Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

VisualWordGrid: Information Extraction From Scanned Documents Using A Multimodal Approach

About

We introduce a novel approach for scanned document representation to perform field extraction. It allows the simultaneous encoding of the textual, visual and layout information in a 3-axis tensor used as an input to a segmentation model. We improve the recent Chargrid and Wordgrid \cite{chargrid} models in several ways, first by taking into account the visual modality, then by boosting its robustness in regards to small datasets while keeping the inference time low. Our approach is tested on public and private document-image datasets, showing higher performances compared to the recent state-of-the-art methods.

Mohamed Kerroumi, Othmane Sayem, Aymen Shabou• 2020

Related benchmarks

TaskDatasetResultRank
Information ExtractionRVL-CDIP (test)
FAR26.9
4
Information ExtractionTax Notice (test)
FAR83.9
4
Showing 2 of 2 rows

Other info

Follow for update