Toward ontological visual understanding

Lack of human prior knowledge is one of the main reasons that the semantic gap still remains when it comes to automatic multimedia understanding. One difference between the human cognition system and state-of-the-art machine vision algorithms is that the former possesses and uses high-level semantic knowledge, or ontology. In this thesis, we present our work on image-level annotation and album-level event recognition, both emphasizing the ontological structure among concepts including object, scene, and event. The inference and learning make use of mutual relations among these concepts, and are general for any concept and initial concept recognition. Our experiments show that the proposed frameworks are able to perform the respective visual recognition tasks better than other methods that are also based on middle-level recognition with or without ontology, and better than methods based purely on low-level features, thus validating the use of ontology in recognizing high-level and abstract concepts.

Name thesis:degree_name

Ph.D.

Level thesis:degree_level

Dissertation

Discipline thesis:degree_discipline

Electrical & Computer Engr

Grantor

University of Illinois at Urbana-Champaign

Year dc:date

2013

Author dc:creator

• Tsai, Shen-Fu

Contributors dc:contributor

• Huang, Thomas S.
• Han, Jiawei
• Hasegawa-Johnson, Mark A.
• Liang, Zhi-Pei

• Visual understanding
• ontology
• machine learning
• pattern recognition

Statement dc:rights

• Copyright 2012 Shen-Fu Tsai

Language dc:language

en

Handle dc:identifier

http://hdl.handle.net/2142/42191

OAI identifier oai:identifier

oai:www.ideals.illinois.edu:2142/42191