PageNet: Page Boundary Extraction in Historical Handwritten Documents
This addresses the need for automated preprocessing in document digitization, particularly for historical archives, but is incremental as it applies existing deep learning methods to a specific domain task.
The paper tackles the problem of removing border noise from digitized historical handwritten document images by developing PageNet, a deep learning system that segments the main page region, achieving over 94% mean intersection over union across four datasets and approaching human performance on two of them.
When digitizing a document into an image, it is common to include a surrounding border region to visually indicate that the entire document is present in the image. However, this border should be removed prior to automated processing. In this work, we present a deep learning based system, PageNet, which identifies the main page region in an image in order to segment content from both textual and non-textual border noise. In PageNet, a Fully Convolutional Network obtains a pixel-wise segmentation which is post-processed into the output quadrilateral region. We evaluate PageNet on 4 collections of historical handwritten documents and obtain over 94% mean intersection over union on all datasets and approach human performance on 2 of these collections. Additionally, we show that PageNet can segment documents that are overlayed on top of other documents.