BusiNet -- a Light and Fast Text Detection Network for Business Documents

TL;DR

BusiNet is a lightweight, fast, and robust text detection network designed for local OCR of business documents, effectively handling noise and damage while preserving privacy.

Contribution

The paper introduces BusiNet, a novel, efficient text detection network optimized for local processing of business documents with noise robustness.

Findings

BusiNet achieves high accuracy on public datasets.

It runs efficiently on local devices, ensuring privacy.

The model effectively handles noisy and damaged documents.

Abstract

For digitizing or indexing physical documents, Optical Character Recognition (OCR), the process of extracting textual information from scanned documents, is a vital technology. When a document is visually damaged or contains non-textual elements, existing technologies can yield poor results, as erroneous detection results can greatly affect the quality of OCR. In this paper we present a detection network dubbed BusiNet aimed at OCR of business documents. Business documents often include sensitive information and as such they cannot be uploaded to a cloud service for OCR. BusiNet was designed to be fast and light so it could run locally preventing privacy issues. Furthermore, BusiNet is built to handle scanned document corruption and noise using a specialized synthetic dataset. The model is made robust to unseen noise by employing adversarial training strategies. We perform an evaluation on publicly available datasets demonstrating the usefulness and broad applicability of our model.