• Journal of the Korea Computer Graphics Society
• /
• v.29 no.3
• /
• pp.79-84
• /
• 2023

Image generation models have been applied in various fields to overcome data sparsity, time and cost issues. However, it has limitations in generating images from regular pattern images and detecting defects in such data. In this paper, we verified the feasibility of the image generation model to generate pattern images and applied it to data augmentation for defect detection of OLED panels. The data required to train an OLED defect detection model is difficult to obtain due to the high cost of OLED panels. Therefore, even if the data set is obtained, it is necessary to define and classify various defect types. This paper introduces an OLED panel defect data acquisition system that acquires a hypothetical data set and augments the data with an image generation model. In addition, the difficulty of generating pattern images in the diffusion model is identified and a possibility is proposed, and the limitations of data augmentation and defect detection data augmentation using the image generation model are improved.

• Journal of IKEEE
• /
• v.26 no.2
• /
• pp.292-298
• /
• 2022

There is a limit to improving the image quality through global processing of images taken under backlighting because too bright and dark parts are mixed in one scene. This paper introduces a method to improve the quality of a photo by making two virtual images that improve the dark and bright areas of a backlit photo, and fusing them with the original image into a Laplacian pyramid. The proposed method reduces the computational burden by using histogram stretching and gamma transformation that can be simplified with LUT when creating the two virtual images. In addition, in order to obtain a color-enhanced image, contrast conversion was performed only on the luminance using the HSV coordinate system. The proposed technique showed its effectiveness by calculating several NIQA indicators using standard image data sets.

• ETRI Journal
• /
• v.10 no.3
• /
• pp.9-23
• /
• 1988

반도체 기술의 급격한 발전으로 마이크로프로세서를 이용하여 수퍼미니급의 컴퓨터를 개발하는 것이 가능하게 되었다. 따라서 프로세서 칩 개발노력이 증대되었으며 컴퓨터 구조 또는 프로세서 구조에 관한 연구도 여러 곳에서 진행되고 있다. 우리나라의 경우 독자적인 명령어를 갖는 컴퓨터를 개발하겠다는 노력은 미미하였으며 외부로 발표된 것은 전무한 상태이다. 본 논문은 한국전자통신연구소에서 개발하고 있는 독자적인 명령어 세트를 가지는 RISC 형태의 32 비트 마이크로프로세서인 HARP의 구조설계에 관한 것으로서 기본구조 설계를 위하여 1980년대 이후에 개발된 RISC 프로세서들에 대한 사례연구를 하였으며, 이를 바탕으로 HARP의 명령어 및 데이터 형식, 레지스터의 구성, 48비트의 가상 어드레스 사용방법, load/store 및 분기 명령어에서 사용되는 어드레싱 모드 그리고 HARP에서 정의한 39개의 명령어들에 대해 기술한다.

• The Transactions of the Korean Institute of Electrical Engineers B
• /
• v.54 no.4
• /
• pp.181-187
• /
• 2005

This paper describes a load simulator with power-recovery capability, which is based on the voltage source converter-inverter set. The load simulator described in this paper can save the electric energy that should be consumed to test the operation and performance of the distributed generation system and the power quality compensator. The load simulator consists of a converter-inverter set with a DSP controller for system control and PWM pulse generation. The converter operates as a universal load to model the linear load and the non-linear load, while the inverter feed the energy back to the power source with harmonic compensation. The load simulator can be widely used in the lab to test the performance of the distributed generation system and the power quality compensator.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2021.06a
• /
• pp.19-22
• /
• 2021

기존 영상 콘텐츠에 새로운 물체를 삽입하는 등의 영상 재구성 기술은 새로운 게임, 가상현실, 증강현실 콘텐츠를 생성하거나 인공신경망 학습을 위한 데이터 증대를 위해 사용될 수 있다. 하지만, 기존 기술은 컴퓨터 그래픽스, 사람에 의한 수동적인 영상 편집에 의존하고 있어 금전적/시간적 비용이 높다. 이에 본 연구에서는 인공지능 신경망을 활용하여 낮은 비용으로 영상을 재구성하는 기술을 소개하고자 한다. 제안하는 방법은 기존 콘텐츠와 삽입하고자 하는 객체를 포함하는 영상이 주어졌을 때, 객체 세그먼테이션 네트워크를 활용하여 입력 영상에서 객체를 분리하고, 스타일 변환 네트워크를 활용하여 입력 영상을 스타일 변환한 후, 사용자 입력과 두 네트워크의 결과를 활용하여 기존 콘텐츠에 새로운 객체를 삽입하는 것이다. 실험에서는 기존 콘텐츠는 온라인 영상을 활용하였으며 삽입 객체를 포함한 영상은 ImageNet 영상 분류 데이터 세트를 활용하였다. 실험을 통해 제안한 방법을 활용하면 기존 콘텐츠와 잘 어우러지게끔 객체를 삽입할 수 있음을 보인다.

