Abstract

Biomedical journal articles contain a variety of image types that can be broadly classified into two categories: regular images, and graphical images. Graphical images can be further classified into four classes: diagrams, statistical figures, flow charts, and tables. Automatic figure type identification is an important step toward improved multimodal (text + image) information retrieval and clinical decision support applications. This paper describes a feature-based learning approach to automatically identify these four graphical figure types. We apply Evolutionary Algorithm (EA), Binary Particle Swarm Optimization (BPSO) and a hybrid of EA and BPSO (EABPSO) methods to select an optimal subset of extracted image features that are then classified using a Support Vector Machine (SVM) classifier. Evaluation performed on 1038 figure images extracted from ten BioMedCentral® journals with the features selected by EABPSO yielded classification accuracy as high as 87.5%.

Meeting Name

SPIE 8297, Document Recognition and Retrieval XIX (2012: Jan. 22, Burlingame, CA)

Department(s)

Electrical and Computer Engineering

Keywords and Phrases

Biomedical journal; Classification accuracy; Clinical decision support; Feature-based; Flow charts; Graphical images; Image features; Learning approach; Multi-modal; Optimal subsets; Support vector; Feature extraction; Information retrieval; Support vector machines; Image processing; Binary Particle Swarm Optimization (BPSO); Evolutionary Algorithm (EA); Support Vector Machine (SVM)

International Standard Book Number (ISBN)

978-0-81948-944-9

International Standard Serial Number (ISSN)

0277-786X

Document Type

Article - Conference proceedings

Document Version

Final Version

File Type

text

Language(s)

English

Rights

© 2012 SPIE -- The International Society for Optical Engineering, All rights reserved.

Publication Date

01 Jan 2012

Share

 
COinS