Skip to Main content Skip to Navigation
Conference papers

Automatic Synthetic Document Image Generation using Generative Adversarial Networks: Application in Mobile-Captured Document Analysis

Abstract : In this paper, we propose a method using Generative Adversarial Networks for automatically synthesizing document images that are similar to real printed documents captured by mobile phone's camera in unconstrained environment. We focus on the simulation of image defects for unconstrained mobile image acquisition procedure (non-uniform illumination, defocusing, optical and mechanical deformations, vibrations, noise in electronic components,...). Our approach is proven to be low-cost as it only requires a collection of real document images without any annotation. Experimental results show the effectiveness of our approach to improve OCR (Optical Character Recognition) recognition rate in a mobile-captured document images framework. Although in this paper, we focus on modern printed document images, our proposed approach could be extended to another type of documents, including historical one.
Document type :
Conference papers
Complete list of metadatas

https://hal.univ-lorraine.fr/hal-02965123
Contributor : Salvatore Tabbone <>
Submitted on : Tuesday, October 13, 2020 - 7:38:19 AM
Last modification on : Thursday, October 15, 2020 - 4:07:56 AM

Identifiers

Collections

Citation

Quang Anh Bui, David Mollard, Salvatore Tabbone. Automatic Synthetic Document Image Generation using Generative Adversarial Networks: Application in Mobile-Captured Document Analysis. 2019 International Conference on Document Analysis and Recognition (ICDAR), Sep 2019, Sydney, Australia. pp.393-400, ⟨10.1109/ICDAR.2019.00070⟩. ⟨hal-02965123⟩

Share

Metrics

Record views

10