• 제목/요약/키워드: Color paper

검색결과 4,552건 처리시간 0.036초

송아지 질병 결정 지원 모델 (A Calf Disease Decision Support Model)

  • 최동운;강윤정
    • 한국정보통신학회논문지
    • /
    • 제26권10호
    • /
    • pp.1462-1468
    • /
    • 2022
  • 송아지 질병 진단을 위해 사용되는 여러 데이터 중에서 분변은 질병 진단의 중요한 역할을 한다. 송아지 분변 이미지에서 형태, 색상, 질감으로 건강 상태를 알 수 있다. 건강 상태를 파악할 수 있는 분변 이미지는 분변 상태에 따라 정상 송아지 207개와 설사증 송아지 158개의 데이터를 전처리하여 사용하였다. 본 논문에서는 수집된 송아지 데이터 중에서 분변 변수의 이미지를 탐지하고 합성곱 네트워크 기술을 활용하여 질병 증상을 포함하고 있는 데이터 세트에 대해 CNN과 GLCM의 속성을 결합한 GLCM-CNN을 적용하여 이미지를 학습시켰다. CNN의 89.9% 정확도와 GLCM-CNN는 91.7%의 정확도를 보이는 GLCM-CNN는 1.8%의 높은 정확도를 나타내는 유의미한 차이가 있었다.

메타버스를 위한 가상 휴먼의 3차원 의상 모델링 (3D Clothes Modeling of Virtual Human for Metaverse)

  • 김현우;김동언;김유진;박인규
    • 방송공학회논문지
    • /
    • 제27권5호
    • /
    • pp.638-653
    • /
    • 2022
  • 본 논문은 고화질 2차원 전신 영상을 입력으로 받아 영상 속 인물이 입고 있는 의상 패턴과 체형 정보를 추정한 후, 이를 반영한 3차원 가상 휴먼의 생성 기법을 제안한다. 의상의 패턴을 얻기 위해서 Cascade Mask R-CNN을 이용하여 의상 분할을 진행한다. 이후 Pix2Pix로 경계를 블러 및 배경색을 추정하고, UV-Map 기반으로 변환하여 3차원 의상 메쉬의 UV-Map을 얻을 수 있다. 또한, SMPL-X를 이용하여 체형 정보를 얻고 이를 기반으로 의상과 신체의 기본 메쉬를 변형한다. 앞서 얻은 의상 UV-Map, 체형이 반영된 의상과 신체의 메쉬를 이용해 최근 각광받고 있는 게임 엔진인 언리얼 엔진에서 렌더링하여 최종적으로 사용자가 그의 외형이 반영된 3차원 가상 휴먼의 애니메이션을 볼 수 있도록 한다.

미소 픽셀을 갖는 비행 객체 인식을 위한 데이터베이스 구축 및 관리시스템 연구 (Database Generation and Management System for Small-pixelized Airborne Target Recognition)

  • 이호섭;신희민;심현철;조성욱
    • 항공우주시스템공학회지
    • /
    • 제16권5호
    • /
    • pp.70-77
    • /
    • 2022
  • 본 논문에서, 데이터베이스 생성 및 관리 시스템은 미소 픽셀 공중 표적 인식을 위해 제안된다. 제안된 시스템은 1)비행 테스트 비디오 프레임에 의한 직접 이미지 추출, 2) 자동 이미지 보관, 3) 이미지 데이터 레이블링 및 메타 데이터 주석, 4) 컬러 채널 변환, 5) HOG/LBP 기반 소화소 대상 증강 이미지 데이터 생성의 다섯가지 주요 기능으로 구성된다. 제안하는 프로그램은 파이썬 기반의 PyQt5와 OpenCV를 이용하여 구성하였고 공중 표적 인식을 위한 이미지 데이터셋은 제안한 시스템을 이용해 생성했으며 비행 실험으로 부터 수집된 영상을 입력영상으로 사용하였다.

