Synthetic document generator for annotation-free layout recognition. (August 2022)

• Record Type: Journal Article
• Authors: Raman, Natraj; Shah, Sameena; Veloso, Manuela
• Is Part Of: Pattern recognition. Volume 128(2022)
• Publication Date: 2022-08
• Subjects: Synthetic image generation -- Bayesian network -- Layout analysis; Pattern perception -- Periodicals; Perception des structures -- Périodiques; Patroonherkenning; 006.4
• DOI: 10.1016/j.patcog.2022.108660
• Languages: English
• ISSNs: 0031-3203

Abstract

Highlights: Automatic generation of documents with ground-truths required for layout recognition. Bayesian Network formulation to capture complex and diverse layouts. Stochastic template characterization to encode domain specific similarities and variations. Deep layout detection on synthetic documents matches performance of real documents. Quantitative comparisons, qualitative analysis, ablation studies and visual explanations. Abstract: 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.