• 제목/요약/키워드: Public image

검색결과 1,278건 처리시간 0.027초

딥 컨볼루셔널 인코더-디코더 네트워크를 이용한 망막 OCT 영상의 층 분할 (Layer Segmentation of Retinal OCT Images using Deep Convolutional Encoder-Decoder Network)

  • 권오흠;송민규;송하주;권기룡
    • 한국멀티미디어학회논문지
    • /
    • 제22권11호
    • /
    • pp.1269-1279
    • /
    • 2019
  • In medical image analysis, segmentation is considered as a vital process since it partitions an image into coherent parts and extracts interesting objects from the image. In this paper, we consider automatic segmentations of OCT retinal images to find six layer boundaries using convolutional neural networks. Segmenting retinal images by layer boundaries is very important in diagnosing and predicting progress of eye diseases including diabetic retinopathy, glaucoma, and AMD (age-related macular degeneration). We applied well-known CNN architecture for general image segmentation, called Segnet, U-net, and CNN-S into this problem. We also proposed a shortest path-based algorithm for finding the layer boundaries from the outputs of Segnet and U-net. We analysed their performance on public OCT image data set. The experimental results show that the Segnet combined with the proposed shortest path-based boundary finding algorithm outperforms other two networks.

간호사의 이미지와 호감도 분석 (Analysis of the Image and Likability of the Nurse)

  • 염영희;김경희;손희숙;전재희;이정민;김명애
    • 임상간호연구
    • /
    • 제21권2호
    • /
    • pp.169-179
    • /
    • 2015
  • Purpose: The purpose of this study was to investigate nurse images and likability that were perceived by various groups in the general population. Methods: Using cross-sectional descriptive design, six groups of people were invited to participate in the survey. The participants included nurses, physicians, nurse aids/technicians, patients/caregivers, college students, and the general public. A total of 1,530 individuals were drawn from 42 hospitals nationwide. Bhargava's likability questionnaires and the Ward Nurse Image tool were used. Results: Compared with other groups, patients and caregivers had higher scores for likability and better nurse image than other groups. Most respondents perceived nurses are clean and caring, but many individuals still had the image that nurses are submissive. Conclusion: To improve nurse image, perceptions from various groups of people need to be considered and programs develop to show the positive aspects of nursing and nurses.

대학 이미지 제고를 위한 유니폼 디자인 (The Uniform Design for Improving the University Image)

  • 유영선
    • 복식문화연구
    • /
    • 제14권2호
    • /
    • pp.206-219
    • /
    • 2006
  • The purpose of this study was to design the ideal student uniform for improving the university image which is related to ideal PR (Public Relations). The results of this study were as follows: Firstly, as for the matter of UIP(University Identity Program), the uniform must transfer the university image. Using the UIP symbol color, the uniform is harmonious with university environment, and should be properly expressed visual image of the university. Secondly, the symbol which expressed the tradition and the spirit of the university was the very important factor to transfer its unique university identity and image of the university in the uniform design. The symbol which comes from the character or textile prints of the university symbolic flower or animals should transfer the consistent and unique design of university identity. Thirdly, the uniform has to be designed considering of the fashion trend as well as the essential factors for the uniform, considering such as functional, beautiful, symbolic aspects. In designing the uniform, fashion trend should be considered to combine the students and the uniform users to be one. As mentioned above, the uniform design which is suggested on this study should be helpful for the improvement of the university status and the reinforcement of the university PR.

  • PDF

감성차원을 통한 디지털 이미지 크리에이팅 (A Study on the Digital Image Creating through Emotional Dimension)

  • 박상진
    • 한국콘텐츠학회:학술대회논문집
    • /
    • 한국콘텐츠학회 2005년도 추계 종합학술대회 논문집
    • /
    • pp.475-479
    • /
    • 2005
  • 디지털 방식이 가져온 변화는 기존사회 가치체계 자체의 변화를 추구하며 남과는 다르게 차별화 시키고자하는 사고방식이 그전보다 훨씬 강해지고 있다. 따라서 변화된 환경에 맞는 다양하고 독창적인 이미지 연출이 필요하며, 이미지 제작을 위한 표현 방법이 필요하다. 본 논고는 디지털 이미지 크리에이팅에 관한 것으로 먼저 개발 대상을 선정하고, 감성차원을 통해 개발대상에서 연상되는 감성어휘를 추출한다. 이 후 대상간의 연계성을 시네틱스의 상징적 유추를 통해 시각화시키는 프로세스로 진행된다. 궁극적인 연구 목적은 단순한 이미지의 왜곡이나 변형이 아니라 본질적인 의미가 담긴 디지털 이미지 제작의 방법 모색과 프로세스 접근에 대한 태도의 전환을 통해 독창적이고 다양한 디지털 이미지 연출에 도움이 되고자 함이다.

