• Smart Media Journal
• /
• v.9 no.4
• /
• pp.9-16
• /
• 2020

Recently, various studies are being conducted to integrate Image Segmentation into smart factory industries and autonomous driving fields. In particular, Image Segmentation systems using deep learning algorithms have been researched and developed enough to learn from large volumes of data with higher accuracy. In order to use image segmentation in the autonomous driving sector, sufficient amount of learning is needed with large amounts of data and the streaming environment that processes drivers' data in real time is important for the accuracy of safe operation through highways and child protection zones. Therefore, we proposed a novel DFCN algorithm that enhanced existing FCN algorithms that could be applied to various road environments, demonstrated that the performance of the DFCN algorithm improved 1.3% in terms of "loss" value compared to the previous FCN algorithms. Moreover, the proposed DFCN algorithm was applied to the existing U-Net algorithm to maintain the information of frequencies in the image to produce better results, resulting in a better performance than the classical FCN algorithm in the autonomous environment.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.32 no.5
• /
• pp.933-943
• /
• 2022

As the Internet develops and the utilization rate of computers increases, the threats posed by malware keep increasing. This leads to the demand for a system to automatically analyzes a large amount of malware. In this paper, an automatic malware analysis technique using a deep learning algorithm is introduced. Our proposed method uses CNN (Convolutional Neural Network) to analyze the malicious features represented as images. To reflect semantic information of malware for detection, our method uses the opcode frequency data of binary for image generation, rather than using bytes of binary. As a result of the experiments using the datasets consisting of 20,000 samples, it was found that the proposed method can detect malicious codes with 91% accuracy.

• International Area Studies Review
• /
• v.15 no.1
• /
• pp.315-339
• /
• 2011

As the Korean economy grows, the brand value of Korean companies such as Samsung, LG and Hyundai Motor has been elevated greatly. Compared to the brand value of Korean companies, Korea's national image is very lowly ranked. In addition Korea's national brand is undervalued compared to economic volume. So, the purpose of this study is to find way to enhance the Korea's national brand in Japanese Market through brand credibility. The results as follows. First, this study find that brand credibility is consist of expertise and trustworthiness in Japanese market. Second Korea national image positive impact on brand credibility. Third, brand credibility positive impact on perceived quality and information cost saving. Finally, brand credibility negative impact on perceived risk. In conclusion, all hypothesis are significant. So these results are very useful to Korea government and Korean companies.

• Archives of design research
• /
• v.13
• /
• pp.139-150
• /
• 1996

This study is to develop brand renovation identities for kolon mode and 5 other brands: Arthur dixon, Arpeggio, Manstar, Just, Bella. Since those brands have their own identities for about 10 to 20 years, new images have to be made very carefully based on the examination of old identities whether they fit their concepts. lifestyle of their consumers, fasion trends and so on. The typical way of adopting a renovation identity for a existing brand is to consider a transition part which never needs to be considered for a new brand.

• Spatial Information Research
• /
• v.7 no.2
• /
• pp.283-303
• /
• 1999

Airphotos taken for the management of unauthorized houses in large cities like Seoul are very important material for understanding periodic change of topogrpahy. A research on construction of digital database using airphoto are required for the efficient management of existing airphotos, for the easy and better understanding of topography together with 1; 1,000 digital topographic map, and for the easy updating of topographic data. Digital data using 1 ; 5, 000 scale airphoto scanned 1,000 dpi has been experimentally constructed from georeferenced images to orthorectified images. The technical and economical possibilities for the construction of digital database using apripjoto have been checked based on the experimentation and future direction of how to make digital database using existing airphoto has been suggested.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• v.9 no.1
• /
• pp.221-224
• /
• 2005

