Object Recognition from Scientific Document based on Compartment Refinement Framework

TL;DR

The paper introduces CTBR, a Compartment & Text Blocks Refinement framework for object recognition in scientific documents. It defines a hierarchical layout model (base domains, compartments, text blocks) and combines rule-based processing for simple blocks with machine learning for complex, multi-modal blocks via an encoder template and SVM classifier. A compartment refinement algorithm then uses the block classifications to accurately locate figures and tables, achieving over 90% recognition accuracy on a small-scale dataset. This approach addresses the challenges of irregular layouts and multi-modal content, enabling more reliable extraction and analysis of scientific content for surveys and knowledge infrastructure.

Abstract

With the rapid development of the internet in the past decade, it has become increasingly important to extract valuable information from vast resources efficiently, which is crucial for establishing a comprehensive digital ecosystem, particularly in the context of research surveys and comprehension. The foundation of these tasks focuses on accurate extraction and deep mining of data from scientific documents, which are essential for building a robust data infrastructure. However, parsing raw data or extracting data from complex scientific documents have been ongoing challenges. Current data extraction methods for scientific documents typically use rule-based (RB) or machine learning (ML) approaches. However, using rule-based methods can incur high coding costs for articles with intricate typesetting. Conversely, relying solely on machine learning methods necessitates annotation work for complex content types within the scientific document, which can be costly. Additionally, few studies have thoroughly defined and explored the hierarchical layout within scientific documents. The lack of a comprehensive definition of the internal structure and elements of the documents indirectly impacts the accuracy of text classification and object recognition tasks. From the perspective of analyzing the standard layout and typesetting used in the specified publication, we propose a new document layout analysis framework called CTBR(Compartment & Text Blocks Refinement). Firstly, we define scientific documents into hierarchical divisions: base domain, compartment, and text blocks. Next, we conduct an in-depth exploration and classification of the meanings of text blocks. Finally, we utilize the results of text block classification to implement object recognition within scientific documents based on rule-based compartment segmentation.

Figures (7)

• Figure 1: Overview
• Figure 2: Internal Environment of scientific document
• Figure 3: Unstructured page layout: Sample articlefig3
• Figure 4: Human annotation for text blocksfig4.
• Figure 5: Boundary setting & compartmentfig5.