• KIPS Transactions on Software and Data Engineering
• /
• v.11 no.10
• /
• pp.409-418
• /
• 2022

In this paper, we propose SAAnnot-C3Pap, a semi-automatic annotation method for obtaining ground truth of a player's posture. In order to obtain ground truth about the two-dimensional joint position in the existing music domain, openpose, a two-dimensional posture estimation method, was used or manually labeled. However, automatic annotation methods such as the existing openpose have the disadvantages of showing inaccurate results even though they are fast. Therefore, this paper proposes SAAnnot-C3Pap, a semi-automated annotation method that is a compromise between the two. The proposed approach consists of three main steps: extracting postures using openpose, correcting the parts with errors among the extracted parts using supervisely, and then analyzing the results of openpose and supervisely. Perform the synchronization process. Through the proposed method, it was possible to correct the incorrect 2D joint position detection result that occurred in the openpose, solve the problem of detecting two or more people, and obtain the ground truth in the playing posture. In the experiment, we compare and analyze the results of the semi-automated annotation method openpose and the SAAnnot-C3Pap proposed in this paper. As a result of comparison, the proposed method showed improvement of posture information incorrectly collected through openpose.

• Journal of the Korean Society for Library and Information Science
• /
• v.57 no.1
• /
• pp.93-114
• /
• 2023

Information extraction can facilitate the intensive analysis of documents by providing semantic triples which consist of named entities and their relations recognized in the texts. However, most of the research so far has been carried out separately for named entity recognition and relation extraction as individual studies, and as a result, the effective performance evaluation of the entire information extraction systems was not performed properly. This paper introduces two models of end-to-end information extraction that can extract various entity names in clinical records and their relationships in the form of semantic triples, namely pipeline and joint models and compares their performances in depth. The pipeline model consists of an entity recognition sub-system based on bidirectional GRU-CRFs and a relation extraction module using multiple encoding scheme, whereas the joint model was implemented with a single bidirectional GRU-CRFs equipped with multi-head labeling method. In the experiments using i2b2/VA 2010, the performance of the pipeline model was 5.5% (F-measure) higher. In addition, through a comparative experiment with existing state-of-the-art systems using large-scale neural language models and manually constructed features, the objective performance level of the end-to-end models implemented in this paper could be identified properly.

• Journal of Internet Computing and Services
• /
• v.14 no.3
• /
• pp.81-90
• /
• 2013

Mobile device can get useful user information, because users have always this device. In this paper, we propose automatically story generation method and user topic extraction using user information in mobile environment. Proposed method is follows: (1) We collect user action information in mobile device. Then, (2) we extract topics from collected information. (3) For the results of (2), we determine episodes for one day. Then, (4) we generate sentences using sentence templates and we compose stories which have theme-based or time-based. Because proposed method is simpler than previous method, proposed method can work only in mobile device. There's no room to leak user information. And proposed method is expressed more informative than previous method, because proposed method is provided sentence-based result. Extracted user-topic, a result of our method, can use to analyze user action and user preference.

• Journal of Korea Multimedia Society
• /
• v.12 no.9
• /
• pp.1217-1232
• /
• 2009

In this paper, we propose a semi-automatic 3D building reconstruction method using uncalibrated images which includes the facade of target building. First, we extract feature points in all images and find corresponding points between each pair of images. Second, we extract lines on each image and estimate the vanishing points. Extracted lines are grouped with respect to their corresponding vanishing points. The adjacency graph is used to organize the image sequence based on the number of corresponding points between image pairs and camera calibration is performed. The initial solid model can be generated by some user interactions using grouped lines and camera pose information. From initial solid model, a detailed building model is reconstructed by a combination of predefined basic Euler operators on half-edge data structure. Automatically computed geometric information is visualized to help user's interaction during the detail modeling process. The proposed system allow the user to get a 3D building model with less user interaction by augmenting various automatically generated geometric information.

• Journal of Internet Computing and Services
• /
• v.5 no.1
• /
• pp.1-13
• /
• 2004

The effect of Application system with class units is not sufficient because of independency and reuse of Component elements due to component abstraction based on only source code. Therefore We need to apply design pattern approach to represent not only the problem abstraction but also information and relationship between system elements for generic solutions of specific domain, Also, it is essential to software reverse engineering acquiring the correct understandings of the system through examining the existing systems and utilizing the acquired knowledges as reusable resources. In this paper, the extraction algorithm with JAVA and the validity of applying reverse engineering with extracting design patterns from source codes of the existing object-oriented system; are devised. The architecture of automatic tool is designed and implemented for 1) automatic extraction of design patterns and 2) reuse tool for retrieving, editing and rebuilding of design patterns.

