Revising FUNSD dataset for key-value detection in document images

2020/10/11 by Hieu M. Vu, Vu, Hieu M., Diep Thi-Ngoc Nguyen +1 · 2 citations
Computer Science · #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #Handwritten Text Recognition Techniques #Image Processing and 3D Reconstruction #Image Retrieval and Classification Techniques

paper · pdf · doi:10.48550/arxiv.2010.05322

openalex publication_date 2020/10/11 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

FUNSD is one of the limited publicly available datasets for information extraction from document im-ages. The information in the FUNSD dataset is defined by text areas of four categories ("key", "value", "header", "other", and "background") and connectivity between areas as key-value relations. In-specting FUNSD, we found several inconsistency in labeling, which impeded its applicability to thekey-value extraction problem. In this report, we described some labeling issues in FUNSD and therevision we made to the dataset. We also reported our implementation of for key-value detection onFUNSD using a UNet model as baseline results and an improved UNet model with Channel-InvariantDeformable Convolution.

Citations

• A guide to convolution arithmetic for deep learning

Cited by

• KH-FUNSD: A Hierarchical and Fine-Grained Layout Analysis Dataset for Low-Resource Khmer Business Document
• CommonForms: A Large, Diverse Dataset for Form Field Detection

Related

• Key Information Extraction From Documents: Evaluation And Generator
• GenKIE: Robust Generative Multimodal Document Key Information Extraction
• Information Redundancy and Biases in Public Document Information Extraction Benchmarks
• PICK: Processing Key Information Extraction from Documents using Improved Graph Learning-Convolutional Networks
• PPN: Parallel Pointer-based Network for Key Information Extraction with Complex Layouts