• 제목/요약/키워드: Digital techniques

검색결과 2,274건 처리시간 0.034초

Wavelet 기반의 영상 디테일 향상 잡음 제거 네트워크 (WDENet: Wavelet-based Detail Enhanced Image Denoising Network)

  • 정군;위승우;정제창
    • 방송공학회논문지
    • /
    • 제26권6호
    • /
    • pp.725-737
    • /
    • 2021
  • 현재 카메라 성능이 점점 발전해 왔지만 카메라로부터 얻은 디지털 영상에는 잡음 (Noise)이 존재하고 이는 높은 해상도의 영상을 획득하는 데 있어서 방해요소로 작용한다. 전통적으로 잡음을 제거하기 위하여 필터링 방법을 사용해 왔고 최근 딥 러닝 기법의 하나인 합성곱 신경망 (Convolutional Neural Network)은 영상 잡음 제거 분야에서 전통적인 기법보다 좋은 성능을 나타내고 있어 많은 연구가 진행되고 있다. 하지만 합성곱 신경망으로 학습하는 과정에서 영상 내 디테일한 부분이 손실될 수 있는 문제점이 있다. 본 논문에서는 웨이블릿 변환 (Wavelet Transform)을 기반으로 영상 내 디테일 정보도 같이 학습하여 영상 디테일을 향상하는 잡음 제거 합성곱 신경망 네트워크를 제안한다. 제안하는 네트워크는 디테일 향상 서브 네트워크 (Detail Enhancement Subnetwork)와 영상 잡음 추출 서브 네트워크 (Noise Extraction Subnetwork)를 이용하게 된다. 실험은 가우시안 잡음과 실제 카메라 잡음을 통해 진행했고 제안하는 방법은 기존 알고리듬보다 디테일 손실 문제를 효과적으로 해결할 수 있었고 객관적 품질 평가와 주관적 품질 비교에서 모두 우수한 결과가 나온 것을 확인하였다.

Visualization, Economic Complexity Index, and Forecasting of South Korea International Trade Profile: A Time Series Approach

  • Dar, Qaiser Farooq;Dar, Gulbadin Farooq;Ma, Jin-Hee;Ahn, Young-Hyo
    • Journal of Korea Trade
    • /
    • 제24권1호
    • /
    • pp.131-145
    • /
    • 2020
  • Purpose - The recent growth of South Korean products in the international market is the benchmark for both developed as well as developing countries. According to the development index, the role of international trade is indeed crucial for the development of the national economy. However, the visualization of the international trade profile of the country is the prerequisite of governmental policy decision-makers and guidance for forecasting of foreign trade. Design/methodology - We have utilized data visualization techniques in order to visualize the import & export product space and trade partners of South Korea. Economic Complexity Index (ECI) and Revealed Comparative Advantage (RCA) were used to identify the Korean international trade diversification, whereas the time series approach is used to forecast the economy and foreign trade variables. Findings - Our results show that Chine, U.S, Vietnam, Hong Kong, and Japan are the leading trade partners of Korea. Overall, the ECI of South Korea is growing significantly as compared to China, Hong Kong, and other developed countries of the world. The expected values of total import and export volume of South Korea are approximately US$535.21 and US$ 781.23B, with the balance of trade US$ 254.02B in 2025. It was also observed from our analysis that imports & exports are equally substantial to the GDP of Korea and have a significant correlation with GDP, GDP per capita, and ECI. Originality/value - To maintain the growth rate of international trade and efficient competitor for the trade partners, we have visualized the South Korea trade profile, which provides the information of significant export and import products as well as main trade partners and forecasting.

