• Journal of the Korea Computer Graphics Society
• /
• v.8 no.3
• /
• pp.9-16
• /
• 2002

Recently, high dynamic range (HDR) compression has attracted much attention due to the wide availability of HDR images. In this paper, we present an HDR compression method using a progressive image, which is a multi-level image representation based on a progressive mesh. An HDR image can be decomposed into a base image and a sequence of details by conversion into a progressive image. This decomposition provides a good structure to highly compress the dynamic range while preserving image details. The base image and larger details are considerably scaled down but smaller details are slightly scaled down. Experimental results show that our method successfully generates HDR compressed images without halo artifacts by controlling two intuitive parameters.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.23 no.6
• /
• pp.682-689
• /
• 2019

In part-based image representation, the partial shapes of an object are represented as basis vectors, and an image is decomposed as a linear combination of basis vectors where the coefficients of those basis vectors represent the partial (or local) feature of an object. In this paper, a face recognition for occluded faces is proposed in which face images are represented using non-negative matrix factorization(NMF), one of part-based representation techniques, and recognized using an artificial neural network technique. Standard NMF, projected gradient NMF and orthogonal NMF were used in part-based representation of face images, and their performances were compared. Learning vector quantizer were used in the recognizer where Euclidean distance was used as the distance measure. Experimental results show that proposed recognition is more robust than the conventional face recognition for the occluded faces.

• Cartoon and Animation Studies
• /
• s.34
• /
• pp.1-22
• /
• 2014

The purpose of this research is to study a case of allegory and experimental presentation technique in Film by Zbigniew Rybczynski. It is to analyse this study is to inquire into the fact that experimental animation carries diverse interpretation of comtemporary art and the purpose of this study is to identify certain style through the interpretation of allegory focused on film Tango which has expanded the field of experimental animation with the unique form of the film structure and technique. Therefore, in this research, I would highlight the characteristic of allegory in Film by Zbigniew Rybczynski and research the experimental presentation technique that appears in experimental animation focused on "fragmentation" which are the expressive style of allegory.

• Journal of Science of Art and Design
• /
• v.8
• /
• pp.45-61
• /
• 2005

The 2D animation screen is a screen work that is produced on the plane. So, it is superficial in terms of space. Therefore, we expressed via picture technique that uses the movement of camera and back-ground in order to recreate the image of realistic feeling that has multiple effect. Though all multiple-effects were expressed realistically in the early Disney animation of the United States, Japan used the expression of Follow Pan profoundly to provide the animation with economic expression of picture and the depthof screen in order to realize a new technical expression of limited animation while it was producing TV series works in 1960s. Now it is positively expressed even in the United States, too. This study tries to analyze the example that applied the long piece works of Japan which was expressed via the Follow Pan, that is, the movement of camera, to the real approach.

• Proceedings of the IEEK Conference
• /
• 2000.09a
• /
• pp.359-362
• /
• 2000

본 논문에서는 비디오 영상에서 지역적 움직임 특성을 표현할 수 있는 지역적 움직임 활동(motion activity)에 관한 기술자(descriptor)를 제안한다. 제안된 방법은 화면 전체에 대해 지역적으로 높은 움직임 활동 정도를 갖는 영역에 대한 공간적 정보를 기술하고, 카메라 움직임에 무관하게 물체의 움직임 활동 특성을 정확히 표현하기 위해 움직임 벡터의 통계적 특성과 화면 분할을 이용한다 본 논문에서 제안하는 움직임 활동의 공간적 특성을 이용하면 동영상에서 화면의 일부에서 일어나는 움직임을 이용한 검색이 가능하고, 물체 추적, 감시 시스템에서도 활용이 가능하다. 실험으로 제안한 방법을 이용해서 움직임 활동이 높은 영역의 추출과정을 보이고, 이를 이용한 검색 결과를 보인다.

• Proceedings of the Korea Multimedia Society Conference
• /
• 2003.11b
• /
• pp.581-584
• /
• 2003

본 연구는 인공생명의 알고리즘을 응용해서 기존 영상작품과 엔터테인먼트(컴퓨터 게임)와는 전혀 다른 형태의 작품을 구현 하는데 그 목적이 있다 기존의 영상작품과 엔터테인먼트는 제한된 상호 작용성(기존 영상작품이나 컴퓨터 게임은 장면의 진행과 시나리오가 정해진 틀에서만 표현된다)을 갖는데, 인공생명 알고리즘을 응용한 작품은 무한한 상호 작용성(interactivity)을 표현할 수 있다. 본 연구는 인공생명 알고리즘 L-system을 응용해 우리 전통미술인 사군자와 인공적으로 진화하는 수족관속의 물고기를 인 실리코(컴퓨터 속의 세계)에서 구현 하였다. 사군자는 여백을 클릭할 때마다 성장과 소멸하면서 무한히 변형된 형태의 모습을 창조하고, 수족관속의 포식자 피기는 눈이 커지는 것, 꼬리가 길어지는 것, 지느러미가 커지는 것으로 진화 한다.

