• Journal of Korea Society of Industrial Information Systems
• /
• v.24 no.5
• /
• pp.17-25
• /
• 2019

In this paper, we introduce the technology to convert a single human image into a fashion show animation video clip. The technology can help the customers confirm the dynamic fitting result when combined with the virtual try on technique as well as the interesting experience to a normal person of being a fashion model. We developed an extended technique of full human 2D to 3D inverse modeling based on SMPLify human body inverse modeling technique, and a rigged model animation method. The 3D shape deformation of the full human from the body model was performed by 2 part deformation in the image domain and reconstruction using the estimated depth information. The quality of resultant animation videos are made to be publically available for evaluation. We consider it is a promising approach for commercial application when supplemented with the post - processing technology such as image segmentation technique, mapping technique and restoration technique of obscured area.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.10 no.5
• /
• pp.871-876
• /
• 2006

In this thesis, to accurately measure 3D face information using the spatial encoding patterns, the new algorithm to segment the pattern images from initial face pattern image is proposed. If the obtained images is non-homogeneous texture and ambiguous boundary pattern, the pattern segmentation is very difficult. Furthermore. the non-encoded areas by accumulated error are occurred. In this thesis, the FCM(fuzzy c-means) clustering method is proposed to enhance the robust encoding and segmentation rate under non-homogeneous texture and ambiguous boundary pattern. The initial parameters for experiment such as clustering class number, maximum repetition number, and error tolerance are set with 2, 100, 0.0001 respectively. The proposed pattern segmentation method increased 8-20% segmentation rate with conventional binary segmentation methods.

• Journal of KIISE:Software and Applications
• /
• v.26 no.2
• /
• pp.273-283
• /
• 1999

래스터 지도에서 직선 또는 곡선과 중첩되어 있는 경우의 문자는 추출하기가 쉽지 않다. 따라서 본 논문에서는 고립되어 있는 문자뿐만 아니라 문자이외의 요소와 중첩되어 있는 문자도 효과적으로 추출할수 있는 분할 정복(divide and conquer) 개념에 기반한 문자 추출방법을 제시한다. 이를 위해 먼저 이미지의 연결 요소로부터 볼록다각형(convex hull)을 생성한다. 그리고 이 다각형이 충분한게 문자영역만을 포함할때가지 볼록 다각형을 이등분하면서 가장 긴 선분(투사 선분)을 기준으로 두 영역으로 분할한다. 다음으로 문자를 추출하기 위해서 이 선분을 기준으로 연결 요소상의 픽셀의 밀집도를 계산하는 알고리즘(프로파일링)을 적용한다. 또한 지도상에서 추출된 개별적인 문자들을 의미있는 단어들로 묶기(grouping)한 새로운 알고리즘을 소개한다. 특히 지도상에 나타나는 문자의 종류는 매우 다양하고 또한 이 문자들이 놓여있는 방향 역시 일정하지 않기 때문에 이러한 단어를 찾는 kd법은 쉽지 않다. 이를 위해 본 논문에서는 3차원 인접 그래프(3-D neighborhood graph)G를 소개한다. 이 그래프 G에서 각 노드는 하나의 분리된 문자를 나타내며 자신의 크기와 위치에 따라서 3차원 공간상에서 위치하게된다. 따라서, 크기가 큰 (작은)문자들은 보다 큰 (작은) z값을 가지고 되며 이 그래프 G에서 서로 인접한 노드들을 연결함으로써 지도상에 존재하는 서로 다른 종류의 문자 스트링을 추출할수 있다. 실험결과는 서로 다른 지도 이미지에 대해서 약 95% 이상의 단어 추출율을 보여준다.

• The Journal of the Convergence on Culture Technology
• /
• v.9 no.3
• /
• pp.825-834
• /
• 2023

The demands of people who purchase fashion products on Internet shopping are gradually increasing, and attempts are being made to provide user-friendly images with 3D contents and web 3D software instead of pictures and videos of products provided. As a reason for this issue, which has emerged as the most important aspect in the fashion web shopping industry, complaints that the product is different when the product is received and the image at the time of purchase has been heightened. As a way to solve this problem, various image processing technologies have been introduced, but there is a limit to the quality of 2D images. In this study, we proposed an automatic conversion technology that converts 2D images into 3D and grafts them to web 3D technology that allows customers to identify products in various locations and reduces the cost and calculation time required for conversion. We developed a system that shoots a mannequin by placing it on a rotating turntable using only 8 cameras. In order to extract only the clothing part from the image taken by this system, markers are removed using U-net, and an algorithm that extracts only the clothing area by identifying the color feature information of the background area and mannequin area is proposed. Using this algorithm, the time taken to extract only the clothes area after taking an image is 2.25 seconds per image, and it takes a total of 144 seconds (2 minutes and 4 seconds) when taking 64 images of one piece of clothing. It can extract 3D objects with very good performance compared to the system.

