• Smart Media Journal
• /
• v.7 no.2
• /
• pp.34-39
• /
• 2018

There are many studies on red tide due to the continuous increase in damage to domestic fish and shell farms by the harmful red tide. However, there is insufficient domestic research of identifying harmful red tide algae that automatically recognizes red tide images. In this paper, we propose a red tide image classification method using deep learning based open source. To solve the problem of recognition of various images of red tide algae, the proposed method is implemented by using tensorflow framework and Google image classification model.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.21 no.6
• /
• pp.13-20
• /
• 2011

Nowadays, digital-images are widely used at Web, industrial and medical applications. There have been many studies on online and Web copyright. But there are a few studies on industrial digital-image. In this paper, we propose the image encryption scheme for digital image in the industrial film. We implement and verify the proposed digital image encryption scheme for prevention of industrial secrets and intellectual property right outflow.

• Annual Conference of KIPS
• /
• 2010.04a
• /
• pp.425-428
• /
• 2010

멀티미디어 기기의 확산과 인터넷의 발달로 Flickr, Facebook 과 같은 사회적 네트워크를 기반으로 이미지 공유가 활발해졌다. 사회적 네트워크 사이트에서 이미지의 효율적인 검색과 관리를 위해서 태그를 이용하는 방법이 많이 사용되고 있다. 하지만 많은 양의 이미지에 수동으로 태그를 등록하는 것은 사용자에게 많은 시간과 노력을 요구한다. 태그 추천 기술은 자동으로 사용자에게 태그를 추천함으로써, 수동 태깅의 한계를 극복할 수 있는 방법이다. 본 논문에서는 사회적 네트워크를 기반으로 하는 폭소노미에서 사용자 사이의 사회적 관계를 사용자 들의 얼굴 정보를 이용하여 측정하고, 이를 활용하여 이미지 태그를 추천하는 기술을 제안한다. 제안하는 방법은 이미지의 시각 정보와 태그 분포뿐만 아니라 사용자 사이의 사회적 관계 정보를 추가로 활용한다. 실험을 통해서 제안하는 방법이 기존의 이미지 태그 추천 방법에 비해서 7% 향상된 태그 추천의 정확성을 보장하는 것을 증명하였다.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.12 no.3
• /
• pp.1341-1349
• /
• 2011

This research is focused on an analysis on the structure of RAW image file and the development of a RAW image file viewer for an embedded device. Recently, several RAW image file formats are being used for saving and displaying the images created by various DSLR cameras, and the necessity of handing RAW images in mobile multimedia devices is increasing. For the development of RAW image decoding/encoding library applicable to WinCE-based embedded devices viewer, an analysis of RAW image file formats, such as CRW, CR2, PEF, NEF, MRW, have been performed because their formats are not released in public. By using the library, the analysis software which can extract RAW image data, 2~3 JPEG image files and other informations such as the specification of a camera and various photographic parameters from RAW image files, were developped and a RAW image file viewer which can run in WinCE-based embedded devices. The experimental result has shown that the viewer could encode and decode RAW image files successfully and it took approximately 10secs to load them to the screen in S3C6410 based embedded platform. The outcomes of this research cloud be a good information and solution to multimedia application developers.

• Journal of the Economic Geographical Society of Korea
• /
• v.13 no.3
• /
• pp.354-380
• /
• 2010

Cities are the most important type of tourist destination across the world, and yet urban areas have neglected in most academic studies of tourism. Urban destinations serve as gateways for tourist entry to the country, as centers of accommodation and a base for excursion to rural areas as well as destinations in their own right. Increasingly cities rely on image promotion to attract tourists to cities. A city's image is the sum of beliefs, ideas, and impressions that a people have of a city. Image has always been of great interest and concern to city marketers. The image improvement is very important especially in urban tourism development because tourism overwhelmingly depends on image. The cost and effectiveness of the image improvement strategy depends on the city's current image and real attributes. Some cities are blessed with positive images. They don't require changing the image so much as amplifying it and delivering it to more target groups. Many cities are stuck with a negative image. They need to remove it and make a positive out of a negative to correct it. Image reversals, however, are difficult to accomplish. Some cities are not well known because they are small, lack attractions, or don't advertise. They need to identify, develop, and disseminate a strong positive image for the city.

• The Journal of the Korea Contents Association
• /
• v.16 no.12
• /
• pp.113-123
• /
• 2016

The purpose of this study is to look into the effect of wearing color lenses on one's image and was based on 221 college students in Gyeonggi-do and Gangwon-do. I examined how it appears as the evaluation factor visually. After by looking in the different image effect and relevance as to the classified evaluating factors, I tried to look into what effect the color lenses has on woman eye and image. The result is as follows. It appears that wearing color lenses makes one look fancier, more attractive, sophisticated, and favorable, whereas not wearing color lenses makes one look softer, weaker, more innocent, and comfortable. Analyzing these evaluations showed that wearing color lenses has most to do with attractiveness followed by pureness, familiarity, and decorativeness in order, whereas not wearing color lenses has most to do with familiarity followed by attractiveness, pureness, and decorativeness. It is considered that eyes with color lenses on them make the person seem decorative, attractive, and pure, which brings effect of improving one's eye and face image. Analyzing the correlation between each color lenses-wearing factor and one's image showed that when a person is wearing color lenses, the more the person is considered decorative, pure, and attractive, the more it has to do with improving the person's eye and face image. The result, therefore, shows that wearing color lenses makes one's eye and face image attractive, pure, and decorative, and wearing them is an important means to improve one's eye and face image.