블록체인을 이용한 자율주행 차량의 포렌식 연구 (Forensic study of autonomous vehicle using blockchain)

  • 강장묵
    • 한국인터넷방송통신학회논문지
    • /
    • 제23권1호
    • /
    • pp.209-214
    • /
    • 2023
  • 장래 국내외 자율주행 차량이 보급되면, 자율주행 차량의 사고 역시 발생 빈도가 늘어날 전망이다. 특히, 완전자율주행 자동차가 운행할 경우, 자동차의 사고 자체뿐만 아니라 운행 중 승객 간의 성폭력, 폭행, 사기 등 여러 가지 형사/민사상 문제가 발생할 수 있다. 이 경우, 자율주행차량의 운행 사고와 차량 내 승객의 사고에 대한 포렌식 역시 변화할 전밍이다. 이 글은 자율주행차량의 보안 위협에 대한 유형, 블록체인 기술을 이용한 증거 데이터의 무결성 유지 방안, 디지털 포렌식의 연구를 고찰하였다. 이를 통해 블록체인 기술을 활용한 자율주행 차량에서 발생할 위협과 다양한 사고 유형 별 포렌식 기법 등을 시나리오식으로 기술할 수 있었다. 본 연구를 통해 자율 주행 차량 대상 취약점, 공격에 대응하기 위한 국내외 웹사이트의 포렌식 보안 기술 조사 및 연구기관, 정보보안기업의 블록체인 보안 연구를 조사하여 사고 전/후 자율주행 차량의 포렌식을 돕는 블록체인 기법을 제안하였다.

Research on the Expression Features of Naked-eye 3D Effect of LED Screen Based on Optical Illusion Art

  • Fu, Linwei;Zhou, Jiani;Tae Soo, Yun
    • International Journal of Internet, Broadcasting and Communication
    • /
    • 제15권1호
    • /
    • pp.126-139
    • /
    • 2023
  • At present, naked-eye 3D appears more and more commonly on the facades of urban buildings. It brings an incredible visual experience to the audience by simulating the natural 3D 3D space effect. At the same time, it also creates enormous commercial value for city publicity and commercial advertisements. There is much research on naked-eye 3D visual effects, but for right-angle LED screens. Right-angle LED screen's brand-new expression method that has only become popular in recent years, how to convey a realistic naked-eye 3D effect through two LED screens combined at right angles has become a problem worth exploring. To explore the whole design ideas and production process of the naked-eye 3D impact of the right-angle LED screen, this paper is a preliminary study aimed at understanding the performance principle and expression features. Before the case analysis, first, understand the standard virtual 3D space construction techniques. Combining it with the optical illusion phenomenon, according to the expression principle of the naked-eye 3D effect of the right-angle LED screen, it can be summarized into seven expressions: Shadow, Color contrast, Background structure line, Magnify object, Object out of bounds, Object floating, Fusion of picture and background. By analyzing the optical illusion phenomenon used in the case, we summarized the main performance characteristics of the naked eye 3D effect. The emergence of right-angle LED screens breaks the limitation of a single plane of optical illusion art, perfectly combines building facades with naked-eye 3D visual effects, and provides designers with a brand-new creative platform. Understanding its production principles and main expressive features can help designers enter this innovative platform better.

SMOTE와 Light GBM 기반의 불균형 데이터 개선 기법 (Imbalanced Data Improvement Techniques Based on SMOTE and Light GBM)

  • 한영진;조인휘
    • 정보처리학회논문지:컴퓨터 및 통신 시스템
    • /
    • 제11권12호
    • /
    • pp.445-452
    • /
    • 2022
  • 디지털 세상에서 불균형 데이터에 대한 클래스 분포는 중요한 부분이며 사이버 보안에 큰 의미를 차지한다. 불균형 데이터의 비정상적인 활동을 찾고 문제를 해결해야 한다. 모든 트랜잭션의 패턴을 추적할 수 있는 시스템이 필요하지만, 일반적으로 패턴이 비정상인 불균형 데이터로 기계학습을 하면 소수 계층에 대한 성능은 무시되고 저하되며 예측 모델은 부정확하게 편향될 수 있다. 본 논문에서는 불균형 데이터 세트를 해결하기 위한 접근 방식으로 Synthetic Minority Oversampling Technique(SMOTE)와 Light GBM 알고리즘을 이용하여 추정치를 결합하여 대상 변수를 예측하고 정확도를 향상시켰다. 실험 결과는 Logistic Regression, Decision Tree, KNN, Random Forest, XGBoost 알고리즘과 비교하였다. 정확도, 재현율에서는 성능이 모두 비슷했으나 정밀도에서는 2개의 알고리즘 Random Forest 80.76%, Light GBM 97.16% 성능이 나왔고, F1-score에서는 Random Forest 84.67%, Light GBM 91.96% 성능이 나왔다. 이 실험 결과로 Light GBM은 성능이 5개의 알고리즘과 비교하여 편차없이 비슷하거나 최대 16% 향상됨을 접근 방식으로 확인할 수 있었다.

