Synthetic document generator for annotation-free layout recognition
作者：
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.
摘要
•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.
论文关键词：Synthetic image generation,Bayesian network,Layout analysis
论文评审过程：Received 11 November 2021, Revised 23 January 2022, Accepted 19 March 2022, Available online 24 March 2022, Version of Record 29 March 2022.
论文官网地址：https://doi.org/10.1016/j.patcog.2022.108660