• Proceedings of the Korean Information Science Society Conference
• /
• 2003.10b
• /
• pp.511-513
• /
• 2003

본 연구는 인공생명의 알고리즘을 응용해서 기존 영상작품과 엔터테인먼트(컴퓨터 게임)와는 전혀 다른 형태의 작품을 구현하는데 그 목적이 있다. 기존의 영상작품과 엔터테인먼트는 제한된 상호 작용성(기존 영상작품이나 컴퓨터 게임은 장면의 진행과 시나리오가 정해진 틀에서만 표현된다)을 갖는데, 인공생명 알고리즘을 응용한 작품은 무한한 상호 작용성(interactivity)을 표현할 수 있다. 본 연구는 인공생명 알고리즘 L-system을 응용해 우리 전통미술인 사군자를 인 실리코(컴퓨터 속의 세계)에서 구현 하였다 이 사군자는 여백을 클릭할 때마다 성장과 소멸하면서 무한히 변형된 형태의 모습을 창조한다.

• Journal of the Korea Society of Computer and Information
• /
• v.10 no.1 s.33
• /
• pp.73-84
• /
• 2005

An increasing in quantity of multimedia data brought a new problem that expected data should be retrieved fast and exactly. The adequate representation is a key element for the efficient retrieval For this reason, the MPEG-7 standard was established for description of multimedia contents in 2001. Recently, the new metadata were developed to represent characteristics of movie information resources by Korea Federation of Film Archives. In this paper. we designed and implemented a movie information retrieval system. This system used XML schema to accept movie information metada. This system offers a keyword retrieval using high-level metadata based on movie information and similarity retrieval using low-level metadata based on MPEG-7. As a result, that ill be Possible more efficient movie information interchange . movie information metadata reuse and fast retrieve.

• Journal of the Korean Society of Radiology
• /
• v.81 no.3
• /
• pp.632-643
• /
• 2020

Purpose To investigate the correlation between magnetic resonance (MR) image-based radiomics features and the genomic features of breast cancer by focusing on biomolecular intrinsic subtypes and gene expression profiles based on risk scores. Materials and Methods We used the publicly available datasets from the Cancer Genome Atlas and the Cancer Imaging Archive to extract the radiomics features of 122 breast cancers on MR images. Furthermore, PAM50 intrinsic subtypes were classified and their risk scores were determined from gene expression profiles. The relationship between radiomics features and biomolecular characteristics was analyzed. A penalized generalized regression analysis was performed to build prediction models. Results The PAM50 subtype demonstrated a statistically significant association with the maximum 2D diameter (p = 0.0189), degree of correlation (p = 0.0386), and inverse difference moment normalized (p = 0.0337). Among risk score systems, GGI and GENE70 shared 8 correlated radiomic features (p = 0.0008-0.0492) that were statistically significant. Although the maximum 2D diameter was most significantly correlated to both score systems (p = 0.0139, and p = 0.0008), the overall degree of correlation of the prediction models was weak with the highest correlation coefficient of GENE70 being 0.2171. Conclusion Maximum 2D diameter, degree of correlation, and inverse difference moment normalized demonstrated significant relationships with the PAM50 intrinsic subtypes along with gene expression profile-based risk scores such as GENE70, despite weak correlations.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2023.05a
• /
• pp.507-509
• /
• 2023

최근 딥러닝은 도로 CCTV 동영상의 교통사고 검출에 널리 사용되지만 일인칭 동영상의 교통사고 검출은 분명히 어렵다. 일인칭 동영상은 역동적이고 시야가 제한되어 있기 때문이다. 본 논문에서는 일인칭 동영상을 분석하여 교통사고를 검출하는 방법을 제시한다. 이 방법은 교통 표현 특성을 분석하는 것 외에도 의미를 이해하고 교통 장면을 인코딩한다. 프레임의 표현 특징은 각 프레임 상의 물체의 특징과 물체의 위치 관계의 공간적 숨겨진 특진을 학습함으로써 얻어진다. 그 후에 프레임 표현 특징과 교통 장면의 특징이 연결되어 GRU 실행기에 공급된다. 여러 GRU 실행기는 분석한 후 사고가 발생했는지 확인된다. 이 방법은 높은 역학과 제한된 시야 문제를 효과적으로 해결한다.