Please use this identifier to cite or link to this item:
Title: Visual Image Recognition System with Object-Level Image Representation
Keywords: Image Recognition, Object Recognition, Image Feature, Intelligent System
Issue Date: 27-Dec-2012
Citation: SONG ZHENG (2012-12-27). Visual Image Recognition System with Object-Level Image Representation. ScholarBank@NUS Repository.
Abstract: In this thesis, we propose a general framework for building object-aware image understanding systems. This unified framework integrates the recent object localization, feature description and data mining techniques. The proposed framework aims to solve the Web image recognition problem given concerned topics. Firstly according to the system requirement, related photos and videos are crawled from the Internet. Then the data are screened and indexed using the object detectors learned from annotated data subsets. Thereafter, the collected datasets are further analysed to obtain the fine details of the objects and object attributes in the images. Comprehensive object description is obtained using image descriptors extracted from key parts of the detected objects. Such object-aware image description is proved to be more effective than traditional global image description in understanding image contents. Core techniques including image feature representation, object detection and object attribute description are thoroughly investigated and implemented.
Appears in Collections:Ph.D Theses (Open)

Show full item record
Files in This Item:
File Description SizeFormatAccess SettingsVersion 
SongZ.pdf5.82 MBAdobe PDF



Page view(s)

checked on Nov 17, 2018


checked on Nov 17, 2018

Google ScholarTM


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.