• Annual Conference on Human and Language Technology
• /
• 2009.10a
• /
• pp.101-105
• /
• 2009

본 논문은 공통적으로 이용할 수 있는 웹 환경에서의 한국어 정보로 획득할 수 있는 정보의 양이 영어권 정보의 양보다 상대적으로 적다는 것을 토대로, 웹정보 이용의 불균형을 해소하고자 하는 목적으로부터 출발하였다. 최근에는 지식 정보의 세계화, 국제화에 따라 동일한 정보를 각국 언어로 제공하고자하는 연구가 꾸준히 증가하고 있다. 온라인 백과사전인 위키피디아 역시 현재 다국어로 제공이 되고 있지만 한국어로 작성된 문서는 영어로 작성된 문서의 5% 미만인 것으로 조사되었다. 본 논문에서는 위키피디아 내에서 제공하는 다국어간의 링크 정보와 인포박스 데이터를 활용하여 위키피디아 문서 내에서 개체명을 인식하고, 자동으로 개체명의 영-한 대역어 쌍을 추출하는 것을 목표로 한다. 개체명은 일반 사전에 등재 되지 않은 경우가 많기 때문에, 기계번역에서 사전 데이터 등을 활용하여 개체명을 처리하는 것은 쉽지 않으며 일반적으로 음차표기 방식을 함께 사용하여 해결하고 있다. 본 논문을 통해 위키피디아 데이터를 활용해 만들어진 영-한 개체명 대역어 사전을 구축하기 위해 사용된 기술은 추후 위키피디아 문서를 기계번역하는데 있어 동일한 방법으로 사용이 가능하며, 구축된 사전 데이터는 추후 영-한 자동 음차표기 연구의 사전 데이터로도 활용이 가능하다.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.5 no.3
• /
• pp.321-326
• /
• 2010

A method that can decide the existence and the severeness of flaws in ceramic materials through the use of non-destructive testing by image processing techniques, is proposed in this paper. The edges of the acquired image are first extracted using Sobel mask and the regions of the image are clustered using another mask after that. Histogram stretching is applied to each of the regions to enhance the image region-wise and objects are extracted by an edge following algorithm. Morphological information is incorporated to remove noise and detect flawed regions. The proposed method can detect flaws in the acquired images and the experimental results also supports that.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2020.01a
• /
• pp.231-233
• /
• 2020

최근 360도 형태로 영상을 촬영하고 제공하는 경우가 많아 일반적인 동영상과 달리 360도 형태의 영상저작물에 적절하고 효과적인 방법으로 광고를 삽입하여 노출 시킬 수 있는 방법이 필요하게 되었다. 따라서 본 논문에서는 실감형 360도 영상저작물 객체 추출을 통한 추천 광고 매칭방법을 제안한다. 360도 영상저작물 내에 광고를 매칭하고 추출된 객체와 연관된 광고를 추출하여 해당 프레임에 자동으로 삽입 노출이 가능하도록 하는 방법으로 이 방법을 이용함으로써 사용자의 현재 시점 영역 내에 광고 영상이 노출되도록 광고의 삽입 위치를 이동시켜 영상이 재생되도록 하거나, 광고 영상이 삽입된 좌표로 사용자의 현재 시점을 이동시켜 영상이 재생되게 할 수 있다.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.26 no.2
• /
• pp.149-156
• /
• 2008

In this paper, we propose a method aiming at updating the building information of the digital maps using single high resolution satellite image and digital map. Firstly we produced a digital orthoimage through the automatic co-registration of QuickBird image and 1:1,000 digital map. Secondly we extracted building height information through the template matching of digital map's building vector data and the image's edges obtained by Canny operator. Finally we refined the shape of some buildings by using the result from template matching as the seed polygon of the greedy snake algorithm. In order to evaluate the proposed method's effectiveness, we estimated accuracy of the extracted building information using LiDAR DSM and 1:1,000 digital map. The evaluation results showed the proposed method has a good potential for extraction and revision of building information.

• Journal of KIISE
• /
• v.44 no.11
• /
• pp.1236-1243
• /
• 2017

In this paper, we propose a novel way of producing keyword networks, named LSI-based ClusterTextRank, which extracts significant key words from a set of clusters with a mutual information metric, and constructs an association network using latent semantic indexing (LSI). The proposed method reduces the dimension of documents through LSI, decomposes documents into multiple clusters through k-means clustering, and expresses the words within each cluster as a maximal spanning tree graph. The significant key words are identified by evaluating their mutual information within clusters. Then, the method calculates the similarities between the extracted key words using the term-concept matrix, and the results are represented as a keyword association network. To evaluate the performance of the proposed method, we used travel-related blog data and showed that the proposed method outperforms the existing TextRank algorithm by about 14% in terms of accuracy.