dhSegment: A generic deep-learning approach for document segmentation

Abstract

In recent years there have been multiple successful attempts tackling document processing problems separately by designing task specific hand-tuned strategies. We argue that the diversity of historical document processing tasks prohibits to solve them one at a time and shows a need for designing generic approaches in order to handle the variability of historical series. In this paper, we address multiple tasks simultaneously such as page extraction, baseline extraction, layout analysis or multiple typologies of illustrations and photograph extraction. We propose an open-source implementation of a CNN-based pixel-wise predictor coupled with task dependent post-processing blocks. We show that a single CNN-architecture can be used across tasks with competitive results. Moreover most of the task-specific post-precessing steps can be decomposed in a small number of simple and standard reusable operations, adding to the flexibility of our approach.

Cited by in corpus (14)

• End-to-end Handwritten Paragraph Text Recognition Using a Vertical Attention Network
• DAN: a Segmentation-free Document Attention Network for Handwritten Document Recognition
• Multiple Document Datasets Pre-training Improves Text Line Detection With Deep Neural Networks
• Boosting offline handwritten text recognition in historical documents with few labeled lines
• docExtractor: An off-the-shelf historical document element extraction
• HORAE: an annotated dataset of books of hours
• A Fast Fully Octave Convolutional Neural Network for Document Image Segmentation
• Efficient few-shot learning for pixel-precise handwritten document layout analysis
• Large Scale Genealogical Information Extraction From Handwritten Quebec Parish Records
• HRCenterNet: An Anchorless Approach to Chinese Character Segmentation in Historical Documents
• End-to-End Hierarchical Relation Extraction for Generic Form Understanding
• Normalized vs Diplomatic Annotation: A Case Study of Automatic Information Extraction from Handwritten Uruguayan Birth Certificates
• Including Keyword Position in Image-based Models for Act Segmentation of Historical Registers
• Synthesis in Style: Semantic Segmentation of Historical Documents using Synthetic Data