Learning of personal visual impression for image database systems

Author

Kurita, Takio ; Kato, Toshikazu

Author_Institution

Electrotechnical Lab., Tsukuba, Japan

fYear

1993

fDate

20-22 Oct 1993

Firstpage

547

Lastpage

552

Abstract

Visual impression may differ with each person. User-friendly interfaces for image database systems require special retrieval methods which can adapt to the visual impression of each user. Algorithms for learning personal visual impressions of visual objects are described. The algorithms are based on multivariate data analysis methods. These algorithms provide a model on visual perception process of each user from a small set of training examples. This model is referred to as a personal index to retrieve desired images for the user. These algorithms were implemented and examined in a graphical symbol database system called TRADEMARK and a full color image database called ART MUSEUM

Keywords

colour graphics; information retrieval; learning (artificial intelligence); user interfaces; visual databases; ART MUSEUM; TRADEMARK; full color image database; graphical symbol database system; image database systems; learning; multivariate data analysis methods; personal index; personal visual impression; special retrieval methods; training examples; user-friendly interfaces; visual objects; visual perception process; Color; Data analysis; Database systems; Image databases; Image retrieval; Information retrieval; Subspace constraints; Trademarks; Visual databases; Visual perception;

fLanguage

English

Publisher

ieee

Conference_Titel

Document Analysis and Recognition, 1993., Proceedings of the Second International Conference on

Conference_Location

Tsukuba Science City

Print_ISBN

0-8186-4960-7

Type

conf

DOI

10.1109/ICDAR.1993.395676

Filename

395676