Page Stream Segmentation with Convolutional Neural Nets Combining Textual and Visual Features
This addresses the need for efficient document preservation in archives and mailrooms, representing a strong specific gain in a domain-specific task.
The paper tackles the problem of automatically segmenting streams of scanned page images into multi-page documents, a key step in digitization workflows, and achieves up to 93% accuracy using a convolutional neural network that combines image and text features.
In recent years, (retro-)digitizing paper-based files became a major undertaking for private and public archives as well as an important task in electronic mailroom applications. As a first step, the workflow involves scanning and Optical Character Recognition (OCR) of documents. Preservation of document contexts of single page scans is a major requirement in this context. To facilitate workflows involving very large amounts of paper scans, page stream segmentation (PSS) is the task to automatically separate a stream of scanned images into multi-page documents. In a digitization project together with a German federal archive, we developed a novel approach based on convolutional neural networks (CNN) combining image and text features to achieve optimal document separation results. Evaluation shows that our PSS architecture achieves an accuracy up to 93 % which can be regarded as a new state-of-the-art for this task.