  • PDF

자연스러운 저조도 영상 개선을 위한 비지도 학습 (Unsupervised Learning with Natural Low-light Image Enhancement)

  • 이헌상;손광훈;민동보
    • 한국멀티미디어학회논문지
    • /
    • 제23권2호
    • /
    • pp.135-145
    • /
    • 2020
  • Recently, deep-learning based methods for low-light image enhancement accomplish great success through supervised learning. However, they still suffer from the lack of sufficient training data due to difficulty of obtaining a large amount of low-/normal-light image pairs in real environments. In this paper, we propose an unsupervised learning approach for single low-light image enhancement using the bright channel prior (BCP), which gives the constraint that the brightest pixel in a small patch is likely to be close to 1. With this prior, pseudo ground-truth is first generated to establish an unsupervised loss function. The proposed enhancement network is then trained using the proposed unsupervised loss function. To the best of our knowledge, this is the first attempt that performs a low-light image enhancement through unsupervised learning. In addition, we introduce a self-attention map for preserving image details and naturalness in the enhanced result. We validate the proposed method on various public datasets, demonstrating that our method achieves competitive performance over state-of-the-arts.

무효 블록의 격리를 이용한 새로운 이미지 인증 방법 (A New Image Authentication Method through Isolation of Invalid Blocks)

  • 김효철;김현철;유기영
    • 한국정보과학회논문지:컴퓨팅의 실제 및 레터
    • /
    • 제8권1호
    • /
    • pp.17-24
    • /
    • 2002
  • 본 논문에서는 이미지 인증을 목적으로 무효한 블록들을 격리하는 새로운 워터마킹 방법을 제안한다. 이 과정에서 워터마크의 비인식성과 깨지기 쉬운 워터마크를 보장하기 위하여 DCT 도메인의 고주파 영역을 사용하였다. 여러 가지 실험을 통하여 에러가 보정된 원본 영상들과 워터마크된 이미지들 사이에 유효한 블록들이 동일함을 확인하였다. 결과적으로 워터마크 추출 과정에서 원본 이미지나 워터마크와 같은 여분의 정보가 필요 없으며, 워터마크된 이미지만으로 2진 워터마크를 추출할 수 있다는 사실을 발견하였다. 실험 결과들은 제안된 방법이 이미지 인증을 위하여 성공적으로 사용될 수 있음을 보여준다.

Global Busan City Brand Image Development Strategy - SWOT/AHP analysis -

  • LEE, Changhwan;RA, Heeryang;OH, Youngsam;LEE, Chunsu
    • 동아시아경상학회지
    • /
    • 제9권3호
    • /
    • pp.115-124
    • /
    • 2021
  • Purpose - An empirical analysis of various opinions of experts to build Busan's global city image. Based on this, we provide strategy establishment metrics using opportunities, strengths, and threats to build Busan's global city image. Research design, data and methodology - SWOT-AHP analysis are used in terms of methodology, and this study is based on experts' reviews and answers. In addition, AHP analysis is performed based on SWOT analysis to derive the result values for important priority factors. Result - As a result of the prioritization of SWOT-AHP results, a matrix of strategic development directions for Busan city brand building can be presented. As a result of the composite weighting, the factors related to opportunity were ranked as important. In addition, matrices on SO strategy, ST strategy, WO strategy, and WT strategy were derived. Conclusion - This study is an interdisciplinary study from the economic aspect, international management and international marketing aspect, administrative aspect, and architectural engineering aspect. Through this, the image of a global city of Busan that can overcome COVID-19 and cope with the 4th industry in the future will be built, and Busan will be able to build a global international city image by commercially attracting the 2030 World Expo.

