RAPTOR: Refined Approach for Product Table Object Recognition

TL;DR

RAPTOR is a modular post-processing system that enhances existing table detection and recognition models, significantly improving accuracy for product tables in documents by addressing common errors and optimizing parameters with genetic algorithms.

Contribution

This work introduces RAPTOR, a novel modular post-processing framework that refines state-of-the-art table detection and structure recognition models, tailored for industrial product tables.

Findings

Improved precision and structural accuracy on product table datasets.

Effective optimization of module parameters using genetic algorithms.

Maintains reasonable performance across diverse table formats.

Abstract

Extracting tables from documents is a critical task across various industries, especially on business documents like invoices and reports. Existing systems based on DEtection TRansformer (DETR) such as TAble TRansformer (TATR), offer solutions for Table Detection (TD) and Table Structure Recognition (TSR) but face challenges with diverse table formats and common errors like incorrect area detection and overlapping columns. This research introduces RAPTOR, a modular post-processing system designed to enhance state-of-the-art models for improved table extraction, particularly for product tables. RAPTOR addresses recurrent TD and TSR issues, improving both precision and structural predictions. For TD, we use DETR (trained on ICDAR 2019) and TATR (trained on PubTables-1M and FinTabNet), while TSR only relies on TATR. A Genetic Algorithm is incorporated to optimize RAPTOR's module parameters, using a private dataset of product tables to align with industrial needs. We evaluate our method on two private datasets of product tables, the public DOCILE dataset (which contains tables similar to our target product tables), and the ICDAR 2013 and ICDAR 2019 datasets. The results demonstrate that while our approach excels at product tables, it also maintains reasonable performance across diverse table formats. An ablation study further validates the contribution of each module in our system.