BusiNet -- a Light and Fast Text Detection Network for Business Documents
This work addresses privacy and accuracy issues in OCR for business documents, though it is incremental as it builds on existing detection methods with specific optimizations.
The paper tackles the problem of poor OCR performance on visually damaged business documents by introducing BusiNet, a fast and lightweight text detection network designed for local use to address privacy concerns, achieving robust results through adversarial training on a synthetic dataset.
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.