• Proceedings of the Korean Information Science Society Conference
• /
• 1999.10b
• /
• pp.622-624
• /
• 1999

모핑 애니메이션은 컴퓨터 그래픽스 및 많은 응용에서 이용되고 있다. 모핑 애니메이션에서는 대부분 이미지들을 동영상 편집기 등을 이용하므로 많은 저장 공간을 필요로 한다. 본 논문에서는 이를 해결하는 한 방법으로 프랙탈 기법을 사용한다. 예를 보이기 위해 두 개의 나무 모핑 애니메이션을 보인다.

• Proceedings of the Korea Contents Association Conference
• /
• 2008.05a
• /
• pp.3-9
• /
• 2008

This paper is related to hair-blending for 2D virtual color hairstyler based on the semi-automatic field morphing. The proposed 2D virtual color hair-styler is characterized as generating virtual hairstyles using the variable morphing mask instead of the fixed one for the semi-automatic morphing, and then hair-blending the generated virtual hairstyles using sigmoid function around the boundary region of the variable morphing mask. The proposed method is able to generate the virtual hairstyles with an easy-to-use interface based on semi-automatic field morphing. According to the proposed method, a user can shorten the working time and even an unskilled user can obtain natural hairstyles as he or she designates a small number of external user inputs.

• Journal of the Korea Computer Graphics Society
• /
• v.20 no.2
• /
• pp.13-24
• /
• 2014

In this study, a graphics-processing-unit (GPU)-based acceleration technique is proposed for the feature-based image morphing. This technique uses the depth-buffer of the graphics hardware to calculate efficiently the shortest distance between a pixel and the control lines. The pairs of control lines between the source image and the destination image are determined by user's input, and the distance function of each control line is rendered using two rectangles and two cones. The distance between each pixel and its nearest control line is stored in the depth buffer through the graphics pipeline, and this is used to conduct the morphing operation efficiently. The pixel-unit morphing operation is parallelized using the compute unified device architecture (CUDA) to reduce the morphing time. We demonstrate the efficiency of the proposed technique using several experimental results.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2003.05a
• /
• pp.161-164
• /
• 2003

A study on the gray images morphing using morphology and spline interpolation is realized. The adapted method is that join the 2 broken line together with the dilation of morphology to the morphing image, remove the holes to be a soft edge at the image boundaries and extract the featuring points with the cubic spline interpolation. As a result of experiment the method elicits more smoothing image morphing in detail and speed up the interframe processing.

• Proceedings of the Korean Information Science Society Conference
• /
• 2007.10b
• /
• pp.217-220
• /
• 2007

본 논문에서는 MPEG-4에서 정의하는 FDP(Facial Definition Parameter)를 이용하여 사람의 3차원 얼굴모델들을 모핑(Morphing)시키는 알고리즘을 기술한다. 3 차원 스캐너로 생성한 얼굴 모델에 MPEG-4 의 FDP 를 기반으로 얼굴의 특징을 구분하는 영역들을 정의한다. 얼굴 모핑 알고리즘은 서로 다른 얼굴 모델 사이에서 이러한 얼굴 특징 영역들간의 변형을 생성하기 위한 일련의 과정을 설명한다. 특징 영역간의 얼굴 모핑을 위해서는 서로 다른 얼굴 모델의 기하 데이터와 속성들을 매핑시켜야 하는 문제가 생긴다. 이를 위해 본 연구에서는 구를 이용하여 각 얼굴 모델의 기하와 속성 정보를 정의하여 매핑한 후에 이들간을 모핑하는 방법을 정의하였다.