Development of pre-procedure virtual simulation for challenging interventional procedures: an experimental study with clinical application

  • Seong, Hyunyoung;Yun, Daehun;Yoon, Kyung Seob;Kwak, Ji Soo;Koh, Jae Chul
    • The Korean Journal of Pain
    • /
    • 제35권4호
    • /
    • pp.403-412
    • /
    • 2022
  • Background: Most pain management techniques for challenging procedures are still performed under the guidance of the C-arm fluoroscope although it is sometimes difficult for even experienced clinicians to understand the modified three-dimensional anatomy as a two-dimensional X-ray image. To overcome these difficulties, the development of a virtual simulator may be helpful. Therefore, in this study, the authors developed a virtual simulator and presented its clinical application cases. Methods: We developed a computer program to simulate the actual environment of the procedure. Computed tomography (CT) Digital Imaging and Communications in Medicine (DICOM) data were used for the simulations. Virtual needle placement was simulated at the most appropriate position for a successful block. Using a virtual C-arm, the authors searched for the position of the C-arm at which the needle was visualized as a point. The positional relationships between the anatomy of the patient and the needle were identified. Results: For the simulations, the CT DICOM data of patients who visited the outpatient clinic was used. When the patients revisited the clinic, images similar to the simulated images were obtained by manipulating the C-arm. Transforaminal epidural injection, which was difficult to perform due to severe spinal deformity, and the challenging procedures of the superior hypogastric plexus block and Gasserian ganglion block, were successfully performed with the help of the simulation. Conclusions: We created a pre-procedural virtual simulation and demonstrated its successful application in patients who are expected to undergo challenging procedures.

안보사건에서 스테가노그라피 분석 및 형사법적 대응방안 (Analysis of Steganography and Countermeasures for Criminal Laws in National Security Offenses)

  • 오소정;주지연;박현민;박정환;신상현;장응혁;김기범
    • 정보보호학회논문지
    • /
    • 제32권4호
    • /
    • pp.723-736
    • /
    • 2022
  • 스테가노그라피는 테러, 간첩 등 국가안보를 위협하는 범죄에 비밀통신 수단으로 활용되고 있다. 정보통신기술 발전에 따라 기술도 고도화되고 있고, 범죄자들은 자체적으로 프로그램을 제작하여 사용하고 있다. 하지만 스테가노그파리 관련내용이 공개되지 않아 수사기술 개발과 형사법적 대응에 한계가 있다. 따라서 본 논문에서는 스테가노그라피 수사를 위하여 탐지와 해독과정을 살펴보고 대법원에서 유죄판결 받은 김목사 간첩사건을 중심으로 수법을 분석하였다. 김목사 간첩사건은 사전에 약속된 스테고 키를 활용한 대칭 스테가노그라피를 사용하였고 다중보안장치를 사용한 고도화된 수법을 사용하고 있었다. 형사법적 쟁점은 ① 관련성, ② 참여권, ③ 공개재판 등 3가지 문제에 대하여 검토하였다. 본 연구가 수사기관이 스테가노그라피에 대한 분석기법을 발전시키는데 출발점이 되기를 기대한다.

IPA 분석을 통한 패션 소상공인 디자이너 브랜드를 위한 패션테크 개발 우선순위 도출 (Study on the Priorities of Fashion Technology Development for Small-Scale Fashion Designer Brands using IPA Analysis)