• Journal of the HCI Society of Korea
• /
• v.14 no.1
• /
• pp.5-13
• /
• 2019

SNS has been advanced from first to third generation by changing its service format in various ways. Nowadays, image-based SNS such as instagram and pinterest where users communicate via images has become popular as third generation service. Due to the fact that users communicate especially through images, image-based SNS utilizes images in different ways compared to other SNS. This study derived various characteristics of images in image-based SNS, and observed how users perceive each of them differently. Also, relationship between the characteristics and user satisfaction on image-based SNS is analyzed. The characteristics include 6 items; 'implicity', 'recordability', 'expressing identity', 'indirect experience', 'temporary amusement', and 'stimulating desire.' As a result of comparing user perception regarding those 6 characteristics, recordability and indirect experience were highly recognized than other characteristics. Also, according to users' age, motivation of using image-based SNS, and number of followers they have, users perceived each characteristic in different level. Finally, relationship between the characteristics and user satisfaction was analyzed, and the result showed that indirect experience had positive influence to user satisfaction. Regarding indirect experience, it was highly perceived by users and also had positive influence to their satisfaction, which means it is the most typical characteristic of image-based SNS.

• Proceedings of the Korean Information Science Society Conference
• /
• 2004.10b
• /
• pp.640-642
• /
• 2004

SVG(Scalable Vector Graphic)는 웹 개발자 디자이너 및 사용자가 간단한 선언 방식의 프로그래밍 모델을 통해 HTML의 한계를 뛰어 넘어 견고한 비주얼 컨텐츠와 대화형 기능을 작성할 수 있는 W3C의 표준 XML 기반의 이미징 모델이다. 웹에서의 SVG는 확장형 벡터 그래픽으로서 2차원 이미지를 이미지의 손상 없이 표현하게 된다. 이 논문에서는 2차원에 국한되어 있는 SVG를 확장하여 3차원 이미지를 표현하고자 한다. 2차원 이미지의 표현은 x축과 y축의 평면 축만 있는데 비해 3차원 이미지의 표현은 깊이 정보인 z축을 가지고 있어야 3차원 이미지를 표현하게 된다. 비트맵 그래픽과 달리 벡터 그래픽인 SVG를 이용하여 웹 브라우저에서 3차원 오브젝트를 표현하는 방법에 대친 고찰하고자 한다.

• Proceedings of the Korea Contents Association Conference
• /
• 2006.11a
• /
• pp.840-844
• /
• 2006

2차원 이미지는 오래전부터 발전되어온 훌륭한 표현 방법 중 한가지 이다. 하지만 단순한 2차원 이미지만을 가지고 보정과 편집을 통해 다양한 효과를 표현하는데 있어 여러 가지 한계가 있다. 본 논문에서는 2차원의 평면 이미지인 나비와 춘란의 이미지를 사용하여 나비의 날개짓과 춘란의 생장을 표현함으로써 단순한 2차원 평면 이미지를 사용하여 3차원 공간상에서 움직임과 동적인 느낌을 강조한 3차원 영상 제작기법을 구현하고자 한다. 이러한 영상제작기법은 동적인 효과를 가진 고품질의 영상을 쉽게 제작할 수 있기 때문에 개인 뿐만 아니라 전문 방송과 영상 매체에 효율적으로 적용할 수 있다는 장점을 가지고 있다.

• Annual Conference of KIPS
• /
• 2006.05a
• /
• pp.657-660
• /
• 2006

자연영상이나 스팸메일 영상으로부터 텍스트 영역을 추출하고 추출한 텍스트 영역에 이진화를 수행하고 나면 가로 방향이나 세로획 방향으로 놓여 있는 "1" 그리고 "ㅡ" 에 해당하는 한글의 종성부분이 이미지 내의 잡영을 지울 때 종종 지워지는 결과를 볼 수 있다. 이렇게 지워진 획 부분을 되살리기 위한 방법으로 텍스트 Hinting 알고리즘을 제안한다. 텍스트 Hinting 알고리즘은 이진화된 이미지의 텍스트 픽셀 위치와 동일한 좌표에 해당하는 원본 이미지의 RGB 값을 추출하여 추출된 텍스트 후보 영역의 색상을 알아낸다. 추출된 텍스트 색상 레이어 이미지와 이진화된 이미지에 OR연산을 수행하게 되면 지워진 획 부분을 복원할 수 있다. 제안한 방법을 스팸 이미지에 적용한 결과 텍스트 추출결과를 획기적으로 개선할 수 있음을 보였다.