• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.15 no.1
• /
• pp.37-43
• /
• 2015

Technical treatments of image contents on the web include the copy protection method such as the image capture protection technology and the traitor tracing method to detect unauthorized duplications through watermarking insertion or feature information technology. However, these two methods have their own weaknesses. The image capture protection method is unable to protect illegal captures when the URLs of image sources are exposed. The traitor tracing method is fundamentally unable to protect illegal captures due to its post-treatment method. Besides, the weakness of using the copyright information display technology involves easy removal of copyright information from copyrighted contents. This paper suggests a model of the web image contents protection system which makes it hard to separate copyright information from web image contents and allows image contents to be shown only in the authorized websites.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.18 no.12
• /
• pp.548-556
• /
• 2017

The purpose of this study is to examine the effects of cognitive and affective images of a farm party venue on consumer satisfaction and revisit intention with a research model and hypothesis test. First, the cognitive and affective images of a farm party venue had a significant effect on consumer satisfaction in the test and the cognitive image had greater impact on consumer satisfaction than the affective image had. Second, consumer satisfaction had a significant effect on the revisit intention in the test, which indicates that farm party venues are required to find a way to boost the satisfaction of tourists in order to encourage their intentions to revisit. In order to revitalize rural tourism through farm party and raise income in rural areas, it is most important that farm party venue produce images that are differentiated from other farmhouses. In order to activate the farm party for the 6th industry, it will be possible to establish images of the farmers and utilize them in promotional marketing for the promotion of rural tourism. The present study is limited in that it did not collect feedback from farm party operators in action. With this in mind, another study is planned, focusing on those farm party operators.

• Journal of the Korea Society of Computer and Information
• /
• v.17 no.3
• /
• pp.193-201
• /
• 2012

For the competition of current corporations, the necessity of image-making strategy differentiating themselves from others are more highlighted than simple technology development or previous sales technique. Thus the corporations need more advanced management measures of corporate image to secure new capabilities. This study figured out previous studies on corporate image, deduced factors to be considered for improving continuous corporate image, analyzed structural relationships among them, and suggested political implications through systematic management strategy about improving corporate image that current corporations need.

• Journal of Broadcast Engineering
• /
• v.26 no.1
• /
• pp.61-69
• /
• 2021

Image outpainting is a very interesting problem in that it can continuously fill the outside of a given image by considering the context of the image. There are two main challenges in this work. The first is to maintain the spatial consistency of the content of the generated area and the original input. The second is to generate high quality large image with a small amount of adjacent information. Existing image outpainting methods have difficulties such as generating inconsistent, blurry, and repetitive pixels. However, thanks to the recent development of deep learning technology, deep learning-based algorithms that show high performance compared to existing traditional techniques have been introduced. Deep learning-based image outpainting has been actively researched with various networks proposed until now. In this paper, we would like to introduce the latest technology and trends in the field of outpainting. This study compared recent techniques by analyzing representative networks among deep learning-based outpainting algorithms and showed experimental results through various data sets and comparison methods.

• The Journal of the Korea Contents Association
• /
• v.10 no.2
• /
• pp.146-154
• /
• 2010

Argument on the postmodernism of philosophy and history, epic and effect, and culture and art is becoming more ambiguous in scope due to digital technology development. Digital technology makes to change of aesthetic approach over the length and breadth of art and culture including medium art. Analysis of Digital images is changed from presence of images to feature analysis of images which is made by digital technology, and raise the question of how to analyze the images of reproducing digital technology focused on realism. Digital image, focused on hyper reality, should be approached not by film aesthetic approach but by shot unit. Due to emphasizes image reality reproduction by frame unit and not the short unit of the narrative approach, the artistic approach should differ from previous realism practice. Particularly, when considering movies which is focused on illusion, the realistic approach should be realized not in the of realistic approach in narrative aspect but in the aspect of realistic approach in painting aspect.

• Journal of Digital Convergence
• /
• v.11 no.4
• /
• pp.449-457
• /
• 2013

This study seeks to find the sociocultural value which influences the man image and make-up in media. It helps to gain the effective data that suggest the application of male make-up in promoting development of market. The man emphasizes the practical value which is the technical and instrumental value to express the man image rationally, aesthetic value to pursue aesthetic purely and symbolic value which is a volitional and intentional value experienced in the history and society to express preferring man images as the society is changed. As analysing the man image based on sociocultural value, the practical value of men's make-up is to maximize the utility vale in order to deliver a clear image considering their activity range, environment, and situation. Second, the aesthetical value of men's make-up is to emphasize femininity through women's make-up technic. Third, the symbolic value of men's make-up is to deliver a concept or intentionally create an image by maximizing overall characteristic image. It will be hopefully valuable as a basic data for developing make-up products and setting trend for men as well as for future studies.

