Saliency-Based Detection of Identity Documents Captured by Smartphones

From LRDE

Abstract

Smartphones have became an easy and convenient mean to acquire documents. In this paper, we focus on the automatic segmentation of identity documents in smartphone photos or videos using visual saliency (VS). VS-based approacheswhich pertain to computer vision, have not be considered yet for this particular task. Here we compare different VS methods, and we propose a new VS scheme, based on a recent distance belonging to the scope of mathematical morphology. We show that the saliency maps we obtain are competitive with state-of-the-art visual saliency methods and, that such approaches are very promising for use in identity document detection and segmentation, even without taking into account any prior knowledge about document contents. In particular they can work in real-time on smartphones.

Documents

LRDE Identity Document Image Database (LRDE IDID)

Data

This dataset is composed of 98 images of identity documents with their detection ground truth.

  • Identity card:
    • Specimen Sweden
    • China (2 persons)
    • Vietnam
    • Germany
    • Benin
  • Passport:
    • China (2 persons)
    • France (3 persons)
    • Vietnam
    • Romania
    • Algeria
    • Specimen UTO
  • Visa:
    • Japan
    • France (4 persons)
    • India (2 persons)
    • United kingdom
    • USA (3 persons)
    • Russia
    • Specimen etats Shengen
  • Titre de sejour:
    • France
  • OFII:
    • France

Sample Image

Original Ground truth
Idid-original small.png
Full resolution
Idid-groundtruth small.png
Full resolution

Copyright Notice

LRDE is the copyright holder of all the images included in the dataset

You are allowed to use these images for research purpose for evaluation and illustration. If so, please specify the following copyright: "Copyright (c) 2018. EPITA Research and Development Laboratory (LRDE)". You are not allowed to redistribute this dataset.

Download

LRDE_IDID_2018.zip

Publication

If this dataset is used in the context of a scientific publication, please cite:

Bibtex (lrde.bib)

@InProceedings{	  movn.18.das,
  author	= {Minh {\^On V\~{u} Ng\d{o}c} and Jonathan Fabrizio and
		  Thierry G\'eraud},
  title		= {Saliency-Based Detection of Identity Documents Captured by
		  Smartphones},
  booktitle	= {Proceedings of the IAPR International Workshop on Document
		  Analysis Systems (DAS)},
  year		= {2018},
  month		= apr,
  address	= {Vienna, Austria},
  abstract	= {Smartphones have became an easy and convenient mean to
		  acquire documents. In this paper, we focus on the automatic
		  segmentation of identity documents in smartphone photos or
		  videos using visual saliency (VS). VS-based approaches,
		  which pertain to computer vision, have not be considered
		  yet for this particular task. Here we compare different VS
		  methods, and we propose a new VS scheme, based on a recent
		  distance belonging to the scope of mathematical morphology.
		  We show that the saliency maps we obtain are competitive
		  with state-of-the-art visual saliency methods and, that
		  such approaches are very promising for use in identity
		  document detection and segmentation, even without taking
		  into account any prior knowledge about document contents.
		  In particular they can work in real-time on smartphones.}
}