닫기
Loading..

Please wait....

학술대회 프로시딩

홈 홈 > 연구문헌 > 학술대회 프로시딩 > IPIU (영상처리 및 이해에 관한 워크샵) > IPIU 2007 (제19회 영상처리 및 이해에 관한 워크샵)

IPIU 2007 (제19회 영상처리 및 이해에 관한 워크샵)

Current Result Document : 7,672 / 7,672

한글제목(Korean Title) Image retrieval and refinement using neural networks
영문제목(English Title) Image retrieval and refinement using neural networks
저자(Author) Kyong Mi Lee   Youn Mi Lee   Hey Jeong Kim                       
원문수록처(Citation) VOL 19 NO. 01 PP. 0088 ~ 0092 (2007. 02)
한글내용
(Korean Abstract)
영문내용
(English Abstract)
This paper proposed a neural network to extend prototype refinement which retains information fed by users. Given a query, the system finds near clusters by an unsupervised approach, and determines similarity with images in the clusters by a supervised approach. To provide preference, users can select some images as relevant ones or irrelevant ones. With this feedback, the proposed refinement method estimates global approximations of radial-basis functions centered, and simultaneously adjusts corresponding prototypes. The system demonstrated the effectiveness of prototype refinement generated by the proposed neural network.
키워드(Keyword)                              
파일첨부 PDF 다운로드