IDEALS Home University of Illinois at Urbana-Champaign logo The Alma Mater The Main Quad

An Exploration of Multimodal Document Classification Strategies

Show full item record

Bookmark or cite this item: http://hdl.handle.net/2142/24006

Files in this item

File Description Format
PDF Chen_Scott.pdf (983KB) (no description provided) PDF
Title: An Exploration of Multimodal Document Classification Strategies
Author(s): Chen, Scott D.
Advisor(s): Moulin, Pierre
Department / Program: Electrical & Computer Eng
Discipline: Electrical & Computer Engr
Degree Granting Institution: University of Illinois at Urbana-Champaign
Degree: M.S.
Genre: Thesis
Subject(s): meta-classifier classification multimodal document support vector machines
Abstract: This thesis explores multimodal document classification algorithms in a unified framework. Classification algorithms are designed to exploit both text and image information, which proliferates in modern documents. We design meta-classification schemes that combine and integrate state-of-the-art text and image feature-extractors with state-of-the-art classifiers. Meta-classifiers fuse information across modalities that differ in nature and hence have more information on hand to make decisions. This thesis also discusses strategies that exploit correlations not only within a single modality but also among modalities. Techniques that exploit correlations within a modality include image meta-feature vector combination and latent Dirichlet allocation-based image meta-feature extraction. Another technique that exploits correlations between text and image cleans image with text information. Experiments on real-world databases from Wikipedia demonstrate the benefits of metaclassification for multimodal documents.
Issue Date: 2011-05-25
URI: http://hdl.handle.net/2142/24006
Rights Information: Copyright 2011 Scott Deeann Chen
Date Available in IDEALS: 2011-05-25
Date Deposited: 2011-05
 

This item appears in the following Collection(s)

Show full item record

Item Statistics

  • Total Downloads: 140
  • Downloads this Month: 1
  • Downloads Today: 0

Browse

My Account

Information

Access Key