Mind the Gaps: A Curated Benchmark for Form Field Detection

arXiv:2609.23679 · cs.CV, cs.DB · Submitted 2026-09-20 · Read on arXiv

cs.CV, cs.DB

Submitted: 2026-09-20

Updated: 2026-09-20

Comments: Accepted at the International Workshop on Document Analysis Systems (DAS) 2026. Dataset: https://huggingface.co/datasets/omoured/minicommonform

Journal ref: Document Analysis Systems (DAS 2026), Lecture Notes in Computer Science, Springer Nature Switzerland, Cham, pp. 459-473

DOI: 10.1007/978-3-032-36207-0_27

Code: https://github.com/moured/mini-commonforms

License: http://creativecommons.org/licenses/by/4.0/

The gist: Form Field Detection (FFD) is a fundamental component of document understanding systems, enabling applications ranging from large-scale industrial digitization to accessible form interaction for

Terminology

Abstract

Form Field Detection (FFD) is a fundamental component of document understanding systems, enabling applications ranging from large-scale industrial digitization to accessible form interaction for automated analysis. Unlike conventional object detection tasks, FFD is inherently challenging because fields are often defined by layout structure and whitespace rather than visible foreground content. Existing large-scale datasets frequently rely on heuristic annotation pipelines, resulting in noisy and inconsistent labels that hinder reliable evaluation. In this work, we introduce mini-CommonForms, a carefully curated FFD benchmark with consistent, high-quality annotations, and present a detailed evaluation of state-of-the-art detection approaches. The benchmark is designed to support reproducible research in document automation and accessibility-oriented applications. Dataset and code are available at https://github.com/moured/mini-commonforms

Sources

Related papers