Synthetic Document Generator for Annotation-free Layout Recognition
This addresses the annotation bottleneck for researchers and practitioners in document analysis, though it is an incremental improvement over existing synthetic data methods.
The paper tackled the problem of expensive annotation for document layout recognition by developing a synthetic document generator that creates realistic labeled documents using a Bayesian Network and stochastic templates, and showed that a model trained on synthetic data matches the performance of one trained on real documents.
Analyzing the layout of a document to identify headers, sections, tables, figures etc. is critical to understanding its content. Deep learning based approaches for detecting the layout structure of document images have been promising. However, these methods require a large number of annotated examples during training, which are both expensive and time consuming to obtain. We describe here a synthetic document generator that automatically produces realistic documents with labels for spatial positions, extents and categories of the layout elements. The proposed generative process treats every physical component of a document as a random variable and models their intrinsic dependencies using a Bayesian Network graph. Our hierarchical formulation using stochastic templates allow parameter sharing between documents for retaining broad themes and yet the distributional characteristics produces visually unique samples, thereby capturing complex and diverse layouts. We empirically illustrate that a deep layout detection model trained purely on the synthetic documents can match the performance of a model that uses real documents.