http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
- 中文 을 입력하시려면 zhongwen을 입력하시고 space를누르시면됩니다.
- 北京 을 입력하시려면 beijing을 입력하시고 space를 누르시면 됩니다.
RISS 인기검색어
- 검색키워드
- 저자 : 김대옥(Daeok Kim) (검색결과 2 건)
- 무료
- 기관 내 무료
- 유료
-
비제약적 환경에서 얼굴 주요위치 특징 서술자 기반의 얼굴인식
김대옥(Daeok Kim),홍종광(Jongkwang Hong),변혜란(Hyeran Byun) Korean Institute of Information Scientists and Eng 2014 정보과학회논문지 Vol.41 No.9
This paper proposes a scalable face recognition method for unconstrained face databases, and shows a simple experimental result. Existing face recognition research usually has focused on improving the recognition rate in a constrained environment where illumination, face alignment, facial expression, and background is controlled. Therefore, it cannot be applied in unconstrained face databases. The proposed system is face feature extraction algorithm for unconstrained face recognition. First of all, we extract the area that represent the important features(landmarks) in the face, like the eyes, nose, and mouth. Each landmark is represented by a high-dimensional LBP(Local Binary Pattern) histogram feature vector. The multi-scale LBP histogram vector corresponding to a single landmark, becomes a low-dimensional face feature vector through the feature reduction process, PCA(Principal Component Analysis) and LDA(Linear Discriminant Analysis). We use the Rank acquisition method and Precision at k(p@k) performance verification method for verifying the face recognition performance of the low-dimensional face feature by the proposed algorithm. To generate the experimental results of face recognition we used the FERET, LFW and PubFig83 database. The face recognition system using the proposed algorithm showed a better classification performance over the existing methods.
-
정승호(Seungho Cheong),김대옥(Daeok Kim),박종광(Chongkwang Park),김광환(Kwanghwan Kim),이은철(Eunchul Lee),김교선(Kyosun Kim) 대한전기학회 2006 대한전기학회 학술대회 논문집 Vol.2006 No.10
The subway passengers are usually alert to the current location of the train in order not to miss the destination or transfer stations. The Global Positioning System (GPS), although expensive, can give an alarm if properly programmed, but cannot receive the satellite signals, underground. Therefore, a novel approach to context-aware location-based subway information system is motivated. The passengers, who are equipped with mobile devices such as laptop, PDA, and mobile phone as clients of the Personal Area Network (PAN), request the Bluetooth connection to the server which is installed in each car of the train. While the server broadcasts the location-based information including the previous station, the current velocity of the train, the distance and time to the next station, the clients provide additional services based on the recognized context of the information, and what the passengers individually want. The services are spontaneous and autonomous rather than passive. The services include not only the information on the nearby stations, exit numbers, connection buses but also the location-based alarms which can be set specific to various personal requests, and sounded by the location of the train rather than time. Whereas the arrival time may not he accurate due to the delays of the train, the location can be accurately traced and broadcast by the server. Also, the clients do not need any expensive systems like GPS. Towards validating the proposed approach, we implemented a Bluetooth PAN including a PC server, two PDA clients and a laptop client. We modeled a train on the Incheon Subway Line #1 and a train on the Seoul-to-Incheon Line on the server, simulated the virtual trains together with the real clients. and verified that all the services were successfully provided.
ScienceON
DBpia연관 검색어 추천
이 검색어로 많이 본 자료
활용도 높은 자료
