End-to-end Handwritten Paragraph Text Recognition Using a Vertical Attention Network
share
Unconstrained handwritten text recognition remains challenging for computer vision systems. Paragraph text recognition is traditionally achieved by two models: the first one for line segmentation and the second one for text line recognition. We propose a unified end-to-end model using hybrid attention to tackle this task. We achieve state-of-the-art character error rate at line and paragraph levels on three popular datasets: 1.90 3.63 using any segmentation label contrary to the standard approach. Our code and trained model weights are available at https://github.com/FactoDeepLearning/VerticalAttentionOCR.
READ FULL TEXT