A Machine Learning Approach for Semantic Structuring of Scientific Charts in Scholarly Documents

Rabah A. Al-Zaidy, C. Lee Giles

Abstract: Large scholarly repositories are designed to provide scientists and researchers with a wealth of information that is retrieved from data present in a variety of formats. A typical scholarly document contains information in a combined layout of texts and graphic images. Common types of graphics found in these documents are scientific charts that are used to represent data values in a visual format. Experimental results are rarely described without the aid of one form of a chart or another, whether it is 2D plot, bar chart, pie chart, etc. Metadata of these graphics is usually the only content that is made available for search by user queries. By processing the image content and extracting the data represented in the graphics, search engines will be able to handle more specific queries related to the data itself. In this paper we describe a machine learning based system that extracts and recognizes the various data fields present in a bar chart for semantic labeling. Our approach comprises of a graphics and text separation and extraction phase, followed by a component role classification for both text and graphic components that are in turn used for semantic analysis and representation of the chart. The proposed system is tested on a set of over 200 bar charts extracted from over 1,000 scientific articles in PDF format.