• Annual Conference of KIPS
• /
• 2015.04a
• /
• pp.683-686
• /
• 2015

본 논문에서는 스케일링-불변 윤곽선 이미지 매칭의 시각화 도구를 제안한다. 윤곽선 이미지를 시계열로 나타낼 경우, 시계열 매칭 기술을 활용하여 대용량 윤곽선 이미지 매칭을 보다 빠르게 수행할 수 있다. 이러한 윤곽선 이미지 매칭에서, 스케일링 불변의 지원은 스케일된 유사 이미지를 검색하기 위한 중요한 요소이다. 본 논문에서는 스케일링-불변 윤곽선 이미지 매칭 시스템을 클라이언트-서버 모델을 기반으로 구현한다. 먼저, 클라이언트는 질의 이미지를 시계열로 변환하고, 스케일링 팩터 구간 및 허용치와 함께 서버에 전달하고, 매칭 결과로 반환된 이미지를 차트 형태로 시각화한다. 다음으로 서버는 다차원 인덱스를 활용하여 대용량 윤곽선 시계열 데이터에 대한 빠른 시계열 매칭을 수행한다. 구현 결과, 제안하는 윤곽선 이미지 매칭 시각화 도구는 질의 이미지와 스케일링-불변 결과 이미지를 세 가지의 차트를 통해 직관적으로 비교 및 분석 가능하게 하였다.

• Journal of the Korean Society for Railway
• /
• v.14 no.4
• /
• pp.320-326
• /
• 2011

This paper proposes a baseline-free SHM technique in which the time-reversal process of Lamb waves and the imaging method are used. The proposed SHM technique has three distinct features when compared with the authors' previously proposed one: (1) It use the reconstructed signal for damage diagnosis, without need to extract the damage signal as the difference between reconstructed signal and initial input signal; (2) It use the imaging method based on the time-offlight information from the reconstructed signal, instead of using a pattern comparison method; (3) In order to make the damage image more clear, the modified mathematical definition of damage image in a pixel is used. The proposed SHM technique is evaluated through the damage detection experiment for an aluminum plate with damage at different locations.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.12 no.12
• /
• pp.2323-2329
• /
• 2008

Advances in wireless communication and hardware technology have made it possible to manufacture high-performance tiny sensor nodes. More recently, the availability of inexpensive cameras modules that are able to capture multimedia data from the environment has fostered the development of Wireless Multimedia Sensor Networks(WMSNs). WMSN supplements the a advanced technique that senses, transmits, and processes the multimedia contents upon the text based traditional wireless sensor network. Since the amount of data which the multimedia contents have, is significantly larger than that of text based data, multimedia contents require lots of computing power and high network bandwidth. To process the multimedia contents on the wireless sensor node which has very limited computing power and energy, a technique for WMSN should take account of computing resource and efficient transmission. In the paper, we propose a new image compression technique YWCE for efficient compression and transmission of image data in WMSN. YWCE introduces 4 type of technique for motion estimation and compensation based on the Resolution Scalability of Wavelet. Experimental result shows that YWCE has high compression performance with different set of 4 type.

• The Journal of the Convergence on Culture Technology
• /
• v.8 no.3
• /
• pp.463-468
• /
• 2022

The prolonged of the Post Corona made many industry's paradigm. It's become very important In the industries products that customers directly touch and use. To cope with this situation, The Cosmetics industry has recently introduced various untact services. many customers would like to try these new services. Typically, online survey services recommend personalized products. but these services reached its limit later. This paper research how to recommend products and define skine type with AI Image diagnosis module combine with legacy survey system.

• Journal of radiological science and technology
• /
• v.35 no.1
• /
• pp.25-33
• /
• 2012

Perception level and social position of radiological technologist influence satisfaction level of their job. This study aims to use foundational data to improve perception level and social position of radiological technologists. We conducted interviews and a fill-out survey with 233 students who have been majoring in health-related fields at five universities and colleges located in Busan and who finished internship programs. The study analyzed 233 answer sheets excluding 17 inadequate answer sheets using T-test, ANOVA and multiple regression analysis with SAS9.1. The mean score of perception level was $3.33{\pm}0.56$. The personal image of radiological technologist showed the best score($3.43{\pm}0.56$) whereas the social image showed the worst($3.12{\pm}0.58$). According to the classification of the subject, the answer, "radiological technologist is specialized job", showed the best score($3.99{\pm}0.79$). The answer "radiological technologist suffered from less stress and workload than others when they work usually" showed the worst score($2.88{\pm}0.98$). According to the classification of each health-related major, the mean score of students who are a major in the department of the radiological technologist was the best($3.46{\pm}0.46$) and the students who are major in department of the physical therapy was the worst($3.24{\pm}0.40$). The radiological technologist have to effort to make positive image in the hospital. It is possible to be developed their knowledge and professionalism by cooperating between school and hospital as well as advertising with mass madia.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.20 no.10
• /
• pp.384-394
• /
• 2019

