• Proceedings of the Korea Society for Industrial Systems Conference
• /
• 2009.05a
• /
• pp.82-87
• /
• 2009

본 논문에서는 감성 기반으로 텍스타일을 자동으로 색인하고 검색 할 수 있는 시스템을 제안한다. 제안된 시스템은 영상 수집기, 감성 색인기, 검색기(Matcher), 질의 인터페이스로 구성되어 있다. 감성 색인기는 텍스타일 영상에 포함된 컬러와 패턴 정보를 기반으로 감성개념을 인식하고, 이를 이용하여 영상을 색인한다. 이때, 감성 어휘로 고바야시가 정의한 8개 (romantic, natural, casual, elegant, chic, classic, dandy, modern)를 사용한다. 질의 인터페이스에서 사용자는 두 가지 방식으로 질의를 선택할 수 있다. 첫 번째 방법은 감성 키워드를 사용하는 것이고, 두 번째는 사용자의 의도를 설명할 수 있는 영상을 이용하는 예제 기반 질의 방식이다. 질의가 주어지면, 검색기는 랭킹 알고리즘을 사용하여 검색 결과를 생성한다. 이 때, 유사도 비교방식은 선택된 질의방식에 따라 달라진다. 제안된 시스템의 성능을 검증하기 위해 웹 검색에 익숙한 50명(남자: 32명, 여자: 18명)을 대상으로 웹에서 수집한 3,416 장에 대해서 3가지 항목으로 사용자 평가를 하였다. 사용자 평가의 항목인 적합도(Relevance), 노력(Search Effort), 만족도(Satisfaction)의 결과로 사용자가 검색한 결과영상에서 적합도의 수치가 낮게 나왔지만, 만족도와 노력의 수치는 높게 평가되었다. 제안된 시스템에서 사용자는 자신이 선호하는 결과 영상을 상위 40개의 영상 내에서 얻을 수 있었다. 이는 제안된 시스템이 사용자들이 원하는 영상을 효율적으로 검색할 수 있다는 것을 증명했다.

• Proceedings of the Korea Society for Industrial Systems Conference
• /
• 2009.05a
• /
• pp.138-143
• /
• 2009

본 논문에서는 감성 공간에서 mean shift clustering과 user feedback을 이용하여 영상 검색 결과를 개선하기 위한 시스템을 제안한다. 제안된 시스템은 사용자 인터페이스, 감성 공간 변환, 검색결과 순위 재지정(re-ranking)으로 구성된다. 사용자 인터페이스는 텍스트 형태의 질의 입력과 감성 어휘 선택에 따른 user feedback에 의해 개선된 검색결과를 보인다. 사용된 감성 어휘는 고바야시가 정의한 romantic, natural, casual, elegant, chic, classic, dandy, modern 등의 8개 어휘를 사용한다. 감성 공간 변환 단계에서는 입력된 질의에 따라 웹 영상 검색 엔진(Yahoo)에 의해 검색된 결과 영상들에 대해 컬러와 패턴정보의 특징을 추출하고, 이를 입력으로 하는 8개의 각 감성별 분류기에 의해 각 영상은 8차원 감성 공간으로의 특징 벡터로 변환된다. 이때 감성 공간으로 변환된 특징 벡터들은 mean shift clustering을 통해 군집화 되고, 그 결과로써 대표 클러스터를 찾게 된다. 검색결과 순위 재지정 단계에서는 user feedback 유무에 따라 대표 클러스터의 평균 벡터와 user feedback에 의해 생성된 사용자 감성 벡터에 의해 검색 결과를 개선할 수 있다. 이때 각 기준에 따라 유사도가 결정되고 검색결과 순위가 재지정 된다 제안된 시스템의 성능을 검증하기 위해 7개의 질의의 각 400장, 총 2,800장에 대한 Yahoo 검색 결과와 제안된 시스템을 개선된 검색 결과를 비교하였다.

• 한국HCI학회:학술대회논문집
• /
• 2009.02a
• /
• pp.562-566
• /
• 2009

In this paper, we present a novel system to categorize web image search results using emotional concepts and to browse the results more conveniently and easily. The proposed system can categorize search results into 8 emotional categories based on emotion vector, which obtained by color and pattern features. Here, we use Kobayashi’s emotional categories: {romantic, natural, casual, elegant, chic, classic, dandy and modern}. With search results for a given query, the proposed system can provide categorized images for each emotional category. With 1,000 Yahoo! search images, we compared the proposed method with Yahoo! image search engine in respect of satisfaction, efficiency, convenience and relevance with a user study. Our experimental results show the effectiveness of the proposed method.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.10 no.5
• /
• pp.645-652
• /
• 2015

In underwater, such as fish farm and sea, turbidity is increased by water droplets and various suspended, therefore light attenuation occurs depending on the depth also caused by the scattering effect of light float. In this paper, in order to improve the visibility of underwater images obtained from these aquatic environment, we propose a visibility enhancement method using a haze removal method based on dark channel prior and a trained color transform model. In order to train a color transform model, we used underwater pattern images captured from Pohang and Yeosu, and to measure the performance of the proposed method, we carried out experiment of visibility enhancement using underwater images collected from Yeosu, Geomundo and Philippines. The results show that the proposed method can improve the visibility of underwater images of various locations.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2015.07a
• /
• pp.441-443
• /
• 2015

