SPAN: a Simple Predict & Align Network for Handwritten Paragraph Recognition
This addresses the problem of simplifying and improving efficiency in document analysis for researchers and practitioners by eliminating the need for segmentation steps, though it is incremental as it builds on existing OCR methods.
The paper tackles unconstrained handwriting recognition by proposing SPAN, an end-to-end recurrence-free Fully Convolutional Network that performs OCR at the paragraph level without prior segmentation, achieving competitive results on RIMES, IAM, and READ 2016 datasets.
Unconstrained handwriting recognition is an essential task in document analysis. It is usually carried out in two steps. First, the document is segmented into text lines. Second, an Optical Character Recognition model is applied on these line images. We propose the Simple Predict & Align Network: an end-to-end recurrence-free Fully Convolutional Network performing OCR at paragraph level without any prior segmentation stage. The framework is as simple as the one used for the recognition of isolated lines and we achieve competitive results on three popular datasets: RIMES, IAM and READ 2016. The proposed model does not require any dataset adaptation, it can be trained from scratch, without segmentation labels, and it does not require line breaks in the transcription labels. Our code and trained model weights are available at https://github.com/FactoDeepLearning/SPAN.