Image annotation by search

In 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...

Full description

Saved in:
Bibliographic Details
Main Author: Tay, Alvin Yunardy
Other Authors: Xu Dong
Format: Final Year Project
Language:English
Published: 2014
Subjects:
Online Access:http://hdl.handle.net/10356/59093
Tags: Add Tag
No Tags, Be the first to tag this record!
Institution: Nanyang Technological University
Language: English
id sg-ntu-dr.10356-59093
record_format dspace
spelling sg-ntu-dr.10356-590932023-03-03T20:51:34Z Image annotation by search Tay, Alvin Yunardy Xu Dong School of Computer Engineering Centre for Multimedia and Network Technology DRNTU::Engineering::Computer science and engineering::Computing methodologies::Pattern recognition In 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. Bachelor of Engineering (Computer Science) 2014-04-22T08:06:42Z 2014-04-22T08:06:42Z 2014 2014 Final Year Project (FYP) http://hdl.handle.net/10356/59093 en Nanyang Technological University 55 p. application/pdf
institution Nanyang Technological University
building NTU Library
continent Asia
country Singapore
Singapore
content_provider NTU Library
collection DR-NTU
language English
topic DRNTU::Engineering::Computer science and engineering::Computing methodologies::Pattern recognition
spellingShingle DRNTU::Engineering::Computer science and engineering::Computing methodologies::Pattern recognition
Tay, Alvin Yunardy
Image annotation by search
description In 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.
author2 Xu Dong
author_facet Xu Dong
Tay, Alvin Yunardy
format Final Year Project
author Tay, Alvin Yunardy
author_sort Tay, Alvin Yunardy
title Image annotation by search
title_short Image annotation by search
title_full Image annotation by search
title_fullStr Image annotation by search
title_full_unstemmed Image annotation by search
title_sort image annotation by search
publishDate 2014
url http://hdl.handle.net/10356/59093
_version_ 1759856035443507200