• Journal of the Korean Institute of Gas
• /
• v.25 no.5
• /
• pp.63-69
• /
• 2021

In this study, we established an algorithm to determine whether the work in the gas facility is a normal work or an abnormal work using the threshold of the reconstruction error of the autoencoder. This algorithm do deep learning the autoencoder only with time-series data of a normal work, and derives the optimized threshold of the reconstruction error of the normal work. We applied this algorithm to the time series data of the new work to get the reconstruction error, and then compare it with the reconstruction error threshold of the normal work to determine whether the work is normal work or abnormal work. In order to train and validate this algorithm, we defined the work in a virtual gas facility, and constructed the training data set consisting only of normal work data and the validation data set including both normal work and abnormal work data.

• Journal of Distribution Research
• /
• v.4 no.3
• /
• pp.47-64
• /
• 2000

This study introduces the mother logit model to predict consumer's store choices. The model is not based on the IIA assumptions and thus accounts for substitution among similar alternatives. The choice data as an input to the model is obtained through the conjoint-type choice experiment. The model is applied to consumer's choice of fastfood stores in the context where new store enters the market. The analysis shows that the substitution effects are significant and therefore the mother logit model predicts better than the IIA model. The mother logit model will be useful as well for the market structure analysis in capturing cannibalization among several brands.

• Journal of the Korea Society of Computer and Information
• /
• v.29 no.8
• /
• pp.11-21
• /
• 2024

This study explores the use of virtual reality (VR) technology to identify and label key segments of the golf swing. To address the limitations of existing VR devices, we developed a platform to collect kinematic data from various VR devices using the OpenVR SDK (Software Development Kit) and SteamVR, and developed a semi-automated labeling technique to identify and label temporal changes in kinematic behavior through LSTM (Long Short-Term Memory)-based time series data analysis. The experiment consisted of 80 participants, 20 from each of the following age groups: teenage, young-adult, middle-aged, and elderly, collecting data from five swings each to build a total of 400 kinematic datasets. The proposed technique achieved consistently high accuracy (≥0.94) and F1 Score (≥0.95) across all age groups for the seven main phases of the golf swing. This work aims to lay the groundwork for segmenting exercise data and precisely assessing athletic performance on a segment-by-segment basis, thereby providing personalized feedback to individual users during future education and training.

• The KIPS Transactions:PartD
• /
• v.11D no.4
• /
• pp.823-834
• /
• 2004

In this research, the similarity search algorithms are provided for large video data streams. A video stream that consists of a number of frames can be expressed by a sequence in the multidimensional data space, by representing each frame with a multidimensional vector By analyzing various characteristics of the sequence, it is partitioned into multiple video segments and clusters which are represented by hyper-rectangles. Using the hyper-rectangles of video segments and clusters, similarity functions between two video streams are defined, and two similarity search algorithms are proposed based on the similarity functions algorithms by hyper-rectangles and by representative frames. The former is an algorithm that guarantees the correctness while the latter focuses on the efficiency with a slight sacrifice of the correctness Experiments on different types of video streams and synthetically generated stream data show the strength of our proposed algorithms.

• Journal of Broadcast Engineering
• /
• v.27 no.1
• /
• pp.20-30
• /
• 2022

Recently, as VR (Virtual Reality) technology has been in the spotlight, 360° panoramic images that can view lively VR contents are attracting a lot of attention. Image stitching technology is a major technology for producing 360° panorama images, and many studies are being actively conducted. Typical stitching algorithms are based on feature point-based image stitching. However, conventional feature point-based image stitching methods have a problem that stitching results are intensely affected by feature points. To solve this problem, deep learning-based image stitching technologies have recently been studied, but there are still many problems when there are few overlapping areas between images or large parallax. In addition, there is a limit to complete supervised learning because labeled ground-truth panorama images cannot be obtained in a real environment. Therefore, we produced three fisheye images with different camera centers and corresponding ground truth image through carla simulator that is widely used in the autonomous driving field. We propose image stitching model that creates a 360° panorama image with the produced fisheye image. The final experimental results are virtual datasets configured similar to the actual environment, verifying stitching results that are strong against various environments and large parallax.