• Proceedings of the Korea Multimedia Society Conference
• /
• 2004.05a
• /
• pp.232-237
• /
• 2004

영상 워핑 및 모핑은 영상 안에서 각 화소들 사이의 공간적인 관계를 재구성하는 영상처리와 컴퓨터 그래픽스 기술이 결합된 분야로서 메쉬 방식과 필드 방식 둥이 대표적이다. 이중에서 필드 방식은 상대적으로 많은 연산량을 요구하는 것에 반해 제어선 설정이 용이하며 설정된 제어선의 위치나 길이의 변화에 대해 비교적 덜 민감하다는 장점이 있다. 필드 방식은 사용자가 제어선을 지정하는 과정의 대부분을 수작업에 의존하기 때문에 작업 시간이 많이 소요될 뿐만 아니라 양질의 결과를 얻기 위해서는 숙련을 요하는 불편함이 있다. 본 논문은 소스 영상과 목표 영상에서 워핑 대상체 쌍의 형상 정보를 획득한 상태에서 사용자가 수동으로 최소한의 특징점 쌍만을 지정하면 이렇게 지정된 특징점 쌍을 기준 삼아 다각형 기반 정점 탐색에 의해 소스 영상과 목표 영상에 상호 대응되는 제어선들을 자동적으로 설정한 후, 제어선 길이의 비율과 제어선으로부터의 이격 거리를 이용하여 영상 워핑과 모핑을 수행함으로써 영상 워핑 및 모핑의 반자동화를 실현할 수 있는 방법을 제안한다. 제안된 방법에 따르면, 사용자가 제어선을 설정하는 시간을 단축할 수 있고 비숙련자도 최소의 제어선만을 지정하여 자연스러운 워핑 및 모핑의 결과를 획득할 수 있는 이점이 있다.

• Journal of Digital Contents Society
• /
• v.5 no.4
• /
• pp.269-274
• /
• 2004

The field based morping requires the user to set most of the control lines manually which require much time and skill to get satisfactory results. This tjesis proposes a method to acquire semi-automation of image morphing through first acquiring shape information from the source image and the target image, than after the user manually designates the least amount of a pair of feature points, these are used as standards for polygon based vertex to set the appropriate control line to the source image and target image, and then using the ratio of control line lengths and space. Using the proposed method the user can reduce the time setting the control line and unskilled persons can get natural image morphing results while desingnating the least amount of control line.

• The KIPS Transactions:PartA
• /
• v.17A no.6
• /
• pp.281-288
• /
• 2010

In this paper, we describe the development of a system for generating a 3-dimensional human face using 3D scanned facial data and photo images, and morphing animation. The system comprises a facial feature input tool, a 3-dimensional texture mapping interface, and a 3-dimensional facial morphing interface. The facial feature input tool supports texture mapping and morphing animation - facial morphing areas between two facial models are defined by inputting facial feature points interactively. The texture mapping is done first by means of three photo images - a front and two side images - of a face model. The morphing interface allows for the generation of a morphing animation between corresponding areas of two facial models after texture mapping. This system allows users to interactively generate morphing animations between two facial models, without programming, using 3D scanned facial data and photo images.

• Journal of KIISE:Computer Systems and Theory
• /
• v.36 no.4
• /
• pp.311-325
• /
• 2009

This paper presents a method for analyzing Hangul glyphs with their outline fonts and obtaining intermediate fonts with two different fonts. The glyphs are represented and analyzed hierarchically such as characters, components(letters) and strokes. With the analysis results, we obtain several intermediate glyphs by morphing two different glyphs of same character. For a natural glyph contour morphing, we employ the curve morphing algorithm by weighted mean of strings. In addition, we provide four operations for transformation of glyphs with different topology. As a result, it is illustrated that the proposed Hangul glyphs morphing scheme is useful for new font generation from any exist fonts or handwritings.

• Proceedings of the Korea Contents Association Conference
• /
• 2004.05a
• /
• pp.377-384
• /
• 2004

The field based morphing requires the user to set most of the control lines manually which requires much time and skill to get satisfactory results. This thesis proposes a method to acquire semi-automation of image morphing through first acquiring shape information from the source image and the target image, then after the user manually designates the least amount of a pair of feature points, these are used as standards for polygon based vertex search to set the appropriate control line to the source mage and target image, and then using the ratio of control line lengths and space. Using the proposed method, the user can reduce the time setting the control line and unskilled persons can get natural image morphing results while designating the least amount control line.