Publication Type

Conference Proceeding Article

Version

publishedVersion

Publication Date

1-2007

Abstract

Decision tree (DT) has great potential in image semantic learning due to its simplicity in implementation and its robustness to incomplete and noisy data. Decision tree learning naturally requires the input attributes to be nominal (discrete). However, proper discretization of continuous-valued image features is a difficult task. In this paper, we present a decision tree based image semantic learning method, which avoids the difficult image feature discretization problem by making use of semantic template (ST) defined for each concept in our database. A ST is the representative feature of a concept, generated from the low-level features of a collection of sample regions. Experimental results on real-world images confirm the promising performance of the proposed method in image semantic learning.

Keywords

decision tree, image feature discretization, image semantic learning, semantic template

Discipline

Artificial Intelligence and Robotics | Databases and Information Systems

Research Areas

Data Science and Engineering; Intelligent Systems and Optimization

Publication

Proceedings, 13th International Multimedia Modeling Conference (MMM'07)

Volume

4352 LNCS

Identifier

10.1007/978-3-540-69429-8_19

City or Country

Singapore

Share

COinS