blurred and a lot of the edge information are lost. In this paper, we analyze super resolution based on CNN and the wavelet transform super resolution method. We compare and analyze the performance according to the number of layers and the training data of the CNN.

• International Journal of Advanced Culture Technology
• /
• v.8 no.4
• /
• pp.229-234
• /
• 2020

Dehazing significantly improves image quality by restoring the loss of contrast and color saturation for images taken in the presence. However, when applied to images not taken according to the prior information, dehazing can cause unintended degradation of image quality. To avoid unintended degradations, we present a hazy scene detection algorithm using a single image based on the distributions of hue, saturation, and dark channel. Through a heuristic approach, we find out statistical characteristics of the distribution of hue, saturation, and dark channels in the hazy scene and make a detection model using them. The proposed method can precede the dehazing to prevent unintended degradation. The detection performance evaluated with a set of test images shows a high hit rate with a low false alarm ratio. Ultimately the proposed method can be used to control the effect of dehazing so that the dehazing can be applied to wide variety of images without unintended degradation of image quality.

• Journal of Korea Society of Industrial Information Systems
• /
• v.14 no.5
• /
• pp.139-148
• /
• 2009

In this paper, I propose an automatic analysis method of golf swine from single-camera video sequences. I define necessary swing features for automatic swing analysis in 2-dimensional environment and present efficient swing analysis methods using various image processing techniques including line and edge detection. The proposed method has two characteristics compared with previous swing analysis systems and related studies. First, the proposed method enables an automatic swing analysis in 2-dimension while previous systems require 3-dimensional environment which is relatively complex and expensive to run. Second, swing analysis is done automatically without human intervention while other 2-dimensional systems necessarily need analysis by a golf expert. I tested the method on 20 swing video sequences and found the proposed method works effective for automatic analysis of golf swing.

• Journal of the Korean Society of Safety
• /
• v.29 no.5
• /
• pp.15-21
• /
• 2014

The aim of this work is conduct the study on light weight and structural performance improvement of the composite wind power blade. GFRP (Glass Fiber Reinforced Plastic) pre-empted by CFRP(Carbon Fiber Reinforced Plastic), the major material of wind power blade, was identified the superiority of mechanical performance through the tensile and fatigue test. SENT(Single Edge Notched Tension) specimen fracture test was conducted on the specimen that laminated together 2 ply CFRP with 4 ply GFRP through DIC(Digital Image Correlation) analysis. The SENT specimen thickness and $a_0/W$ ratio is 1.45 mm and 0.2, respectively. The fracture test accomplished with displacement control with 0.1 mm/min at the room temperature. The experimental apparatus used for the fracture test consisted of a 50kN universal dynamic tester and CCD camera connected to a personal computer (PC), which was used to record images of the specimen surface. Following data acquisition, the images and load-displacements were transferred to the PC, on which the DIC software was implement. The experiment and DIC analysis results show that CFRP/GFRP laminated composite exhibits improvement of the strength, compared with that of the existing blade material. This study shows the result that the strength of CFRP rotor blade of wind turbine satisfies through the experimental and DIC method.

• The Journal of Asian Finance, Economics and Business
• /
• v.9 no.7
• /
• pp.153-171
• /
• 2022

To measure economic performance, customer satisfaction indices are constructed. This study proposes an index for banking and telecom, a significant evaluative system for comparing and enhancing customer satisfaction across the industries. The study suggests and examines amendments and improvements to the prior indices and incorporates ignored indicators to propose a punier index for Pakistan. The study is a pioneer in integrating online and offline indices into a single comprehensive model. The study is enriched by the Theory of Reasoned Action and Technological Acceptance Model. A sample of 320 respondents was used. The sample was divided based on gender and marital status. To authenticate the theoretical model, PLS-SEM was applied. We discovered nine latent variables that define customer satisfaction and conclude that a single model can be utilized for e-commerce enterprises as well. The index scores are comparable to the American index for banking and the Turkish index for telecom. Multi-group analysis (MGA) was used to comprehend the differences among the groups. This reveals that customization, design, reliability, and responsiveness induce satisfaction in telecom male and married customers. For the banking industry, the difference exists in complaint handling, customization, corporate image, perceived price, reliability, responsiveness, sentiments, convenience, and security to satisfaction links, image and complaint handling to loyalty links.