이미지의 Symbolic Representation 기반 적대적 예제 탐지 방법 (Adversarial Example Detection Based on Symbolic Representation of Image)

  • 박소희;김승주;윤하연;최대선
    • 정보보호학회논문지
    • /
    • 제32권5호
    • /
    • pp.975-986
    • /
    • 2022
  • 딥러닝은 이미지 처리에 있어 우수한 성능을 보여주며 큰 주목을 받고 있지만, 입력 데이터에 대한 변조를 통해 모델이 오분류하게 만드는 적대적 공격에 매우 취약하다. 적대적 공격을 통해 생성된 적대적 예제는 사람이 식별하기 어려울 정도로 최소한으로 변조가 되며 이미지의 전체적인 시각적 특징은 변하지 않는다. 딥러닝 모델과 달리 사람은 이미지의 여러 특징을 기반으로 판단하기 때문에 적대적 예제에 속지 않는다. 본 논문은 이러한 점에 착안하여 이미지의 색상, 모양과 같은 시각적이고 상징적인 특징인 Symbolic Representation을 활용한 적대적 예제 탐지 방법을 제안한다. 입력 이미지에 대한 분류결과에 대응하는 Symbolic Representation과 입력 이미지로부터 추출한 Symbolic Representation을 비교하여 적대적 예제를 탐지한다. 다양한 방법으로 생성한 적대적 예제를 대상으로 탐지성능을 측정한 결과, 공격 목표 및 방법에 따라 상이하지만 specific target attack에 대하여 최대 99.02%의 탐지율을 보였다.

에콜로지의 조형적 특징을 활용한 패션디자인 연구 (Research on Fashion Design Using the Formative Features of Ecology)

  • 박한힘
    • 패션비즈니스
    • /
    • 제26권2호
    • /
    • pp.15-27
    • /
    • 2022
  • The purpose of this study is to perform research of ecology concepts expressed in fashion and to propose a new ecology fashion design based on the results. As a specific research method, first, to determine the concept of ecology, the contents related to ecology were extracted and organized through literature research, and then a fashion collection research was conducted to acquire basic design data, such as silhouettes, materials, details, and colors. From WGSN, and a total of 57 images were selected and used as basic data for the design suggestions. As a result of collecting the collection images, it was found that cotton or denim fabrics were mainly used, and in particular, the frequency of use was high mainly for bright tones. The use of chambray, lace, and wrinkles, was also frequent, and the use of expression techniques using burn-out, bleach, and bleaching effects or parts, or entire dyeing was often noticeable. The colors showed neutral and pastel-toned characteristics, and the silhouette was mainly composed of long silhouettes centered on maxi, such as a top or calf based on the knee, rather than a mini. Fabrics for the final designs were linen and sappan wood, and they were used for the dye and red was used as the overall color. The silhouettes were simplified, and care was taken to prevent unnecessary waste, such as paper or materials, from being generated during the production stage. We tried to achieve the purpose of eco-logy by refraining from excessive trimming, except for essential subsidiary materials, such as zippers.

나노 이산화티탄 광촉매 코팅을 적용한 모르타르의 자기정화성능 평가 (Evaluation of Self-Cleaning Performance of Mortar Using Nano-Titanium Dioxide Photocatalytic Coating)

  • 양인환;전효진;이승진
    • 한국건설순환자원학회논문집
    • /
    • 제10권1호
    • /
    • pp.56-65
    • /
    • 2022
  • 본 연구에서는 시설물의 자기정화성능을 확보하기 위하여 이산화티탄 광촉매 용액을 코팅한 모르타르의 자기정화성능을 분석하였다. 광촉매 코팅 용액의 농도(1.5 %와 3.0 %), 초친수강화 용액 적용 유무 및 프라이머 용액의 사용 유무를 실험변수로 고려하였다. 광촉매 농도가 증가할수록 메틸렌블루 수용액의 색상 변화율이 증가하였으며, 이는 광촉매 농도가 증가할수록 자기정화성능이 증가하는 것을 나타낸다. 초친수성 광촉매 용액의 적용은 일반 광촉매 용액에 비해 자기정화성능을 다소 감소시킬 가능성이 있음을 나타낸다. 또한, 프라이머를 사용한 모르타르의 자기정화성능은 프라이머를 사용하지 않은 모르타르의 자기정화성능과 뚜렷한 차이를 나타내지 않는다. 한편, 낮은 농도(1.5 %)로 코팅된 모르타르에 비해 높은 농도(3.0 %)로 코팅된 모르타르 시편 표면의 코팅 균열이 미세하여 상대적으로 큰 광촉매 반응면적을 확보하고 자기정화성능 증가에 유리한 영향을 미친 것으로 판단된다.

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.

