• Journal of the Institute of Electronics and Information Engineers
• /
• v.50 no.6
• /
• pp.131-137
• /
• 2013

The barrel distortion makes serious problems in a wide-angle camera employing a lens of a short focal length. This paper presents a low-complexity hardware architecture for a real-time barrel distortion corrector and its implementation. In the proposed barrel distortion corrector, the conventional algorithm is modified so that the correction is performed incrementally, which results in the reduction of the number of required hardware modules for the distortion correction. The proposed barrel distortion corrector has a pipelined architecture so as to achieve a high-throughput correction. The correction rate is 74.86 frames per sec at the operating frequency of 314MHz in a $0.11{\mu}m$ CMOS process, where the frame size is $2048{\times}2048$. The proposed barrel distortion corrector is implemented with 14.3K logic gates.

• Cartoon and Animation Studies
• /
• s.41
• /
• pp.337-356
• /
• 2015

Recently augmented reality contents are variously used in public such as advertisements or exhibits as well as children's books. Therefore, it is certain that the market, development of augmented reality contents, is gradually growing. Those who are the producer of augmented reality may be familiar with the skill where those images are used as a marker which is created by image recognition technique. In case of using image recognition technique, they usually use the augmented reality marker platform from Qualcomm since it is able to recognize self-produced images and 3-dimensional figures at no cost. This study was started when undergraduate students began to use those general techniques in their contents producing process. AR majoring students in Namseoul University applied image recognition technique to 3 AR contents exhibited in Sejong Center. Creating 3 different images, they have registered images at Image Target Manager provided by Vuforia to use as a marker. Moreover, they have modified the image producing method to raise the recognition rate by research. The higher recognition rate brings the more stable use of augmented reality contents. To achieve the satisfied rate, they have compared the elements of color contrast, pattern and etc. in the use of platform. Thus, the effective image creation method has been drawn. This study is aiming to suggest the production of stable contents by recognizing smart devices' limitation and producing educational contents. The purpose of this study is to help practically augmented reality contents developers by illustrating the application of augmented reality contents which are based on image recognition technique and also its effectiveness at the same time.

• Korean journal of communication and information
• /
• v.47
• /
• pp.96-119
• /
• 2009

Although there ate many studies on cross-cultural comparison of advertising appeals, very little is known about how receivers from different cultures process visual images in global advertising. The purpose of this study is to examine how cultural differences between East Asians and Westerners influence the cognitive process of visual images from standardized global advertising by employing the Nisbett's framework of holistic/analytic thought. Nisbett contends that East Asian tend to attend to the context and the relations between objects and contexts as holistic thinkers while Americans tend to see the worlds analytically. The results of a experimental study conducted using 80 subjects from Korea and the United States suggest that Korean participants are more likely to mention relatively peripheral, nonsalient, or background information than are American participants. Thus, this study support the Nisbett's notion that East Asians are more sensitive to contextual information than are Westerners and challenge the belief that standardized visual images are part of a "universal language".

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2014.06a
• /
• pp.55-58
• /
• 2014

방송 제작 환경은 고품질의 콘텐츠를 빠르고 효율적으로 서비스하기 위하여 IT 기반 시스템으로의 전환을 진행하여 완성 단계에 이르렀으며, 대부분의 방송 콘텐츠는 파일 기반으로 제작 및 보관되고 있다. 과거 테이프 기반에서 파일 기반 콘텐츠로 전환되면서 신호 레벨로 진행되던 전통적인 품질 관리에 대한 새로운 방안이 요구되었으며, 이를 위하여 파일 기반 콘텐츠에 최적화된 콘텐츠 품질검사 시스템 개발이 진행되어 왔다. 이미지 처리에 기반하는 오류 검출 알고리듬의 복잡성으로 인하여 실시간 검사를 지원하지 못하여 HD 실시간 시스템에의 적용에 어려움이 있었으며, 대용량의 아카이브 시스템에서는 품질검사 시간에 대한 단축이 지속적으로 요구되고 있다. 이에 본 논문에서는 방송 환경에서 발생하는 블록 오류 등 다양한 A/V 오류를 고속으로 검출하기 위하여 최근에 급부상하고 있는 GPU 기반의 병렬처리를 이용하는 품질검사 실시간 고속화 시스템의 구현에 대하여 기술하고자 한다.