  • 장세윤;이유리;김하연
    • 패션비즈니스
    • /
    • 제26권4호
    • /
    • pp.64-82
    • /
    • 2022
  • This study aimed to explore fashion technologies for small-scale designer brands and reveal the priorities of the derived fashion technologies. Interviews were conducted with owners of 15 designer brands to explore fashion technologies needed in the field based on the business operation stage (study 1), and an online survey of owners of 61 designer brands was conducted to verify their priorities (study 2). A total of 12 fashion technologies were derived from study 1, including 2 market analysis stages, 6 season planning stages, and 4 product operation stages. In study 2, importance and satisfaction were measured with 12 fashion techniques derived from study 1, and importance-performance analysis (IPA) was performed. The technologies of product management with image tagging and sales channel matching were considered to be the fashion technologies that should be developed first. Second, in the case of maintenance, demand prediction and price determination were applicable. Third, over-effort avoidance was revealed through market analysis and design generation. Finally, in automatic product detail page creation and digital marketing, development was the lowest priority. The results of this study are expected to provide insight into priority areas for fashion technology developers and policy departments providing emerging brand support.

High Noise Density Median Filter Method for Denoising Cancer Images Using Image Processing Techniques

  • Priyadharsini.M, Suriya;Sathiaseelan, J.G.R
    • International Journal of Computer Science & Network Security
    • /
    • 제22권11호
    • /
    • pp.308-318
    • /
    • 2022
  • Noise is a serious issue. While sending images via electronic communication, Impulse noise, which is created by unsteady voltage, is one of the most common noises in digital communication. During the acquisition process, pictures were collected. It is possible to obtain accurate diagnosis images by removing these noises without affecting the edges and tiny features. The New Average High Noise Density Median Filter. (HNDMF) was proposed in this paper, and it operates in two steps for each pixel. Filter can decide whether the test pixels is degraded by SPN. In the first stage, a detector identifies corrupted pixels, in the second stage, an algorithm replaced by noise free processed pixel, the New average suggested Filter produced for this window. The paper examines the performance of Gaussian Filter (GF), Adaptive Median Filter (AMF), and PHDNF. In this paper the comparison of known image denoising is discussed and a new decision based weighted median filter used to remove impulse noise. Using Mean Square Error (MSE), Peak Signal to Noise Ratio (PSNR), and Structure Similarity Index Method (SSIM) metrics, the paper examines the performance of Gaussian Filter (GF), Adaptive Median Filter (AMF), and PHDNF. A detailed simulation process is performed to ensure the betterment of the presented model on the Mini-MIAS dataset. The obtained experimental values stated that the HNDMF model has reached to a better performance with the maximum picture quality. images affected by various amounts of pretend salt and paper noise, as well as speckle noise, are calculated and provided as experimental results. According to quality metrics, the HNDMF Method produces a superior result than the existing filter method. Accurately detect and replace salt and pepper noise pixel values with mean and median value in images. The proposed method is to improve the median filter with a significant change.

Variation of Paleotopography around the Ssangsujeong Pavilion Area in Gongsanseong Fortress using GIS and 3D Geospatial Information

  • Lee, Chan Hee;Park, Jun Hyoung
    • 보존과학회지
    • /
    • 제38권4호
    • /
    • pp.347-359
    • /
    • 2022
  • Gongsanseong Fortress was registered of a World Heritage Site in 2015 as a representative cultural heritage from the Woongjin Baekje period, and it has been used throughout the entire period from Baekje Kingdom to the Joseon Dynasty. Within Gongsanseong Fortress, the area around Ssangsujeong is presumed the site of royal palace of the Woongjin Baekje. Also, the excavated culture layers of the Baekje Kingdom, the Unified Silla period, and the Joseon Dynasty were confirmed. In this study, paleotopography was modeled by digitally converting the elevation data obtained through surveying the excavation process, and the use of the topography in the Ssangsujeong area was considered by examining the variations in the topography according to the periods. As a result, the topography of the slope around the peak changed by periods, and the topography did not change on the flat land. The topography between the Baekje Kingdom and the Unified Silla period appeared to be almost identical, and it seems that the space of the Baekje period was maintained as it is. Also, during the Joseon Dynasty, it is confirmed that flat surfaces in the previous period were used. However, sediments on the slopes flowed down, reducing the area of the flatland, and architectural techniques that could utilize the natural topography of the changed slope were applied to interpret it as having a different topography from the previous period. In order to model and interpret the paleotopography, excavation data, geological and topographic analysis, and digital data must be secured. It is expected that location conditions and ancient human life can be identified if the analysis technique in the study is applied to other archaeological sites in the future.