• 한국멀티미디어학회논문지
• /
• 제9권5호
• /
• pp.529-541
• /
• 2006

본 논문에서는 객체기반 비디오 부호화 또는 멀티미디어 편집을 위한 반지동 비디오 객체 분할방식을 제안한다. 반자동 객체분할은 사용자 지원에 의한 분할 방식으로, 비디오 시퀀스의 초기 프레임에서 사용자가 관심객체의 경계를 표시하고 이후의 영상 프레임의 객체를 배경으로부터 연속적으로 분리해 낸다. 제안된 방식은 부분적으로 사용자 조력에 의한 프레임내 분할과 완전 자동에 의한 프레임간 분할 처리과정으로 구성되는데, 영상 전체에 대해 연산을 수행하는 기존 방식과는 달리 객체 경계가 존재하는 영상영역 부분에서만 연산을 수행한다. 프레임내 분할은 사용자가 관심객체의 경계를 지정하고, 이 경계 주위 화소들의 유사성을 이용한 후처리에 의해 정확한 초기 객체를 구한다. 프레임간 분할에서는 이전 프레임에서 추출한 객체의 경계 정보에 근거하여 시간적 유사성을 구한 후 경계와 영역 추적에 의해 연속적으로 동영상 객체를 추출한다. 실험결과로부터 제안된 방식은 비디오 편집, 객체기반 비디오 압축 및 인덱싱 등의 멀미디어 응용에 사용 가능할 정도로 안정되고 정확한 객체추출을 수행함을 확인하였다. 이 결과를 바탕으로 다수의 편리한 기능을 포함한 비디오 편집시스템을 개발하였다.

• 대한임베디드공학회논문지
• /
• 제18권6호
• /
• pp.267-275
• /
• 2023

This paper presents the development of specialized software for annotating volume-of-interest on ¹⁸F-FDG PET/CT images with the goal of facilitating the studies and diagnosis of head and neck cancer (HNC). To achieve an efficient annotation process, we employed the SE-Norm-Residual Layer-based U-Net model. This model exhibited outstanding proficiency to segment cancerous regions within ¹⁸F-FDG PET/CT scans of HNC cases. Manual annotation function was also integrated, allowing researchers and clinicians to validate and refine annotations based on dataset characteristics. Workspace has a display with fusion of both PET and CT images, providing enhance user convenience through simultaneous visualization. The performance of deeplearning model was validated using a Hecktor 2021 dataset, and subsequently developed semi-automatic annotation functionalities. We began by performing image preprocessing including resampling, normalization, and co-registration, followed by an evaluation of the deep learning model performance. This model was integrated into the software, serving as an initial automatic segmentation step. Users can manually refine pre-segmented regions to correct false positives and false negatives. Annotation images are subsequently saved along with their corresponding ¹⁸F-FDG PET/CT fusion images, enabling their application across various domains. In this study, we developed a semi-automatic annotation software designed for efficiently generating annotated lesion images, with applications in HNC research and diagnosis. The findings indicated that this software surpasses conventional tools, particularly in the context of HNC-specific annotation with ¹⁸F-FDG PET/CT data. Consequently, developed software offers a robust solution for producing annotated datasets, driving advances in the studies and diagnosis of HNC.

• 한국정밀공학회:학술대회논문집
• /
• 한국정밀공학회 2002년도 추계학술대회 논문집
• /
• pp.119-122
• /
• 2002

Collimators were mostly produced by handwork and semi-automatic system in some companies. Under this situation, automatic manufacturing system for optical collimators is on the rise most essential technique in the development of optical communication components. In this study, automatic manufacturing system was designed and constructed to develop optical collimators with high functionality. Also optical collimators were manufactured using a developed automatic system. We have compared collimators made by automatic system and handwork fer performance test with a measured values of angle alignment, beam size and TIL. As a result, it brought a reduction of the tact time fur manufacturing and improvement of an efficiency of optical collimators, and then it was found that automatic system was indispensable for materialization of optical collimators with high functionality.

• 정보처리학회논문지:소프트웨어 및 데이터공학
• /
• 제11권10호
• /
• pp.409-418
• /
• 2022

본 논문에서는 연주자 자세의 그라운드 트루스 획득을 위한 반자동 주석 방법인 SAAnnot-C3Pap를 제안한다. 기존 음악 도메인에서 2차원 관절 위치에 대한 그라운드 트루스를 획득하기 위하여 2차원 자세 추정 방법인 오픈포즈를 활용하거나 수작업으로 라벨링 하였다. 하지만 기존의 오픈포즈와 같은 자동 주석 방법은 빠르지만 부정확한 결과를 보인다는 단점이 있고, 사용자가 직접 주석을 생성하는 수작업 주석화의 경우 많은 노동력이 필요하다는 한계점이 있다. 따라서 본 논문에서는 그 둘의 절충 방안인 반자동 주석화 방법인 SAAnnot-C3Pap을 제안한다. 제안하는 SAAnnot-C3Pap은 크게 3가지 과정으로 오픈포즈를 사용하여 자세를 추출하고, 추출된 부분 중 오류가 있는 부분을 슈퍼바이즐리를 사용하여 수정한 뒤, 오픈포즈와 슈퍼바이즐리의 결과값을 동기화하는 과정을 수행한다. 제안하는 방법을 통하여 오픈포즈에서 발생하는 잘못된 2차원 관절 위치 검출 결과를 교정할 수 있었고, 2명 이상의 사람을 검출하는 문제를 해결하였으며, 연주 자세 그라운드 트루스 획득이 가능하였다. 실험에서는 반자동 주석 방법인 오픈포즈와 본 논문에서 제안하는 SAAnnot-C3Pap의 결과를 비교·분석한다. 비교 결과, 제안하는 SAAnnot-C3Pap는 오픈포즈로 잘못 수집된 자세 정보를 개선한 결과를 보였다.

