• Korean Journal of Cognitive Science
• /
• v.22 no.4
• /
• pp.347-364
• /
• 2011

In this paper, we propose a automatic image bases extraction method for visual image reconstruction from brain activity using Non-negative Matrix Factorization (NMF). Image bases are basic elements to construct and present a visual image. Previous method used brain activity that evoked by predefined 361 image bases of four different sizes: $1{\times}1$, $2{\times}1$, $1{\times}2$, $2{\times}2$, and $2{\times}2$. Then the visual stimuli were reconstructed by linear combination of all the results from these image bases. While the previous method used 361 predefined image bases, the proposed method automatically extracts image bases which represent the image data efficiently. From the experiments, we found that the proposed method reconstructs the visual stimuli better than the previous method.

• Journal of KIISE
• /
• v.42 no.11
• /
• pp.1372-1379
• /
• 2015

This paper presents an analysis of feature extraction methods used for distinguishing the speech of patients with cleft palates and people with normal palates. This research is a basic study on the development of a software system for automatic recognition and restoration of speech disorders, in pursuit of improving the welfare of speech disabled persons. Monosyllable voice data for experiments were collected for three groups: normal speech, cleft palate speech, and simulated clef palate speech. The data consists of 14 basic Korean consonants, 5 complex consonants, and 7 vowels. Feature extractions are performed using three well-known methods: LPC, MFCC, and PLP. The pattern recognition process is executed using the acoustic model GMM. From our experiments, we concluded that the MFCC method is generally the most effective way to identify speech distortions. These results may contribute to the automatic detection and correction of the distorted speech of cleft palate patients, along with the development of an identification tool for levels of speech distortion.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.23 no.4
• /
• pp.374-380
• /
• 2019

Containers are fitted with various placards on the surface to indicate the risk of cargo. If the containers are loaded with dangerous goods, care should be taken in handling the containers. Therefore, as part of the port automation system, there is a demand for automatic placard recognition. In this paper, proposed is a method to extract placard areas from a container image, which is the first part of the placard recognition system. The fact that placards are of various types but all have a diamond shape can be an advantage in recognition. However, it is a disadvantage in recognition that the placards can be distorted in various ways because the container surface is not flat. When the proposed method was applied to actual images, type I error did not occur. In addition, since the shape feature of the object and basic image operations are used to extract regions of interest, it can be applied to various shape-based region extraction problems.

• Annual Conference on Human and Language Technology
• /
• 1997.10a
• /
• pp.59-64
• /
• 1997

복합명사로부터 적절한 색인어를 추출하는 것은 한국어 정보검색 시스템의 성능 향상에 중요한 역할을 한다. 본 논문에서는 복합명사로부터 색인어 추출을 하기 위해 복합명사 구문 구조 분석 결과를 활용한다. 단일명사가 3개 이상 결합된 복합명사의 경우 각 단일명사의 구문적 관계를 파악하여 적절한 괄호치기를 한 후 색인어를 추출하면 보다 좋은 결과를 얻을 수 있다. 이러한 복합명사 구문 구조 분석을 위해 말뭉치로부터 구조적 중의성이 없는 연어 관계의 완전 복합명사와, 서술성 명사와 공기하는 명사쌍을 추출한 결과를 이용한다. 또한 서술성 명사는 이와 공기하는 명사와 결합되어 복합명사를 이를 가능성이 많고, 복합명사의 형태로 인식되어야만 정확한 의미 파악이 가능하다. 서술성 명사와 공기하는 명사를 파악하여 복합명사를 추출하기 위해서 부분 파서로 공기쌍을 찾아 복합명사 후보를 생성한 후, 이 후보 가운데 적합한 복합명사만을 선택하기 위해 말뭉치에서 추출한 완전 복합명사 사전을 통해 검증한다. 이러한 방법으로 서술성 명사에서 복합명사 형태의 색인어를 추출한다.