디지털 홀로그래픽 TV 시스템을 구현하려면 홀로그래픽 정보 획득 장치가 필요한데, 해상도 한계 때문에 홀로그램의 프린지 패턴을 상용 촬상 소자로는 직접 기록할 수 없다. 이를 극복하는 방법으로는 컬러 영상과 거리영상 정보를 얻은 후에 압축을 거쳐 수신 디스플레이단에 전송하고 이 정보로부터 3차원 모델을 형성한 후에 컴퓨터 생성 홀로그램을 생성하고 이를 회절소자를 이용하여 디스플레이하는 방법이 현재로서는 현실적인 방법이 될 것이다. 홀로그래픽 디스플레이에서는 회절소자인 공간광변조기 성능의 한계 때문에 기존 2DTV와 같은 수준의 디스플레이 구현은 매우 어렵다. 기존 공간광변조기는 픽셀피치가 커서 시야각이 매우 좁으나, 픽셀 크기를 작게 하는 동시에 공간광변조기 면적을 크게 하기에는 기술적인 어려움이 많다. 본 논문에서는 홀로그래픽 TV를 구현하는데 있어서 기술적으로 극복하고 고려해야 할 주요 요소에 대하여 분석한다.

• Journal of Korea Multimedia Society
• /
• v.13 no.3
• /
• pp.392-399
• /
• 2010

The Automobile has developed and changed through the years from the invention and increased human-being's scope of activity. Junction Box, one of the part of automobile, is inspected by human eyes which caused mistakes and slow progress. To achieve the speed and accuracy the system was compensated by vision system which is inspecting automatically. This paper is automatic inspection of fuse and relay which is inserted in the junction box by checking the color and pattern of the cover. After checking the performance of the system by using the junction box, the result was 100 percent perception and open the possibility to inspect junction box fast and easy and accurate if it is applied to the industry.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2015.11a
• /
• pp.71-73
• /
• 2015

In this paper, we propose the Real-Time Free Viewpoint TV System with multiple Microsoft Kinects and CUDA of NVidia GPGPU library. It generates a virtual view between two views by using color and depth image acquired by Kinect in real time. In order to reduce complexity of coordinate transformations and nearest neighbor method for hole filling caused by IR pattern interference, we parallelize this process using CUDA. Finally, it is observed that CUDA based system generates more frames than using CPU based system in the same time.

• Journal of Convergence Society for SMB
• /
• v.6 no.4
• /
• pp.85-91
• /
• 2016

This study is to research the tear film stability for 48 eyes, agreed the purpose of study, didn't have no contact lens wearing and were tested all two times in a day. Their visual acuity was more than 0.8, corrective visual acuity more than 0.8, the fattest K-reading, apical corneal radius, was in 7.40~8.40mm, corneal astigment was less than 1.00D and orthophoria. The tests, tear scope test, tear film break up time test(TBUT) and schirmer test order, were performed their functions before and after their working at interval of 6 hours over. The tearscope test results was no difference, TBUT was no difference, although 1.2 seconds more in the afternoon, shcirmer test was decreased 2.0mm in the afternoon.

• Journal of the HCI Society of Korea
• /
• v.3 no.1
• /
• pp.39-47
• /
• 2008

A mobile phone became the practical necessities of Chinese life that can not be explained without a mobile phone as it is rapidly popularized in China in recent years. As income increases due to economic growth, so did desire to buy better products. And This desire has made consumers in China more concerned about design and consequently leads to artistic design of a mobile phone. And also this trend is getting linked to people's personalisation in that people prefer rather to choose products they like than standardized ones in the middle of a variety of cultural inflows. This study mainly focuses on the development of the characterized mobile phone with a high class brand by use of traditional elements and of design identity of a mobile phone with Chines style that is well harmonized with cultural and personalized identity as consumers' preferences are quite different from each other depending on each country's culture. For this, this study investigates traditional elements such as patterns, colors and characters as well as development and features of the mobile phone design. This will also lead to the development of a mobile phone with traditional elements of China by studying utilization of design with traditional patterns. To do this, the study analyzes to research traditional patterns(Dragon, Phoenix, Peony, Lotus Flower), colors(Red, Yellow, Blue, Black, White) and historical origin and concept of characters. The study also looks into instances and personalisation of mobile phone design by analyzing literatures.

• Journal of Broadcast Engineering
• /
• v.19 no.3
• /
• pp.396-404
• /
• 2014

The field of searching clothing, which is very difficult due to the nature of the informal sector, has been in an effort to reduce the recognition error and computational complexity. However, there is no concrete examples of the whole progress of learning and recognizing for cloth, and the related technologies are still showing many limitations. In this paper, the whole process including identifying both the person and cloth in an image and analyzing both its color and texture pattern is specifically shown for classification. Especially, deformable search descriptor, LBPROT_35 is proposed for identifying the pattern of clothing. The proposed method is scale and rotation invariant, so we can obtain even higher detection rate even though the scale and angle of the image changes. In addition, the color classifier with the color space quantization is proposed not to loose color similarity. In simulation, we build database by training a total of 810 images from the clothing images on the internet, and test some of them. As a result, the proposed method shows a good performance as it has 94.4% matching rate while the former Dense-SIFT method has 63.9%.