• 한국HCI학회:학술대회논문집
• /
• 2007.02a
• /
• pp.1057-1062
• /
• 2007

얼굴표정 인식은 심리학 연구, 얼굴 애니메이션 합성, 로봇공학, HCI(Human Computer Interaction) 등 다양한 분야에서 중요성이 증가하고 있다. 얼굴표정은 사람의 감정 표현, 관심의 정도와 같은 사회적 상호작용에 있어서 중요한 정보를 제공한다. 얼굴표정 인식은 크게 정지영상을 이용한 방법과 동영상을 이용한 방법으로 나눌 수 있다. 정지영상을 이용할 경우에는 처리량이 적어 속도가 빠르다는 장점이 있지만 얼굴의 변화가 클 경우 매칭, 정합에 의한 인식이 어렵다는 단점이 있다. 동영상을 이용한 얼굴표정 인식 방법은 신경망, Optical Flow, HMM(Hidden Markov Models) 등의 방법을 이용하여 사용자의 표정 변화를 연속적으로 처리할 수 있어 실시간으로 컴퓨터와의 상호작용에 유용하다. 그러나 정지영상에 비해 처리량이 많고 학습이나 데이터베이스 구축을 위한 많은 데이터가 필요하다는 단점이 있다. 본 논문에서 제안하는 실시간 얼굴표정 인식 시스템은 얼굴영역 검출, 얼굴 특징 검출, 얼굴표정 분류, 아바타 제어의 네 가지 과정으로 구성된다. 웹캠을 통하여 입력된 얼굴영상에 대하여 정확한 얼굴영역을 검출하기 위하여 히스토그램 평활화와 참조 화이트(Reference White) 기법을 적용, HT 컬러모델과 PCA(Principle Component Analysis) 변환을 이용하여 얼굴영역을 검출한다. 검출된 얼굴영역에서 얼굴의 기하학적 정보를 이용하여 얼굴의 특징요소의 후보영역을 결정하고 각 특징점들에 대한 템플릿 매칭과 에지를 검출하여 얼굴표정 인식에 필요한 특징을 추출한다. 각각의 검출된 특징점들에 대하여 Optical Flow알고리즘을 적용한 움직임 정보로부터 특징 벡터를 획득한다. 이렇게 획득한 특징 벡터를 SVM(Support Vector Machine)을 이용하여 얼굴표정을 분류하였으며 추출된 얼굴의 특징에 의하여 인식된 얼굴표정을 아바타로 표현하였다.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2013.05a
• /
• pp.183-185
• /
• 2013

As mobile devices have developed, flash animations suitable for the existing web have solved part of the weakness caused by the image quality deterioration and the transmission capacity, but it is difficult to express 3D stereo-scopic images. Also, for the real time-randering of visual expressions for animation and the device technique for smartphone to accord with commercial demands, it is required to develop the 3D image processing technique. This paper studied on the image processing method for 3D animation capable of 3D graphic rendering with view system of android and OpenGL M3G in an embedded system device and OpenGL ES 2.0 library.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.34 no.2C
• /
• pp.186-193
• /
• 2009

Multi-view video is necessary to develop a new compression encoding technique for storage and transmission, because of a huge amount of data. Layered depth image is an efficient representation method of multi-view video data. This method makes a data structure that is synthesis of multi-view color and depth image. This paper proposed enhanced compression method by presentation of efficient layered depth image using real distance comparison, solution of overlap problem, and YCrCb color transformation. In experimental results, confirmed high compression performance and good reconstructed image.

• Journal of the Korea Society of Computer and Information
• /
• v.12 no.1 s.45
• /
• pp.67-72
• /
• 2007

In this paper, we present a construction method using perspective model which allows for the representation of the motion of a planar surface under perspective projection. The motion parameters are obtained by minimizing a disparity measure between the region in the current frame and the mapped region in the previous frame. The frames are constructed with dynamic panoramic image using a fixed reference or a time varying reference. By experiment, panoramic image proposed in this paper represents contents more efficiently than static image or video, and has a high volume reduction ratio.

• Journal of KIISE:Software and Applications
• /
• v.33 no.5
• /
• pp.481-488
• /
• 2006

The performance of face recognition methods using subspace projection is directly related to the characteristics of their basis images, especially in the cases of local distortion or partial occlusion. In order for a subspace projection method to be robust to local distortion and partial occlusion, the basis images generated by the method should exhibit a part-based local representation. We propose an effective part-based local representation method named locally salient ICA (LS-ICA) method for face recognition that is robust to local distortion and partial occlusion. The LS-ICA method only employs locally salient information from important facial parts in order to maximize the benefit of applying the idea of 'recognition by parts.' It creates part-based local basis images by imposing additional localization constraint in the process of computing ICA architecture I basis images. We have contrasted the LS-ICA method with other part-based representations such as LNMF (Localized Non-negative Matrix Factorization) and LFA (Local Feature Analysis). Experimental results show that the LS-ICA method performs better than PCA, ICA architecture I, ICA architectureII, LFA, and LNMF methods, especially in the cases of partial occlusions and local distortions.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.23 no.9
• /
• pp.1096-1103
• /
• 2019

