TRACE: Table Reconstruction Aligned to Corner and Edges

TL;DR

This paper introduces TRACE, a bottom-up table reconstruction method that directly localizes table cells using corners and edges, reducing complexity and error propagation compared to traditional two-stage approaches.

Contribution

The novel bottom-up approach reconstructs tables from low-level features, simplifying training and inference while achieving state-of-the-art results.

Findings

Achieves state-of-the-art performance on ICDAR2013 benchmark.

Requires less computation than previous methods.

Simplifies table reconstruction by focusing on cell borders.

Abstract

A table is an object that captures structured and informative content within a document, and recognizing a table in an image is challenging due to the complexity and variety of table layouts. Many previous works typically adopt a two-stage approach; (1) Table detection(TD) localizes the table region in an image and (2) Table Structure Recognition(TSR) identifies row- and column-wise adjacency relations between the cells. The use of a two-stage approach often entails the consequences of error propagation between the modules and raises training and inference inefficiency. In this work, we analyze the natural characteristics of a table, where a table is composed of cells and each cell is made up of borders consisting of edges. We propose a novel method to reconstruct the table in a bottom-up manner. Through a simple process, the proposed method separates cell boundaries from low-level features, such as corners and edges, and localizes table positions by combining the cells. A simple design makes the model easier to train and requires less computation than previous two-stage methods. We achieve state-of-the-art performance on the ICDAR2013 table competition benchmark and Wired Table in the Wild(WTW) dataset.