• Journal of Microbiology and Biotechnology
• /
• v.32 no.8
• /
• pp.1026-1033
• /
• 2022

This study presents a novel DNA part characterization technique that increases throughput by combinatorial DNA part assembly, solid plate-based quantitative fluorescence assay for phenotyping, and barcode tagging-based long-read sequencing for genotyping. We confirmed that the fluorescence intensities of colonies on plates were comparable to fluorescence at the single-cell level from a high-end, flow-cytometry device and developed a high-throughput image analysis pipeline. The barcode tagging-based long-read sequencing technique enabled rapid identification of all DNA parts and their combinations with a single sequencing experiment. Using our techniques, forty-four DNA parts (21 promoters and 23 RBSs) were successfully characterized in 72 h without any automated equipment. We anticipate that this high-throughput and easy-to-use part characterization technique will contribute to increasing part diversity and be useful for building genetic circuits and metabolic pathways in synthetic biology.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.21 no.6
• /
• pp.1438-1446
• /
• 1996

Infrared seekers using reticles with a single detector have been widely used due to small size and low cost. However, the analysis of the error signals and the performance in multiple targets are performed either simplistically or not at all. In this paper, we present detector signals and processing results using image and signal processing techniques, especially performance analysis in multiple targets. The simulation results are essential to make the advanced signal processing part of retical seekers which can deal with various engagement scenarios.

• Journal of the Korean Society for Heat Treatment
• /
• v.37 no.2
• /
• pp.73-78
• /
• 2024

This study presents a real-time method that uses Laser Absorption Spectroscopy (LAS) to measure exhaust gas temperatures in turbulent flow fields. It was possible to measure temperature by passing a laser beam through the exhaust gas in a grid pattern, and obtain a temperature distribution image through time series analysis at 0.1 second intervals. Temperature image resolution has been improved with CT reconstruction algorithms. Estimating maximum temperature values and locations enabled 2D temperature analysis, surpassing single-point methods like thermocouples. The accuracy of LAS measurements was evaluated by comparison with thermocouple measurements. This approach will contribute to automotive technology and environmental protection by providing reliable temperature data for interpreting turbulent temperature distributions.

• Journal of the Korean Society of Clothing and Textiles
• /
• v.22 no.8
• /
• pp.1052-1059
• /
• 1998

The purposes of the study were to analyse the colors and, color combinations effect on the image perception using gestalt theory. The research method was a quasi-experimental with a between subjects design. The experimental materials developed for the study were a set of stimuli and a response scale. The stimuli was consisted of 17 drawings of females wearing Korean traditional dress, by using CAD simulation. A response scale consisted of semantic differential scales. The subjects were 1138 undergraduate students of Taejon city, Chungnam province and Chungbuk province. Their responses to the semantic differential scales were analyzed using factor analysis, ANOVA, Duncans multiple range test. Results were as follows; 1) The colors effect of blouse was significantly greater than the effect of skirt, and no interaction effect was found between blouse colors and skirt colors. 2) In bi-color combination dress set, the combined image of the two colors were compared to the image of the two mono color sets: No single principle was found, however, salient color (such as yellow) and unattractive color (such as green) seemed to act as central trait colors on the image perception. On conclusion the visual image of Korean traditional dress wearer was affected by central trait colors in bi-color combination, and this results support the gestalt theory with central traits.

• Progress in Medical Physics
• /
• v.28 no.3
• /
• pp.77-82
• /
• 2017

We proposed the objective ROC analysis method based on the setting of threshold value for evaluation of single photon emission computed tomography (SPECT) image. This proposed ROC analysis method uses the quantification computational threshold value to each signal on the SPECT image. The SPECT images for this study were acquired by using Monte Carlo n-particle extended simulation code (MCNPX, Ver. 2.6.0, Los Alamos National Laboratory, USA). The basic SPECT detectors and specific water phantom were realized in the simulation, and we could get the simulation results by the simulation operation. We tried to analyze the reconstructed images using threshold value application based objective ROC method. We can get the accuracy information of reconstructed region in the image. This proposed ROC technique can be helpful when we have to evaluate the weak signal for the NM image. In this study, the proposed threshold value based computational ROC analysis method can provide better objectivity than the conventional ROC analysis method.