혼잡 환경에서 강인한 딥러닝 기반 인간 추적 프레임워크 (A Robust Deep Learning based Human Tracking Framework in Crowded Environments)

  • 오경석;김성현;김진섭;이승환
    • 로봇학회논문지
    • /
    • 제16권4호
    • /
    • pp.336-344
    • /
    • 2021
  • This paper presents a robust deep learning-based human tracking framework in crowded environments. For practical human tracking applications, a target must be robustly tracked even in undetected or overcrowded situations. The proposed framework consists of two parts: robust deep learning-based human detection and tracking while recognizing the aforementioned situations. In the former part, target candidates are detected using Detectron2, which is one of the powerful deep learning tools, and their weights are computed and assigned. Subsequently, a candidate with the highest weight is extracted and is utilized to track the target human using a Kalman filter. If the bounding boxes of the extracted candidate and another candidate are overlapped, it is regarded as a crowded situation. In this situation, the center information of the extracted candidate is compensated using the state estimated prior to the crowded situation. When candidates are not detected from Detectron2, it means that the target is completely occluded and the next state of the target is estimated using the Kalman prediction step only. In two experiments, people wearing the same color clothes and having a similar height roam around the given place by overlapping one another. The average error of the proposed framework was measured and compared with one of the conventional approaches. In the error result, the proposed framework showed its robustness in the crowded environments.

Lightweight multiple scale-patch dehazing network for real-world hazy image

  • Wang, Juan;Ding, Chang;Wu, Minghu;Liu, Yuanyuan;Chen, Guanhai
    • KSII Transactions on Internet and Information Systems (TIIS)
    • /
    • 제15권12호
    • /
    • pp.4420-4438
    • /
    • 2021
  • Image dehazing is an ill-posed problem which is far from being solved. Traditional image dehazing methods often yield mediocre effects and possess substandard processing speed, while modern deep learning methods perform best only in certain datasets. The haze removal effect when processed by said methods is unsatisfactory, meaning the generalization performance fails to meet the requirements. Concurrently, due to the limited processing speed, most dehazing algorithms cannot be employed in the industry. To alleviate said problems, a lightweight fast dehazing network based on a multiple scale-patch framework (MSP) is proposed in the present paper. Firstly, the multi-scale structure is employed as the backbone network and the multi-patch structure as the supplementary network. Dehazing through a single network causes problems, such as loss of object details and color in some image areas, the multi-patch structure was employed for MSP as an information supplement. In the algorithm image processing module, the image is segmented up and down for processed separately. Secondly, MSP generates a clear dehazing effect and significant robustness when targeting real-world homogeneous and nonhomogeneous hazy maps and different datasets. Compared with existing dehazing methods, MSP demonstrated a fast inference speed and the feasibility of real-time processing. The overall size and model parameters of the entire dehazing model are 20.75M and 6.8M, and the processing time for the single image is 0.026s. Experiments on NTIRE 2018 and NTIRE 2020 demonstrate that MSP can achieve superior performance among the state-of-the-art methods, such as PSNR, SSIM, LPIPS, and individual subjective evaluation.

조선 의원 이원풍(李元豊)의 마진 의서, 『마진휘성(麻疹彙成)』연구 (A Study on the Majinhwiseong (麻疹彙成), a Medical Text on Measles Written by Joseon physician Lee Wonpung)

  • 오재근
    • 대한한의학원전학회지
    • /
    • 제35권3호
    • /
    • pp.41-58
    • /
    • 2022
  • Objectives : In this paper, the outline and overall content of the Majinhwiseong, a specialized medical text on measles written by Lee Wonpung was introduced, along with its academic historical meaning. Methods : The entire Majinhwiseong was analyzed according to content and form. In terms of form, organization, construction, cited literature, etc., were studied, while in terms of content, diagnosis of disease pattern and treatment formulas were studied. Later, based on cited medical texts and the author's social position, the academic historical meaning of this book was discussed. Results : Through the Majinhwiseong, Lee Wonpung strengthened the credibility of the text by not only providing medical knowledge on measles but listing their sources and comparing and analyzing related contents. In the diagnosis part, Lee focused on the changes in symptom, shape, color, and pulse of measles, discussing in detail its differential diagnostic methods. In the treatment part, while listing numerous formulas suggested by Ming (明) masters, Lee did not leave out treatment experiences of Joseon physicians. Meanwhile, the Majinhwiseong is indicative of measles medicine in 18th century Joseon having been progressed in the private sector rather than the official, and how the results of private sector medicine were being absorbed into the official realm through the Uiyakdongcham (議藥同參) system. Conclusions : The Majinhwiseong is a practical treatment manual written by clinician Lee Wonpung to deal measles which was widely spread at the time. The author organized existing medical knowledge on measles for clinicians while reflecting outcomes and medical situation of Joseon physicians in this book. Based on these findings, we could verify that medicine in 18th century Joseon had been progressing actively around the private medical sector.