본 논문에서는 워터마크가 삽입된 데이터의 저작권 보호를 위하여 데이터의 복제 시 신속한 위치추적을 통한 불법 복제 방지 시스템을 제안하고 시뮬레이션 하였다. 제안된 방법은 복사기, 프린터, 스캐너 등에 부착된 워터마크 검출 장치로부터 워터마크 검출 시 원 워터마크 이미지와 추출된 워터마크이미지가 일정 비 이상의 상관관계가 있을 경우 불법 복제 상황으로 간주하고, 디지털 데이터로 변환된 워터마크 이미지와 주소 정보가 전력선을 통하여 전송된다. 수신단에서는 수신된 데이터의 발신자 정보를 통해 위치정보를 알아내어 불법 복제 작업현장의 위치를 추적한다. 전력선을 통신선로로 이용 시 전송신호는 전력선 채널 환경에서 임펄스 잡음에 많은 영향을 받기 때문에 본 논문에서는 제안한 시스템의 검증을 위해 AWGN과 임펄스 잡음을 고려하고 잡음 특성이 우수하고 신뢰성이 비교적 강한 DS-CDMA/BPSK 시스템을 통해 제안된 시스템을 시뮬레이션 하였다. 또한, 열악한 채널 환경으로부터 수신성능을 개선하기 위해 컨벌루션 부호화기법을 적용하여 성능 개선 전 후의 복원 이미지의 성능을 비교 분석 하였다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2011.11a
• /
• pp.330-333
• /
• 2011

TIP 기술은 2D 그림 또는 한 장의 사진으로부터 기하정보를 추출하여 3 차원 입체 효과를 만들어 영상 내부를 네비게이션할 수 있는 기술로써, 게임, 엔터테인먼트, 교육, 홍보 등 다양한 분야에서 요구되는 주요기술이다. 본 논문에서는 최근 대두되고 있는 스마트 device 의 platform 가운데 하나인 android platform 상에서의 OpenGL ES Library 를 이용한 TIP 기술 적용 및 구현 기술을 제안한다. 제안 방법은 전경객체의 추출이 어려운 상황을 감안하여 보다 사실적 장면 구성이 용이하도록 사용자의 선택에 의한 소실점을 이용하고, OpenGL ES Library 를 이용하여 3D 배경 모델을 획득하고, 이미지를 텍스쳐 매핑하여 3D 가상공간을 완성한 후 카메라의 시점 변환을 통해 이미지 내부를 네베게이션할 수 있도록 한다. 실험영상은 android platform 상의 device 에서 촬영한 이미지를 사용하고, android 2.1 및 OpenGL ES 1.0 기반으로 구축함으로써, 제안 기술을 다양한 android platform smart device 에서 적은 비용과 시간으로 응용 개발에 효과적으로 적용 가능하도록 구현하였다.

• Asia Marketing Journal
• /
• v.12 no.3
• /
• pp.99-116
• /
• 2010

There is now intense competition among many outdoor brands in the domestic market. Establishing differentiated brand image and enhancing brand identity are very important in this situation. This case is to investigate Black Yak's strategy for enhancing their brand identity. The Black Yak builds up their popularity by implementing social responsibility activities along with sustaining their extreme traditional outdoor image. It is effective to step up their brand identity. Future challenges and suggestions are discussed at the end.

• Journal of IKEEE
• /
• v.28 no.2
• /
• pp.158-167
• /
• 2024

In this study, U-net model based on electrical capacitance is applied to monitor the condition inside the pipeline of semiconductor rear end process implemented in the numerical simulation. Capacitance values measured from electrodes attached to the pipeline is used as input data for the U-net network model and estimated permittivity distribution by the U-net model is used to reconstructed cross-sectional image at the pipeline. In the numerical simulation, images reconstructed by U-net model, Fully-connected neural network (FCNN) model and Newton-Raphson method are compared for evaluation. U-net model shows good results as compared to other models.

• The Research Journal of the Costume Culture
• /
• v.9 no.4
• /
• pp.629-638
• /
• 2001

This study was intended to identify the desired image and fabric preference of woman college student for apparel and the relationship between these variables. Data were collected by questionnaire distributed to 260 woman college students through August to September of 2000. After eliminating incomplete questionnaires, 236 were analyzed. The most desired image was neat, and the most preferred fabric was natural fiber textile in fiber contents and light and soft in fabric sensation. The avoided image was masculine, and the negative sensation was heaviness. As a result of factor analysis, 7 factors -cute, intellectual, animate, neat, mature, sporty, sexy- were determined in image. And 8 factors -soft, durable, flat, rigid, light, bulky, heavy, pliable- were determined in fabric sensation. These factors explained large percentage of variance respectively. Multidimensional scaling was employed to analyze the relationship between desired image and fabric preference. Two dimensions were accepted to interpret the relationship. One of the results showed the closeness among the natural fiber textile, lightness, durability and natural image. And the short distance among the blended textile, elasticity, warmness and sporty image was presented.