The purpose of this study is to investigate the relationships between physical factors, economic factors, and cultural factors of tourism gentrification (TG) in urban areas. Based on the results of an empirical analysis, we provide the basic theory and practical implications of the relationship between tourism phenomena and city image. This study used a questionnaire for residents of the Jeju area. From September 1, 2018, to October 3, 2018, the survey was conducted in Nuemori Street, Yeongdong Street, Gucheong Eup, and Moon Town. Thus, we use 479 samples for analysis out of 500 samples obtained. This study produced two important results. First, the physical, economic, and cultural factors of tourism gentrification have significant effects on cognitive image and emotional image. Second, economic factors have statistical significance in cognitive image and emotional image. These results and implications can be useful for practical implications of the theoretical implications of tourism gentrification and regional specialization promotion policies. In addition, from the economic point of view, what should be considered is that development-centered area development can have a negative impact on urban image. Despite these research results, there are limitations in the research, such as cross-sectional studies and short-term studies, and we look forward to a longitudinal study in the future from a long-term perspective.

• Journal of KIISE
• /
• v.42 no.6
• /
• pp.699-706
• /
• 2015

In recent years, as near-duplicate image has been increasing explosively by the spread of Internet and image-editing technology that allows easy access to image contents, related research has been done briskly. However, BoF (Bag-of-Feature), the most frequently used method for near-duplicate image detection, can cause problems that distinguish the same features from different features or the different features from same features in the quantization process of approximating a high-level local features to low-level. Therefore, a post-verification method for BoF is required to overcome the limitation of vector quantization. In this paper, we proposed and analyzed the performance of a post-verification method for BoF, which converts SIFT (Scale Invariant Feature Transform) descriptors into 128 bits binary codes and compares binary distance regarding of a short ranked list by BoF using the codes. Through an experiment using 1500 original images, it was shown that the near-duplicate detection accuracy was improved by approximately 4% over the previous BoF method.

• Cartoon and Animation Studies
• /
• s.36
• /
• pp.259-280
• /
• 2014

Animation is showing the highest record in entertainment around the world and writing the history of 3D animation again. The image contents effect thanks to the proper introduction of the state-of-art digital technology, which is one of the causes of the outstanding entertainment and the factual reproduction of the images, provided an opportunity to transmit the meaning of image aesthetics, which is a virtual reality and image reproduction through the reality realization of photo medium, and to reinterpret the boundary of virtual reality. Especially, the development of digital contents technology due to scientific technologies demolishes the boundary of virtual reality and reality and creates the effect of making viewers be absorbed by realizing the virtual reality by means of 3D reality images which highlight the special characteristic of photos. The aspect of the contents technology and image aesthetics which can be interpreted in a view point beyond the existing concept of reality is found in the aura theory of Benjamin and in the Simulacres of Baudrillard. The 3D image by photo-reality herein presents various suggestions in the aspect of real existence of spatial expression, the meaning creation process of reality, the existence value of virtual images.

• Proceedings of the KAIS Fall Conference
• /
• 2010.11a
• /
• pp.235-238
• /
• 2010

멀티미디어 시대가 도래함에 따라 콘텐츠들이 인터넷을 통해 셀 수 없을 만큼 많은 양이 전송되어지고 있다. 하지만 콘텐츠를 전송할 때의 안전성과 보안성 및 저작권 문제 등은 아직도 보완해야 할 문제이다. 따라서 본 논문에서는 콘텐츠 중 이미지로 한정하여서 이 이미지의 부분의 좌표를 선택하여 그 부분만 암호화함으로써 이미지를 안전하게 보호할 수 있는 기법에 대해 연구하고자 한다.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2017.11a
• /
• pp.139-141
• /
• 2017

화재는 다른 재난보다 확산 속도가 빠르기 때문에 신속하고 정확한 감지와 지속적인 감시가 요구된다. 최근, 신속하고 정확한 화재 감지를 위해, CCTV(Closed-Circuit TeleVision)으로 획득한 이미지를 기계학습(Machine Learning)을 이용해 화재 발생 여부를 감지하는 화재 감지 시스템이 주목받고 있다. 본 논문에서는 기계학습의 기술 중 정확도가 가장 높은 딥러닝(Deep Learning)기반의 CCTV 화재 감지 시스템을 제안한다. 본 논문의 시스템은 딥러닝 기술 적용뿐만이 아니라, CCTV 이미지 전처리 과정을 보완함으로써 딥러닝에서의 미지 데이터(unseen data)의 낮은 분류 정확도 문제인 과적합(overfitting)문제를 해결하였다. 본 논문의 시스템은 약 80,000 개의 CCTV 이미지 데이터를 학습하여, 90% 이상의 화재 이미지 분류 정확도의 성능을 보여주었다.