• Annual Conference on Human and Language Technology
• /
• 2022.10a
• /
• pp.553-558
• /
• 2022

최근, 구어체 데이터에 대한 자연어처리 응용 기술이 늘어나고 있다. 구어체 문장은 소통 방식 등의 형태로 인해 정제되지 않은 형태로써, 필연적으로 띄어쓰기, 문장 왜곡 등의 다양한 문법적 오류를 포함한다. 자동 문법 교정기는 이러한 구어체 데이터의 전처리 및 일차적 정제 도구로써 활용된다. 사전학습된 트랜스포머 기반 문장 생성 연구가 활발해지며, 이를 활용한 자동 문법 교정기 역시 연구되고 있다. 트랜스포머 기반 문장 교정 시, 교정의 필요 유무를 잘못 판단하여, 오류가 생기게 된다. 이러한 오류는 대체로 문맥에 혼동을 주는 단어의 등장으로 인해 발생한다. 본 논문은 트랜스포머 기반 문법 교정기의 오류를 보강하기 위한 방식으로써, 필요하지 않은 형태소인 고유명사를 마스킹한 입력 및 출력 문장틀 형태를 제안하며, 이러한 문장틀에 대해 고유명사를 복원한 경우 성능이 증강됨을 보인다.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2021.06a
• /
• pp.112-115
• /
• 2021

최근 가상현실 및 증강 현실에 대한 관심도가 높아지면서, 깊이 추정, 객체 인식, 영상 분할 등의 다양한 컴퓨터 비전 알고리즘을 360° 영상에 적용하는 연구가 활발히 진행되고 있다. 이 중, 다수의 RGB 카메라를 활용하여 3 차원 정보를 추출하는 깊이 추정 기술은 보다 나은 몰입감을 제공하기 위한 핵심 기술이다. 그러나 깊이 추정 알고리즘의 객관적 성능 평가를 위한 정제된 360° 영상 데이터셋은 극히 부족하며, 이로 인하여 관련 분야 연구에 한계가 있다. 따라서 본 논문에서는 객관적인 알고리즘 성능 평가가 가능하며, 정제된 360° 동영상 데이터셋을 제안하고, 추후 다양한 360° 영상 응용 알고리즘 개발에 활용하고자 한다.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2022.06a
• /
• pp.1216-1217
• /
• 2022

포인트 클라우드는 객체 또는 장면을 재구성하기 위한 3D 데이터의 표현 방식 중 하나로써 가상 및 증강 현실을 포함한 다양한 분야에서 활용되고 있다. 포인트 클라우드 데이터는 품질에 따라 수많은 포인트로 이루어질 수 있으며, 이와 관련된 데이터의 양은 2차원 영상의 데이터보다 상당히 많다. 따라서 포인트 클라우드 데이터를 사용하여 다양한 서비스를 제공하기 위해서는 포인트 클라우드의 특징을 고려한 효율적인 압축 기술이 요구되며, 이에 따라 국제 표준화 단체의 Moving Picture Experts Group은 포인트 클라우드 데이터의 효율적인 압축을 위한 V-PCC 표준을 제정하였다. V-PCC는 포인트 클라우드 데이터를 다수의 2차원 공간으로 투영하여 점유 맵, 기하 영상, 그리고 속성 영상을 생성하고 각 2차원 영상을 기존의 비디오 코덱을 활용하여 압축하는 방식이다. 기존의 코덱을 사용하여 압축함에 따라 활용성이 높지만, 3차원 데이터를 다수의 2차원 영상을 통하여 압축하기 때문에 압축의 효율성을 높이기 위한 많은 연구가 필요하다. 본 논문에서는 V-PCC의 부호화 효율을 높이기 위해 점유 맵의 투영 정보를 활용한 속성 영상의 효율적인 압축 방법을 소개하고 이를 위한 적응적 SAO 방법을 제안한다. 실험에서 제안 방법은 V-PCC의 속성 영상에 대해 약 3.2%의 부호화 효율을 보인다.

• Tunnel and Underground Space
• /
• v.32 no.2
• /
• pp.131-143
• /
• 2022

The lunar exploration autonomous vehicle operates based on the lunar topography information obtained from real-time image characterization. For highly accurate topography characterization, a large number of training images with various background conditions are required. Since the real lunar topography images are difficult to obtain, it should be helpful to be able to generate mimic lunar image data artificially on the basis of the planetary analogs site images and real lunar images available. In this study, we aim to artificially create lunar topography images by using the location information-based style transfer algorithm known as Wavelet Correct Transform (WCT2). We conducted comparative experiments using lunar analog site images and real lunar topography images taken during China's and America's lunar-exploring projects (i.e., Chang'e and Apollo) to assess the efficacy of our suggested approach. The results show that the proposed techniques can create realistic images, which preserve the topography information of the analog site image while still showing the same condition as an image taken on lunar surface. The proposed algorithm also outperforms a conventional algorithm, Deep Photo Style Transfer (DPST) in terms of temporal and visual aspects. For future work, we intend to use the generated styled image data in combination with real image data for training lunar topography objects to be applied for topographic detection and segmentation. It is expected that this approach can significantly improve the performance of detection and segmentation models on real lunar topography images.