Today the influence of digital video media grows bigger due to the development of information and telecommunication gradually and most of juveniles spend a number of image contents with their smart phones and computers. And they not only consume such image contents but also upload the videos they make at YouTube or Vimeo by recording and editing them by themselves. As we learned from such phenomenon, the education of media that uses and expresses the video in various environment such as making, reading and expressing video media is very important. The education of using the advance digital device and software of producing image contents is essential as current education of media cannot be discussed without that. This study treats the education of media based on the view point of education on image contents production. It discusses the education method that we can learn from the process of image contents production based on Non-Linear Editing System.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.20 no.3
• /
• pp.400-406
• /
• 2019

This study will explore the reenactment of visual special effects used in TV dramas. The subjects of the study are images that are reproduced in visual special effects through and . Accordingly, we looked at the changes in the way TV dramas were produced according to the times, and looked at the changes in the market. Also, we looked at cases of visual special effects of Korean dramas, and looked at expressions according to the degree of completion of visual special effects. For the purpose of the analysis of the research targets, the images of reproducibility and the flow through reality were analyzed. In the case of , the period setting is realistic, but visual special effects were used to maximize the actor's safety and expression, and in the case of , the visual effects were used to maximize the aesthetic of the period background. In addition, it can be seen that the visual special effects were used for the effect of PPL on the export of images. This shows that the emphasis of reality and image montage techniques are being used to pursue hyperrealism. It is now possible to actively express and use the beauty of TV dramas rather than technical limitations. In addition, the pursuit of realism can actively express the changing times of digital age. This is an active representation of the camera's angle, lighting, and perspective that coincides with the background. The environment of video production is crucial for realistic expressions. The study examined various visual directions and applications. In TV images, we looked at reproduction, which can make a natural period of time by combining. As a follow-up study, we are going to study the changes in the new quadratic image based on the present image representation.

• The KIPS Transactions:PartB
• /
• v.11B no.1
• /
• pp.1-6
• /
• 2004

Motion Information in a video clip often plays an important role in characterizing the content of the clip. A number of methods have been developed to analyze and retrieve video contents using motion information. However, most of these methods focused more on the analysis of direction or trajectory of motion but less on the analysis of the movement of an object. In this paper, we introduce the shape variation descriptor for describing shape variation caused by object movement along time, and propose a method to describe and retrieve the shape variation of the object using shape variation map. The experimental results shows that the proposed method performed much better than the previous method by l1％ and is very effective for describing the shape variation which is applicable to semantic retrieval applications.

• The Journal of the Korea Contents Association
• /
• v.22 no.4
• /
• pp.727-741
• /
• 2022

This article focused on contemporary American animation since the 1990s and later detailed clues to the theory that contemporary pop art style influenced contemporary American animation art creation expression and contemporary American animation. Knowing why American animation swept the world summarizes the art creation characteristics of modern American animation. After a combination of theoretical and actual animation works, the main manifestations of the postmodern pop art style in contemporary American animation: exaggerated and superficial shapes highlight character characteristics; rebellious colors reconstruct emotional perception; creation impacts the mass media-dependence; bizarre collage and repetition, embodying the postmodern pop spirit of jokes and spoofs, Etc. Through this, it is expected that the current analysis of American animation will provide new innovative ideas for domestic animation design and increase the competitiveness of domestic animation in international video animation.

• Proceedings of the Acoustical Society of Korea Conference
• /
• 1998.06e
• /
• pp.181-184
• /
• 1998

웨이브렛 변환은 신호나 영상을 분석하기 위한 다해상도 분해기법으로 사용되어 왔다. 웨이브렛 변환영역에서 신호는 스케일과 위치상의 크기로 표현된다. 이 변환영역에서는 신호나 영상의 주파수 성분들이 각각의 스케일에 따라서 분리되어 나타난다. 또한 각 변환영역은 신호나 영상의 공간적인 특성을 상당부분 포함하고 있다. 이러한 웨이브렛 변환의 특성은 푸리에 변화에 기초한 방법과는 달리, 에지와 잡음성분을 효과적으로 분리할 수 있는 정보를 우리에게 제공해 준다. 본 논문에서는 웨이브렛 변환영역의 각 스케일 특성과 공간적인 특성을 이용하여 영상의 잡음성분을 제거하였다. 잡음제거 기법의 성능평가를 위해 Wiener 필터링 방법과 비교하였다.