dc.contributor.authorTay, Alvin Yunardy
dc.date.accessioned2014-04-22T08:06:42Z
dc.date.available2014-04-22T08:06:42Z
dc.date.copyright2014en_US
dc.date.issued2014
dc.identifier.urihttp://hdl.handle.net/10356/59093
dc.description.abstractIn recent years of advances technology in digital cameras and mobile phone cameras have led to the massive growth of digital personal photo albums and the consumer videos. The issue of organizing and indexing such huge amount of photo collections has attracted much effort of research in this area to develop effective and efficient methods. Methods and algorithms used are intended to provide users with a convenience of searching their photo collections with a specific content. However, this is still a challenging task for many researchers to develop such framework to improve retrieval performance on large scale image collections in a real-time manner. In this paper, we present a framework of a photo search engine based on prior annotation. After the user provides a textual query (e.g. “animal”), this framework will utilize the annotated web images from database as a bridge between domains in web images and consumer photos. The pre-learned classifier is then built using the annotated web images. This approach utilizes a large number of readily available images with their associated textual descriptions. This classifier can be used to predict and rank the consumer photos.en_US
dc.format.extent55 p.en_US
dc.language.isoenen_US
dc.rightsNanyang Technological University
dc.subjectDRNTU::Engineering::Computer science and engineering::Computing methodologies::Pattern recognitionen_US
dc.titleImage annotation by searchen_US
dc.typeFinal Year Project (FYP)en_US
dc.contributor.supervisorXu Dong (SCE)en_US
dc.contributor.schoolSchool of Computer Engineeringen_US
dc.description.degreeCOMPUTER SCIENCEen_US
dc.contributor.researchCentre for Multimedia and Network Technologyen_US


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record