• 연구논문집
• /
• 통권32호
• /
• pp.23-34
• /
• 2002

Up to now, collimators have teen generally produced by handwork and only a few companies have produced by semi-automatic system. Under this situation, automatic system for assembly of optical collimators has risen as a mast essential technique in the development of optical communication components. In this study, it was constructed to develop optical collimators with high functionality and we manufactured optical collimators with a GRIN rod lens and spherical lens using automatic system. Therefore, we worked a performance test through a comparison of collimators made by automatic system and handwork with angle augment, bean size. Also we selected a optimum assembly condition of GRIN rod lens and spherical lens. As a result, it brought a reduction of the tact time and an improvement of an efficiency and a productivity of optical collimators, therefore it was found that automatic system was indispensable for materialization of optical collimators with high functionality.

• 소성∙가공
• /
• 제11권7호
• /
• pp.589-595
• /
• 2002

Up to now, Collimators have been generally produced by handwork and only a few companies have produced by semi-automatic system. Under this situation, automatic system for assembly of optical collimator has risen as a most essential technique in the development of optical communication components. In this study, it was constructed to develop optical collimators with high functionality and We manufactured optical collimators with a GRIN rod lens using automatic system. Therefore, we worked a performance test through a comparison of collimators made by automatic system and handwork with angle alignment, beam size. Also we compared common product with auto-manufactured sample. As a result, it brought a reduction of the tact time and an improvement of an efficiency and a productivity of optical collimators. therefore it was found that automatic system was indispensable for materialization of optical collimators with high functionality.

• 한국컴퓨터정보학회논문지
• /
• 제11권4호
• /
• pp.283-289
• /
• 2006

현재 영상분할은 사용자가 원하는 영상을 분할하고, 분할된 객체에 다른 영상을 합성하는 기술에 대해 많은 연구가 진행되어왔다. 본 논문에서는 점진적 영역병합과 유전자 알고리즘을 이용하여 새로운 반자동 영상 분할방법을 제안하였다. 제안된 알고리즘은 사용자가 원하는 객체를 선정한 후, 유전자 알고리즘을 이용해 객체의 경계를 검색한다. 검색된 경계를 기반으로 분수령 알고리즘을 이용하여 사용자가 원하는 객체의 영역을 분할하였다. 분할된 객체에서 불명확한 영역들을 점진적 영역 병합으로 배경과 객체를 분리하였다. 그리고, 알고리즘 개발을 효과적으로 수행하기 위해 GUI기반의 인터페이스를 만들어 사용자가 원하는 값을 적용할 수 있게 하였다. 실험에서는 제한된 방법의 우수성 입증을 위하여 다양한 영상을 분석하였다.

• 한국감성과학회:학술대회논문집
• /
• 한국감성과학회 2000년도 춘계 학술대회 및 국제 감성공학 심포지움 논문집 Proceeding of the 2000 Spring Conference of KOSES and International Sensibility Ergonomics Symposium
• /
• pp.120-125
• /
• 2000

We propose a semi-automatic and dynamic indexing algorithm for multi-media database(e.g. movie files, audio files), which are difficult to create indexes expressing their emotional or abstract contents, according to user's sensitivity by using user's histories of access to database. In this algorithm, we simply categorize data at first, create a vector space of each user's interest(user model) from the history of which categories the data belong to, and create vector space of each data(title model) from the history of which users the data had been accessed from. By continuing the above method, we could create suitable indexes, which show emotional content of each data. In this paper, we define the recurrence formulas based on the proposed algorithm. We also show the effectiveness of the algorithm by simulation result.

• Journal of Computing Science and Engineering
• /
• 제5권2호
• /
• pp.150-160
• /
• 2011

Automatic text classification has a long history and many studies have been conducted in this field. In particular, many machine learning algorithms and information retrieval techniques have been applied to text classification tasks. Even though much technical progress has been made in text classification, there is still room for improvement in text classification. In this paper, we will discuss remaining issues in improving text classification. In this paper, three improvement issues are presented including automatic training data generation, noisy data treatment and term weighting and indexing, and four actual studies and their empirical results for those issues are introduced. First, the semi-supervised learning technique is applied to text classification to efficiently create training data. For effective noisy data treatment, a noisy data reduction method and a robust text classifier from noisy data are developed as a solution. Finally, the term weighting and indexing technique is revised by reflecting the importance of sentences into term weight calculation using summarization techniques.

• 대한원격탐사학회:학술대회논문집
• /
• 대한원격탐사학회 2006년도 Proceedings of ISRS 2006 PORSEC Volume II
• /
• pp.606-609
• /
• 2006

Extraction of building is one of essential issues for the 3D city models generation. In recent years, high-resolution satellite imagery has become widely available, and this shows an opportunity for the urban mapping. In this paper, we have developed a semi-automatic algorithm to extract 3D buildings in urban settlements areas from high-spatial resolution panchromatic imagery. The proposed algorithm determines building height interactively by projecting shadow regions for a given building height onto image space and by adjusting the building height until the shadow region and actual shadow in the image match. Proposed algorithm is tested with IKONOS images over Deajeon city and the algorithm showed promising results.┌阀؀䭏佈䉌ᔀ鳪떭臬隑駭验耀