Impacts of label quality on performance of steel fatigue crack recognition using deep learning-based image segmentation

  • Hsu, Shun-Hsiang;Chang, Ting-Wei;Chang, Chia-Ming
    • Smart Structures and Systems
    • /
    • 제29권1호
    • /
    • pp.207-220
    • /
    • 2022
  • Structural health monitoring (SHM) plays a vital role in the maintenance and operation of constructions. In recent years, autonomous inspection has received considerable attention because conventional monitoring methods are inefficient and expensive to some extent. To develop autonomous inspection, a potential approach of crack identification is needed to locate defects. Therefore, this study exploits two deep learning-based segmentation models, DeepLabv3+ and Mask R-CNN, for crack segmentation because these two segmentation models can outperform other similar models on public datasets. Additionally, impacts of label quality on model performance are explored to obtain an empirical guideline on the preparation of image datasets. The influence of image cropping and label refining are also investigated, and different strategies are applied to the dataset, resulting in six alternated datasets. By conducting experiments with these datasets, the highest mean Intersection-over-Union (mIoU), 75%, is achieved by Mask R-CNN. The rise in the percentage of annotations by image cropping improves model performance while the label refining has opposite effects on the two models. As the label refining results in fewer error annotations of cracks, this modification enhances the performance of DeepLabv3+. Instead, the performance of Mask R-CNN decreases because fragmented annotations may mistake an instance as multiple instances. To sum up, both DeepLabv3+ and Mask R-CNN are capable of crack identification, and an empirical guideline on the data preparation is presented to strengthen identification successfulness via image cropping and label refining.

보건계열학생이 인지하는 치과기공사의 이미지 조사연구 (Research on dental laboratory technician's image perceived by health allied college students)

  • 김석환;김재홍
    • 대한치과기공학회지
    • /
    • 제35권3호
    • /
    • pp.221-229
    • /
    • 2013
  • Purpose: The purpose of this study was to investigate the image and the awareness of dental laboratory technicians in health allied college students. Methods: The subject of this research are 431 health-related major students who are selected by convenience sampling from Seoul, Gyeonggi-do, Chungcheong-do, Jeolla-do and Gyeongsang-do. After a survey was conducted, the answer sheets from 401 respondents were analyzed except for 30 incomplete ones. The collected data is statistically analyzed by SPSS(Statistical Packages for Social Science 12.0. SPSS Inc., Chicago, IL, USA). Results: The findings of the study were as follows: As a result of general awareness about dental laboratory technicians, the health allied college students knew 83.0% about dental laboratory technician as a job. Respondents showed high recognition about dental laboratory technician as a job($3.62{\pm}0.31$), which showed that the health allied college students took a favorable view of dental laboratory in general. There were significant difference in dental laboratory technician image with age, gender(P<.05). Conclusion: It is required to develop programs such as proactive public relations or campaign via mass media that could enhance the public recognition about dental laboratory technician up to one of professional as required. It is also necessary that dental laboratory technicians make steady efforts for self-development to enhance their own job philosophy and skills in the level of quality, while they need various educations for building up their own favorable personality and positive ideas.

Policy Direction for Promoting the Satellite Data Use in Public Sector

  • Kim, Young-Pyo;Sakong, Hosang;Park, Sung-Mi
    • 대한원격탐사학회:학술대회논문집
    • /
    • 대한원격탐사학회 1999년도 Proceedings of International Symposium on Remote Sensing
    • /
    • pp.355-362
    • /
    • 1999
  • With the ready access to the high resolution satellite image data, users of and areas covered by satellite image data are constantly on the rise world-wide. Korea will also be able to take full advantage of the satellite data once the KOMPSAT is successfully launched. Harmonizing satellite data production and application technology and users' needs, along with the guiding policy is essential for promoting satellite data use. Up to now, the Korean government has mainly concentrated on developing production technology for the satellite units. However, the imminent task of independent satellite data production demands a promotion policy for satellite data use. In this context, the policy is defined as an important medium for identifying the role and status of satellite image information at the national level and also Preparing the legal as well as systematic foundation for producing, building, distributing, and packaging satellite data. For example, in the countries with the advanced satellite technology, such as the United States, the United Kingdom, and Australia, digital ortho image and digital elevation model (DEM) are mandatorily included in the National Geographic Framework Data through policy measures. In addition, in order for the efficient provision of the satellite data, separate organization or agency is being in operation for the exclusive production and distribution of the satellite data. The present paper aims to examine the role and status of the satellite data as well as their current status and problems in Korea in reference to the National Spatial Data Infrastructure, and finally to provide the policy directions to promote the satellite data use in public sector on the basis of the preceding analyses.

  • PDF