• The Korean Journal of Nuclear Medicine Technology
• /
• v.24 no.1
• /
• pp.15-19
• /
• 2020

Purpose Generative Adversarial Network(GAN) is one of deep learning technologies. This is a way to create a real fake image after learning the real image. In this study, after acquiring artificial intelligence images through GAN, We were compared and evaluated with real scan time images. We want to see if these technologies are potentially useful. Materials and Methods 30 patients who underwent ¹⁸F-FDG Brain PET/CT scanning at Severance Hospital, were acquired in 15-minute List mode and reconstructed into 1,2,3,4,5 and 15minute images, respectively. 25 out of 30 patients were used as learning images for learning of GAN and 5 patients used as verification images for confirming the learning model. The program was implemented using the Python and Tensorflow frameworks. After learning using the Pix2Pix model of GAN technology, this learning model generated artificial intelligence images. The artificial intelligence image generated in this way were evaluated as Mean Square Error(MSE), Peak Signal to Noise Ratio(PSNR), and Structural Similarity Index(SSIM) with real scan time image. Results The trained model was evaluated with the verification image. As a result, The 15-minute image created by the 5-minute image rather than 1-minute after the start of the scan showed a smaller MSE, and the PSNR and SSIM increased. Conclusion Through this study, it was confirmed that AI imaging technology is applicable. In the future, if these artificial intelligence imaging technologies are applied to nuclear medicine imaging, it will be possible to acquire images even with a short scan time, which can be expected to reduce artifacts caused by patient movement and increase the efficiency of the scanning room.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.17 no.10
• /
• pp.61-67
• /
• 2016

With the current high distribution rate of smart devices and the recent development of computing technology, user interest in multimedia, such as photos, videos, and so on, has rapidly increased, which is a departure from the simple pattern of information retrieval. Because of these increasing interests, image processing techniques, which generate and process images for diverse applications, are being developed. In entertainment recently, there are some techniques that present a celebrity's image as a mosaic comprising many small images. In addition, studies into the mosaic technique are actively conducted. However, conventional mosaic techniques result in a long processing time as the number of database images increases, because they compare the images in the databases sequentially. Therefore, to increase search efficiency, this paper proposes an algorithm to generate a mosaic image using a discrete cosine transform (DCT) hash. The proposed photo mosaic-generation algorithm is composed of database creation and mosaic image generation. In database creation, it first segments images into blocks with a predefined size. And then, it computes and stores a DCT hash set for each segmented block. In mosaic generation, it efficiently searches for the most similar blocks in the database via DCT hash for every block of the input image, and then it generates the final mosaic. With diverse experimental results, the proposed photo mosaic-creation algorithm can effectively generate a mosaic, regardless of the various types of images and sizes.

• Journal of The Korean Association For Science Education
• /
• v.34 no.8
• /
• pp.719-730
• /
• 2014

The purpose of this study was to investigate elementary school students' perceptions about science, engineering and technology and their images of scientists, engineers, and technicians. In order to investigate students' images of scientists, engineers, technicians and student's perception of science, engineering, and technology, we used the tools "Draw a scientist at work, Draw an engineer at work, and Draw a technician at work". We have revised the tool DAST (Draw a scientist test), which was used in Fralick et al.'s study (2009). Subjects were 209 6th grade students sampled from an elementary school in G-city in Korea. According to the results of this study, the students' representative image of a scientist was similar to stereotypical scientist image in previous studies, but the students perceived science as a field of research with various professionals. The students' representative image of an engineer was a man with short hair, no beard or mustache, wearing ordinary clothes but no glasses. The engineer was designing or constructing a ship, a robot, a computer, and an airplane. The students' representative image of a technician was a man with short hair, wearing protective goggles and a mask for welding. The technician was fixing a car, a robot, a rocket, etc. and working with wrenches, hammers, screw drivers, welding machines, etc. Many students didn't perceive engineering and technology as fields of research. Also, many students didn't variously perceive engineering and technology as fields and ways of study.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• fall
• /
• pp.283-286
• /
• 2021

4차 산업혁명을 맞이해 최근 산업 및 기술 영역에서는 인공지능을 이용한 생산력 향상, 자동화 등 딥러닝의 보편화가 빠르게 진행되고 있다. 또한, 딥러닝의 성능을 도출하기 위해서는 수많은 양의 학습용 데이터가 필요하며 그 데이터의 양은 딥러닝 모델의 성능과 정비례한다. 이에 본 작품은 최신형 영상처리 Library인 Albumentations를 이용하여 영상처리 알고리즘을 이용하여 이미지를 증강하고, 이미지 데이터 크롤링 기능을 통해 Web에서 영상 데이터를 수집을 자동화하며, Label Pix를 연동하여 수집한 데이터를 라벨링 한다. 더 나아가 라벨링 된 데이터의 증강까지 포함하여 다양한 증강 자동화를 한 인터페이스에 집적시켜 딥러닝 모델을 생성할 때 데이터 수집과 전처리를 수월하게 한다. 또한, Neural Net 기반의 AdaIN Transfer를 이용하여 이미지를 개별적으로 학습하지 않고 Real time으로 이미지의 스타일을 옮겨올 수 있도록 하여 그림 데이터의 부족 현상을 해결한다.