Full Page Handwriting Recognition via Image to Sequence Extraction
This addresses the problem of recognizing unconstrained handwritten documents for applications like digitizing historical texts or educational assessments, representing a strong incremental improvement.
The authors tackled full-page handwritten text recognition without segmentation, achieving state-of-the-art results on the IAM dataset and outperforming commercial HTR APIs on real-world scans with complex layouts and symbols.
We present a Neural Network based Handwritten Text Recognition (HTR) model architecture that can be trained to recognize full pages of handwritten or printed text without image segmentation. Being based on Image to Sequence architecture, it can extract text present in an image and then sequence it correctly without imposing any constraints regarding orientation, layout and size of text and non-text. Further, it can also be trained to generate auxiliary markup related to formatting, layout and content. We use character level vocabulary, thereby enabling language and terminology of any subject. The model achieves a new state-of-art in paragraph level recognition on the IAM dataset. When evaluated on scans of real world handwritten free form test answers - beset with curved and slanted lines, drawings, tables, math, chemistry and other symbols - it performs better than all commercially available HTR cloud APIs. It is deployed in production as part of a commercial web application.