DELINE8K: A Synthetic Data Pipeline for the Semantic Segmentation of Historical Documents
This work addresses the need for better synthetic data to facilitate document analysis tasks like OCR and form classification, though it is incremental in nature.
The authors tackled the problem of limited class variety and document diversity in synthetic datasets for document semantic segmentation by introducing the DELINE8K dataset, which improved performance on the NAFSS benchmark.
Document semantic segmentation is a promising avenue that can facilitate document analysis tasks, including optical character recognition (OCR), form classification, and document editing. Although several synthetic datasets have been developed to distinguish handwriting from printed text, they fall short in class variety and document diversity. We demonstrate the limitations of training on existing datasets when solving the National Archives Form Semantic Segmentation dataset (NAFSS), a dataset which we introduce. To address these limitations, we propose the most comprehensive document semantic segmentation synthesis pipeline to date, incorporating preprinted text, handwriting, and document backgrounds from over 10 sources to create the Document Element Layer INtegration Ensemble 8K, or DELINE8K dataset. Our customized dataset exhibits superior performance on the NAFSS benchmark, demonstrating it as a promising tool in further research. The DELINE8K dataset is available at https://github.com/Tahlor/deline8k.