• Journal of Broadcast Engineering
• /
• v.24 no.1
• /
• pp.67-76
• /
• 2019

In this paper, we propose an efficient object classification method based on semantic segmentation for multi-labeled image data. In addition to various pixel unit information and processing techniques such as color information, contour, contrast, and saturation included in image data, a detailed region in which each object is located is extracted as a meaningful unit and the experiment is conducted to reflect the result in the inference. We use a neural network that has been proven to perform well in image classification to understand which object is located where image data containing various class objects are located. Based on these researches, we aim to provide artificial intelligence services that can classify real-time detailed areas of complex images containing various objects in the future.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2019.05a
• /
• pp.436-438
• /
• 2019

Air hockey robots are machine vision systems that allow users to play hockey balls through the camera. The position detection of the hockey ball is realized by using the color information of the ball using OpenCV library. It senses the position of the hockey ball, predicts its trajectory, and sends the result to the ARM Cortex-M board. The ARM Cortex-M board controls a 2- Axis Cartesian Coordinate Robot to run an air hockey game. Depending on the strategy of the air hockey robot, it can operate in defensive, offensive, defensive and offensive mode. In this paper, we describe a vision system development and trajectory prediction system and propose a new method to control a biaxial orthogonal robot in an air hockey game.

• Journal of Platform Technology
• /
• v.9 no.3
• /
• pp.63-69
• /
• 2021

Limited materials to make coins for countries and designs suitable for hand-carry make the shape, size, and color of coins similar. This similarity makes that it is difficult for visitors to identify each country's coins. To solve this problem, we propose the coin classification method using CNN effective to image processing. In our coin identification method, we collect the training data by using web crawling and use OpenCV for preprocessing. After preprocessing, we extract features from an image by using three CNN layers and classify coins by using two fully connected network layers. To show that our model designed in this paper is effective for coin classification, we evaluate our model using eight different coin types. From our experimental results, the accuracy for coin classification is about 99.5%.

• Journal of Digital Convergence
• /
• v.19 no.1
• /
• pp.343-348
• /
• 2021

This study investigated the method of constructing and combining blocks based on the atomic design system in order to propose a framework for rescue of a reusable design system. For that, I first looked at the necessity of a design system and examples of snow white, skeuomorphic design, flat design, and material design. In addition, molecules, atoms, organisms, templates and pages of atomic design using the principles of chemistry as metaphors were defined through literature studies. In order to implement a new framework, an interface inventory was constructed, and among them, font, color, image and control elements were extracted as core visual elements, and guidelines were defined, and molecular elements were classified and composed of atoms based on them. Blocks are constructed in the form of blocks based on the design pattern most used in the content inventory, and the framework is constructed to implement a layout based on a visual grid and design a page through a combination of blocks. The significance of this paper is that the new framework helps team consistency and collaboration by reusing blocks and supports file sharing and updating.

• Journal of the Architectural Institute of Korea Planning & Design
• /
• v.36 no.5
• /
• pp.83-91
• /
• 2020

Environmental conditions are known to impact human health and behavior, emotions such as pleasure, anxiety, and depression, and reduce stress. Interior design that elevates emotional comfort and satisfaction can help improve mental health and well-being. This study is a systematic review that analyzed previous empirical studies that explored the effect of interior design elements on the user's emotional response which is quantitatively evaluated by bio-signal and qualitatively evaluated through self-reported questionnaire surveys. This paper aims to derive the attributes of interior design and biometric indicators that affect the user's positive emotion through the synthesis of previous studies and to confirm the feasibility of measuring bio-signals as an objective evaluation tool for architectural design and as a quantitative research method. As a result of the review, the biometric data from EEG, fMRI, ECG, EMG, GSR, and eye-tracking were used to measure the participants' emotional responses, which were manifested as positive or negative depending on certain attributes of interior design such as the form, color, lighting, material and furniture. The attributes of interior design related to the positive emotional response were the curved shape, high ceiling, openness of space, and subdued tone colors. Standard lighting conditions and wooden spaces were related to stress reduction in terms of comfort and relaxation. The free arrangement of furniture was related to the user's positive emotions. On the other hand, consistent experimental protocols could not be found, and although the sample sizes of the studies were small, the studies have demonstrated the feasibility of the emotional response measurement by using the biometric data. Therefore this method can be a useful objective tool in the measurement of human-centric data in architectural design, and to develop the evidence-based design to induce positive emotions and minimize stress.

• 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.