• The KIPS Transactions:PartD
• /
• v.14D no.3 s.113
• /
• pp.339-346
• /
• 2007

The objective of this study is to satisfy requirements for a variety of terminals to play wired web page contents in ubiquitous environment constantly connected to network. In other words, this study intended to automatically transcode wired web page into mobile web page in order to receive service by using mobile base to carry contents in Internet web page. To achieve this objective, we suggest the method that is to directly enter URL of web page in mobile device and to check contents of the current web page. For this, web page is converted into an image and configured into a mobile web page suitable for personal terminals. Users can obtain the effect of having web services provided by using computer with interfaces to expand, reduce and move the web page as desired. This is a caret unit play method, with which contents of web page are transcoded and played to suit each user According to the method proposed in this study, contents of wired web page can be played by using a mobile device. This study confirms that a single content can be serviced to suit users of various terminals. Through this, it will be able to reuse numerous wired web contents as mobile web contents.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.15 no.11
• /
• pp.2493-2499
• /
• 2011

With growth of nano-bio industry, it is of significant importance to develop an automated system to exploit cell behaviors, including migration, mitosis, apoptosis, shape deformation of individual cells and their interactions among cells in the process of cell growth. In this paper, we proposed preprocessing techniques, a classification method which classifies clusters (overlapping multiple cells) from cells and an automated method which counts the number of cells and clusters in order to analyze 2D or 3D deformations of the cells in the real-time images from microscope in the cell culture. We conducted the 3T3 cell images taken from each thirty-minute interval. It showed the average 99.8% accuracy automatically for separating cells and clusters.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2012.11a
• /
• pp.309-311
• /
• 2012

최근 데스크탑 가상화 서비스와 관련한 솔루션들이 많아지고 있다. 하지만, 이들 솔루션은 클라이언트의 수가 늘어날수록 서버의 부담이 커지며, 특히 3D 그래픽을 지원하는 고사양의 SW 를 지원하기 어려운 한계를 가지고 있다. 이러한 제약을 극복하기 위해 서버에서 데이터 집중적인 작업을 실행하고, 클라이언트 PC 에서는 그래픽 처리와 같은 사용자 인터페이스 작업을 분담하여 실행하는 서버 기반 그래픽 분할 실행 기술[4]이 제안되었다. 본 논문에서는 그래픽 분할 실행 기술을 개발하는데 있어 이미지 비트맵 관련 함수가 실행되었을 때 나타나는 비트맵 불일치 현상을 해결하기 위해 백업 비트맵을 이용한 가상 비트맵 관리 기법을 제안하여 궁극적으로 분할 실행 기술 개발을 지원하고자 한다.

• Proceedings of the Korean Information Science Society Conference
• /
• 2005.11b
• /
• pp.856-858
• /
• 2005

본 논문에서는 비디오 영상 및 이미지 시퀀스의 특징점 추적을 통해 얻은 2D 좌표를 분해기법을 사용하여 특징점에 대응되는 3D 좌표를 추정하는 방법을 제안한다. 3D 좌표를 복원함과 동시에 카메라의 위치와 방향을 계산하였다. 분해 기법에는 직교분해기법, 스케일된 직교분해기법, 근접 원근분해기법이 있다. 본 논문에서는 형상과 카메라 움직임을 계산하는 개선된 직교 분해 기법을 제안한다. 제안된 방법을 실 영상에 대해 실험한 결과 구조 및 카메라 파라메터 추정의 정확성이 개선되었다.

• Journal of Korea Society of Industrial Information Systems
• /
• v.7 no.4
• /
• pp.29-36
• /
• 2002

In this paper, a new edge detection method for area images is presented based on the scan-line image segmentation technology. The existing algorithms are lack of precision in its detections due to the noise factors such as depth perception and illumination problems when processing the 3D image into a 2D image. The general process of applying the scan-line method is to extract straight line components to determine the shape of the objects. However, we implement this method to an arc curve for precise detections. the paper proved precise detections that from off line to on line.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.18 no.6
• /
• pp.1321-1330
• /
• 2023

This study attempts to address the problem of 3D pose estimation for multiple human objects through a single image generated during the character development process that can be used in augmented reality. In the existing top-down method, all objects in the image are first detected, and then each is reconstructed independently. The problem is that inconsistent results may occur due to overlap or depth order mismatch between the reconstructed objects. The goal of this study is to solve these problems and develop a single network that provides consistent 3D reconstruction of all humans in a scene. Integrating a human body model based on the SMPL parametric system into a top-down framework became an important choice. Through this, two types of collision loss based on distance field and loss that considers depth order were introduced. The first loss prevents overlap between reconstructed people, and the second loss adjusts the depth ordering of people to render occlusion inference and annotated instance segmentation consistently. This method allows depth information to be provided to the network without explicit 3D annotation of the image. Experimental results show that this study's methodology performs better than existing methods on standard 3D pose benchmarks, and the proposed losses enable more consistent reconstruction from natural images.