-
SPAN: a Simple Predict & Align Network for Handwritten Paragraph Recognition
The proposed model performs OCR at paragraph level, without any prior segmentation stage. -
Human Annotated Paragraph Dataset
The dataset used for paragraph recognition in document images by spatial graph convolutional networks (GCN) applied on OCR text boxes. -
Web Synthetic Page Layout
The dataset used for paragraph recognition in document images by spatial graph convolutional networks (GCN) applied on OCR text boxes.