CDeC-Net: Composite Deformable Cascade Network for Table Detection in Document Images

TL;DR

CDeC-Net is an end-to-end deep learning model that effectively detects tables in document images across multiple benchmarks using a multi-stage deformable convolution approach.

Contribution

The paper introduces CDeC-Net, a novel multi-stage Mask R-CNN extension with deformable convolutions, achieving high accuracy in table detection across diverse datasets.

Findings

Performs well across all benchmark datasets

Achieves high detection accuracy at higher IoU thresholds

Consistently outperforms existing methods on standard benchmarks

Abstract

Localizing page elements/objects such as tables, figures, equations, etc. is the primary step in extracting information from document images. We propose a novel end-to-end trainable deep network, (CDeC-Net) for detecting tables present in the documents. The proposed network consists of a multistage extension of Mask R-CNN with a dual backbone having deformable convolution for detecting tables varying in scale with high detection accuracy at higher IoU threshold. We empirically evaluate CDeC-Net on all the publicly available benchmark datasets - ICDAR-2013, ICDAR-2017, ICDAR-2019,UNLV, Marmot, PubLayNet, and TableBank - with extensive experiments. Our solution has three important properties: (i) a single trained model CDeC-Net{\ddag} performs well across all the popular benchmark datasets; (ii) we report excellent performances across multiple, including higher, thresholds of IoU; (iii) by following the same protocol of the recent papers for each of the benchmarks, we consistently demonstrate the superior quantitative performance. Our code and models will be publicly released for enabling the reproducibility of the results.