• Journal of the Korea Convergence Society
• /
• v.12 no.1
• /
• pp.29-35
• /
• 2021

License plate recognition plays a key role in intelligent transportation systems. Therefore, it is a very important process to efficiently detect the number and character areas. In this paper, we propose a method to effectively detect license plate number area by applying deep learning and semantic image segmentation algorithm. The proposed method is an algorithm that detects number and text areas directly from the license plate without preprocessing such as pixel projection. The license plate image was acquired from a fixed camera installed on the road, and was used in various real situations taking into account both weather and lighting changes. The input images was normalized to reduce the color change, and the deep learning neural networks used in the experiment were Vgg16, Vgg19, ResNet18, and ResNet50. To examine the performance of the proposed method, we experimented with 500 license plate images. 300 sheets were used for learning and 200 sheets were used for testing. As a result of computer simulation, it was the best when using ResNet50, and 95.77% accuracy was obtained.

• Parasites, Hosts and Diseases
• /
• v.59 no.1
• /
• pp.15-22
• /
• 2021

Artemisinin resistance (ART) has been confirmed in Greater Mekong Sub-region countries. Currently, C580Y mutation on Pfkelch13 gene is known as the molecular marker for the detection of ART. Rapid and accurate detection of ART in field study is essential to guide malaria containment and elimination interventions. A simple method for collection of malaria-infected blood is to spot the blood on filter paper and is fast and easy for transportation and storage in the field study. This study aims to evaluate LAMP-SNP assay for C580Y mutation detection by introducing an extra mismatched nucleotide at the 3' end of the FIP primer. The LAMP-SNP assay was performed in a water bath held at a temperature of 56℃ for 45 min. LAMP-SNP products were interpreted by both gel-electrophoresis and HNB-visualized changes in color. The method was then tested with 120 P. falciparum DNA from dried blood spot samples. In comparing the LAMP-SNP assay results with those from DNA sequencing of the clinical samples, the 2 results fully agreed to detect C580Y. The sensitivity and specificity of the LAMP-SNP assay showed 100%. There were no cross-reactions with other Plasmodium species and other Pfkelch13 mutations. The LAMP-SNP assay performed in this study was rapid, reliable, and useful in detecting artemisinin resistance in the field study.

• Korean Journal of Remote Sensing
• /
• v.37 no.4
• /
• pp.777-788
• /
• 2021

Since aerosol has a relatively short duration and significant spatial variation, satellite observations become more important for the spatially and temporally continuous quantification of aerosol. However, optical remote sensing has the disadvantage that it cannot detect AOD (Aerosol Optical Depth) for the regions covered by clouds or the regions with extremely high concentrations. Such missing values can increase the data uncertainty in the analyses of the Earth's environment. This paper presents a spatial gap-filling framework using a univariate statistical method such as DCT-PLS (Discrete Cosine Transform-based Penalized Least Square Regression) and FMM (Fast Matching Method) inpainting. We conducted a feasibility test for the hourly AOD product from AHI (Advanced Himawari Imager) between January 1 and December 31, 2019, and compared the accuracy statistics of the two spatial gap-filling methods. When the null-pixel area is not very large (null-pixel ratio < 0.6), the validation statistics of DCT-PLS and FMM techniques showed high accuracy of CC=0.988 (MAE=0.020) and CC=0.980 (MAE=0.028), respectively. Together with the AI-based gap-filling method using extra explanatory variables, the DCT-PLS and FMM techniques can be tested for the low-resolution images from the AMI (Advanced Meteorological Imager) of GK2A (Geostationary Korea Multi-purpose Satellite 2A), GEMS (Geostationary Environment Monitoring Spectrometer) and GOCI2 (Geostationary Ocean Color Imager) of GK2B (Geostationary Korea Multi-purpose Satellite 2B) and the high-resolution images from the CAS500 (Compact Advanced Satellite) series soon.

• Science of Emotion and Sensibility
• /
• v.25 no.1
• /
• pp.55-66
• /
• 2022

Many studies have shown that musical dissonance generally evokes negative affect, but few studies detail how distinct dissonant intervals, ranging in various roughness, influence emotions and cognition. This research entailed two experiments to confirm whether varying musical intervals of dissonance trigger particular negative emotions and increase cognitive interference. Experiment 1 assumed that different dissonant intervals would elicit distinct negative emotions. In a survey involving 131 participants, there was an overwhelming consensus that dissonant intervals elicited stronger high arousal negative affect than low arousal negative affect. The major 7th degree was found to evoke a significantly stronger feeling of scared. Experiment 2 investigated whether emotions-affecting dissonance would have an enhancing effect on cognitive interference. According to a color-word Stroop task conducted on 81 participants, the presence of any dissonant sound caused significantly higher reaction times and error rates than in the absence of sound. In particular, the minor 2nd degree was cognitively the most disruptive and associated with the slowest reaction times. This paper shows how different ranges of dissonance can effectively influence negative affect and heighten cognitive interference.