DocumentCode :
2281630
Title :
KnownStyleNoLife.com: Resource Sharing System for Explicit Fashion-Related Image Annotation
Author :
Toyama, Toshiaki ; Konishi, Katsumi
Author_Institution :
Depertment of Comput. Sci. & Commun. Eng., Kogakuin Univ., Tokyo
Volume :
3
fYear :
2008
fDate :
9-12 Dec. 2008
Firstpage :
152
Lastpage :
156
Abstract :
In this paper, we present the Web-based resource sharing system KnownStyleNoLife, which allows users explicitly annotate fashion-related images. KnownStyleNoLife harnesses human power and collects image metadata such as object locations, object labels, image rating and semantic relationships among images. Metadata of that type are invaluable as it is difficult for ordinary computer software to extract equivalent metadata from the Web. Acquiring image metadata such as the type and location of objects in images requires a computer to use machine learning techniques, needing training with sample images and Web search techniques, with the outcome that only limited image metadata are extracted. Furthermore, the semantic image relationship metadata is based upon peoplepsilas image perception, hence user feedback is required to acquire it. KnownStyleNoLife provides a social value to users in return for their explicit annotations. It is a novel approach to harness human power to acquire relevant image metadata.
Keywords :
image retrieval; image sampling; learning (artificial intelligence); meta data; resource allocation; semantic Web; social networking (online); KnownStyleNoLife; Web search; explicit fashion-related image annotation; image perception; image sample training; machine learning technique; resource sharing system; semantic image relationship metadata; user feedback; Collaborative tools; Computer science; Computer vision; Humans; Informatics; Intelligent agent; Power engineering and energy; Resource management; Software; Tagging; Distributed knowledge acquisition; Image annotation; Semantic annotation; Social Web; fashion community;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Web Intelligence and Intelligent Agent Technology, 2008. WI-IAT '08. IEEE/WIC/ACM International Conference on
Conference_Location :
Sydney, NSW
Print_ISBN :
978-0-7695-3496-1
Type :
conf
DOI :
10.1109/WIIAT.2008.187
Filename :
4740749
Link To Document :
بازگشت