• Journal of Broadcast Engineering
• /
• v.4 no.2
• /
• pp.187-196
• /
• 1999

This paper presents an efficient and automatic color and motion feature extraction algorithm for content-based MPEG-l video retrieval. Based on the proposed method. a video retrieval system is implemented. For color feature. the proposed algorithm considers dynamic color iRformation in video data, and thereby can overcome the limits of the previous key-frame based method. For motion feature, we utilize the motion vector in MPEG-l video with color information. and extract the color-motion feature. The proposed algorithm can solve the weakness of the previous location based motion feature method. Finally. the proposed method is evaluated within the implemented video retrieval system.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.7 no.6
• /
• pp.1210-1216
• /
• 2003

Traditional indexing mechanism are based on the song's metadata such as the title and the composer and so on. However, these system have a major limitation that users have to know the metadata of the songs they want to retrieve. In order to solve these limitation, we proposed a rhythm extraction system that allows users to retrieve music information efficiently from a large music database using the rhythm that is defined as the parts of the music.

• Proceedings of the Korean Information Science Society Conference
• /
• 1999.10c
• /
• pp.471-473
• /
• 1999

인터넷상의 정보 검색 엔진들은 웹 로봇을 실행해서 인터넷에 연결되어 있는 수많은 웹 서버들을 방문해서 웹 문서를 획득하고, 인덱싱 기법을 써서 자료를 추출하고 분류해서 검색 엔진의 기초가 되는 데이터 베이스를 구축한다. 정보 추출을 위해 웹 로봇을 운영할 때 웹 서버에 대한 사전 지식 없이 진행된다면 수많은 불필요한 요구가 전송돼서 인터넷 트래픽을 증가시키는 요인이 된다. 하지만 웹 서버가 사전에 자신이 공개할 문서에 대한 요약 정보를 웹 로봇에게 통보하고, 웹 로봇은 이 정보를 이용해서 웹 서버의 해당 문서에 대한 정보 수집 작업을 처리한다면 불필요한 인터넷 트래픽을 줄일 수 있을 뿐만 아니라 검색 엔진의 정보의 정확도를 높이고, 웹 서버상의 웹 문서 파일의 변동 사항을 자동으로 검사하고 변동된 사항들을 종합 정리해서 등록된 각 웹 로봇에게 전송하는 문서 감시 통보 시스템과 통보된 요약 정보를 토대로 웹 서버로부터 해당 문서를 전송받아 필요한 인덱스 정보를 추출하는 효율적인 웹 로봇을 제안한다.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.21 no.1
• /
• pp.27-36
• /
• 2003

Generally, the latest acquisition method of geo-spatial informations in urban area is executed by generation of digital elevation model (DEM) and digital ortho image by digital photogrammetry method which is used large scale photo image. However, the biggest problem of this method is coarse accuracy of DEM which is automatically generated by digital photogrammetry workstation system. The coarse accuracy of DEM caused geo-spatial information in urban area to reduce of accuracy. Therefore, this study is purposed to increase of DEM accuracy which is applied to method terrain classification in urban area. As the results of this study, the proposed method of this study which is increased to accuracy of DEM by classification of terrain is better than accuracy of DEM which is automatically generated by digital photogrammetry workstaion system. And, the edge detection method which is proposed by this study is established to capability of 3D digital mapping in urban area.

• The Journal of Korean Association of Computer Education
• /
• v.12 no.6
• /
• pp.21-32
• /
• 2009

This paper proposes a method to extract a user's intention automatically and implementation of intention map that support a user can appropriate search results using a user' information need accurately. It selects user intention based on searching history obtained from previous users' same queries and extracts user intentions by using clustering algorithm and user intention extraction algorithm, extracted user intentions are represented in an intention map base on a theory of knowledge representation. For the efficiency analysis of intention map, we extracted user intentions using 2,600 search history data which provided by a current domestic commercial search engine. The experimental results using the information intention map search when using general search engines represent more than satisfaction was statistically significant.

• Korean Journal of Cognitive Science
• /
• v.19 no.4
• /
• pp.443-458
• /
• 2008

Since Web pages contain a lot of information today, the Web becomes an important resource to extract some information. In this paper, we proposes a set expansion system which can automatically extract named entities from the Web. Overall, the proposed method consists of three steps. First of all, Web pages, which may include many named entities of a domain, are collected by using several seed words of the domain. Then some pattern rules are extracted by using seed words and the collected Web pages, and the named entity candidates are selected through applying the extracted pattern rules into Web pages. To distinguish real named entities, we develop the new mutual importance measurement method which estimates the importance of named entity candidates. We conducted experiments for 3 domains for Korean and for 8 domains for English. As a result, the proposed method obtained 78.72% MAP in Korean and 96.48% MAP in English. In particular, the performances of English domains are better than the results of the Google set.