• Journal of the Korea Society of Computer and Information
• /
• v.15 no.10
• /
• pp.11-17
• /
• 2010

Mobile device, one of typical devices in ubiquitous environment, is received attention owing to portability. In these days, technical researches on a kind of the device are focusing on applications of smart phone. For example, the techniques using geographical position and applied instances such as augmented reality techniques are gradually increasing. That makes data processing important. Mobile application services for users also require various application techniques based on moving objects. In addition, they require the techniques that processed data are needed to be shown in visualization. However, this is reality that it lacks of showing visualization works to improve the understanding of thing what it is. To reduce or solve the problems, in this paper we show the results to implement the R tree based 3 dimension index architecture in visualization. Further, we implemented and present creating objects, showing in 3D for the objects, catching spatial position on a node map through mini map function and improving the understanding of R tree by visualizing.

• Journal of the Microelectronics and Packaging Society
• /
• v.30 no.4
• /
• pp.69-78
• /
• 2023

With the rapid growth of artificial intelligence, the demand for semiconductors is enormously increasing everywhere. To ensure the manufacturing quality and quantity simultaneously, the importance of automatic defect detection during the packaging process has been re-visited by adapting various deep learning-based methodologies into automatic packaging defect inspection. Deep learning (DL) models require a large amount of data for training, but due to the nature of the semiconductor industry where security is important, sharing and labeling of relevant data is challenging, making it difficult for model training. In this study, we propose a new framework for securing sufficient data for DL models with fewer computing resources through a divide-and-conquer approach. The proposed method divides high-resolution images into pre-defined sub-regions and assigns conditional labels to each region, then trains individual sub-regions and boundaries with boundary loss inducing the globally coherent and seamless images. Afterwards, full-size image is reconstructed by combining divided sub-regions. The experimental results show that the images obtained through this research have high efficiency, consistency, quality, and generality.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2008.10a
• /
• pp.285-288
• /
• 2008

In many intrusion detection applications, n-gram approach has been widely applied. However, n-gram approach has shown a few problems including double counting of features. To address those problems, we applied n-gram augmented Naive Bayes directly to classify intrusive sequences and compared performance with those of Naive Bayes and Support Vector Machines (SVM) with n-gram features by the experiments on host-based intrusion detection benchmark data sets. Experimental results on the University of New Mexico (UNM) benchmark data sets show that the n-gram augmented method, which solves the problem of independence violation that happens when n-gram features are directly applied to Naive Bayes (i.e. Naive Bayes with n-gram features), yields intrusion detectors with higher accuracy than those from Naive Bayes with n-gram features and shows comparable accuracy to those from SVM with n-gram features.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.20 no.11
• /
• pp.2125-2130
• /
• 2016

In this paper, we researched the excellency of 3D graphic nursery contents which is developed by mobile AR technology. AR technology has currently people's attention because of the potential to be core contents of future ICT industry. We applied AR nursery contents for kid's subtitle language selection in Korean, Chinese and English education. The original fairy tale consisted of 6~8 scenes for the 3D contents production, and was adapted and translated. Dubbing was dubbed by the native speaker using the standard pronunciation, and the effect sound was edited separately to fit the scene. After composing a scenario, constructing a 3D model, constructing a interaction, constructing a sound effect, and creating content metadata, the Unity 3D game engine is executed to create a project and describe it as a script. It provides a fun and informative tradition of fairy tales with abundant content that incorporates ICT technology, accepting advanced technology-based education, and having opportunities to perceive software in daily life.

• KIPS Transactions on Software and Data Engineering
• /
• v.5 no.5
• /
• pp.243-250
• /
• 2016

Recently, public interest in virtual reality (VR) and augmented reality (AR) has increased. Therefore, computer graphics-related research has been actively conducted. This has included research on virtual space related to human posture implementation. However, such research has focused on general posture in humans. This paper presents a system with reference to the basic posture in sports climbing and the inverse kinematics method for generating the positions and behavior of virtual characteristics in a three-dimensional virtual space. The simulation based on the inverse kinematics method, produced with an inverse kinematics solver and initial pose animation from motion capture, provides realistic and natural movement. We designed a simulation system to generate correct posture and motions similar to those in sports climbing by applying the basic procedure of sports climbing. The simulation system provides help for producing content about sports climbing, such as learning programs for novice climbers and sports climbing games.

• Annual Conference on Human and Language Technology
• /
• 2021.10a
• /
• pp.467-472
• /
• 2021

본 연구는 패션앱 후기글에 나타나는 구매자의 의견에 대한 '평가분석(Evaluation Analysis: EA)'을 수행하여, 이를 기반으로 상품의 검색 및 추천을 수행하는 의류 검색추천 챗봇을 개발하는 LICO 프로젝트의 언어데이터 구축의 일환으로 수행되었다. '평가분석 트리플(EAT)'과 '평가기반요청 쿼드러플(EARQ)'의 구성요소들에 대한 주석작업은, 도메인 특화된 단일형 핵심어휘와 다단어(MWE) 핵심패턴들을 FST 방식으로 구조화하는 DECO-LGG 언어자원에 기반하여 반자동 언어데이터 증강(SSP) 방식을 통해 진행되었다. 이 과정을 통해 20여만 건의 후기글 문서(230만 어절)로 구성된 EVAD 평가주석데이터셋이 생성되었다. 여성의류 도메인의 평가분석을 위한 '평가속성(ASPECT)' 성분으로 14가지 유형이 분류되었고, 각 '평가속성'에 연동된 '평가내용(VALUE)' 쌍으로 전체 35가지의 {ASPECT-VALUE} 카테고리가 분류되었다. 본 연구에서 구축된 EVAD 평가주석 데이터의 성능을 평가한 결과, F1-Score 0.91의 성능 평가를 획득하였으며, 이를 통해 향후 다른 도메인으로의 확장된 적용 가능성이 유효함을 확인하였다.