• Proceedings of the Korea Multimedia Society Conference
• /
• 2003.11a
• /
• pp.261-264
• /
• 2003

얼굴인식은 동일 사람의 얼굴이라도 조명변화나 얼굴 표정변화에 따라 매우 다른 영상들로 나타나기 때문에 매우 어려운 문제이다. 본 논문에서는 조명변화에도 강인하고 얼굴영상에 대해 높은 얼굴 인식률을 얻기 위해 2D-HMM(Hidden Markov Model) 얼굴인식 방법을 제안하고 실험하였다. 제안된 방법은 조명변화에 대해서 조명변화 함수인 $\delta$(delta) 함수를 0, 40, 60, 80으로 변화해 가면서 이미지 보정을 실험하였으며, 계산의 복잡성을 줄이고 얼굴영상에 대한 높은 인식률을 얻기 위해 기존의 픽셀값 대신에 2D-DCT 계수를 관측벡터로 사용하였다. 시스템의 성능을 평가하기 위해 정량적 평가방법은 FAR(False Accpt Rate)와 FRR(False Reject Rate)를 측정하여 비교하였으며, 기존의 얼굴인식 방법인 PCA, 1차원 HMM과 비교분석하였다. 실험결과 2D-HMM의 경우 FAR(False Accept Rate)가 5.08%로 ID-HMM 5.18%, PCA 10.16%보다 높은 성능을 보였으며, FRR(False Reject Rate)의 경우에도 0.01%로 10.16%인 PCA보다 좋은 성능을 보였다. 이로서 조명변화에 대해서는 PCA보다 2D-HMM 얼굴인식 방법이 우수함을 알 수 있었다.

• The KIPS Transactions:PartB
• /
• v.11B no.7 s.96
• /
• pp.779-784
• /
• 2004

In this paper, we have proposed an image contrast control method using brightness preserving on the FPD(Flat Panel Display). The proposed method can be easily applied to the FPD required real-time processing, since hardware complexity is greatly reduced using linear approximation method of CDF(Cumulative Density Function). For effective processing of the proposed algorithm, we have utilized the sample value of CDF and Barrel Shift. Visual test and standard deviation of their histogram have been introduced to evaluate the resultant output images of the pro-posed method and the original ones.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.17 no.10
• /
• pp.1109-1116
• /
• 1992

Mathematical morphology, theoretical foundation for morphological filter, is very efficient for the analysis of the geometrical characteristics of signals and systems and is used as a predominant tool for smoothing the data with noise. In this study, H/W design of morphological filter is implemented to process the gray scale dilation and the erosion in the same circuit and to choose the maximum and minimum value by a selector, resulting in their education of the complexity of the circuit and an architecture for parallel processing. The structure of morphological filter consists of the structuring-element block, the image data block, the control block, the ADD block, the MIN/MAX block, etc, and is designed on an one-chip for real time operation.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2024.05a
• /
• pp.114-115
• /
• 2024

컨테이너 오케스트레이션은 에지 클라우드에 컨테이너를 효율적으로 배포, 관리할 수 있게 해 주는 자동화 기술이다. 지리적으로 떨어져 있을 수 있는 에지 노드의 집합인 에지 클라우드의 규모와 복잡성이 커지면서 에지 클라우드에서 컨테이너의 고속 프로비저닝이 중요해졌다. 이때, 에지 클라우드에서 컨테이너의 배포 속도가 중요한 변수로 작용한다. 본고에서는 배포 속도를 개선하기 위해 이미지 내의 파일을 에지 노드 간에 공유하는 Peer-to-Peer 아키텍처에 기반을 둔 컨테이너 가속화 방법을 제시하고 단순화한 유량 모델을 통해 그 성능을 분석한다.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.20 no.8
• /
• pp.1-7
• /
• 2019

When using conventional 3D image scanning methods, it is common for image scanning to be done manually, which is labor-intensive. Scanning a space made up of complicated equipment or scanning a narrow space that is difficult for the user to enter, is problematic, resulting in quality degradation due to the presence of shadow areas. This paper proposes a method to scan an image using a rover equipped with a scanner in areas where it is difficult for a person to enter. To control the scan path precisely, the 3D image remote scan automation method based on the rover move rule definition is described. Through the study, the user can automate the 3D scan plan in a desired manner by defining the rover scan path as the rule base.

• Journal of Broadcast Engineering
• /
• v.24 no.1
• /
• pp.67-76
• /
• 2019

In this paper, we propose an efficient object classification method based on semantic segmentation for multi-labeled image data. In addition to various pixel unit information and processing techniques such as color information, contour, contrast, and saturation included in image data, a detailed region in which each object is located is extracted as a meaningful unit and the experiment is conducted to reflect the result in the inference. We use a neural network that has been proven to perform well in image classification to understand which object is located where image data containing various class objects are located. Based on these researches, we aim to provide artificial intelligence services that can classify real-time detailed areas of complex images containing various objects in the future.