Identity documents classification as an image classification problem

Ronan Sicre 1 Ahmad Awal 2 Teddy Furon 1
1 LinkMedia - Creating and exploiting explicit links between multimedia fragments
Inria Rennes – Bretagne Atlantique , IRISA_D6 - MEDIA ET INTERACTIONS
Abstract : This paper studies the classification of images of identification documents. This problem is critical in various security context where proposed system must offer high performances. We address this challenge as an image classification problem, which has received a large attention from the scientific community. Several image classification methods are evaluated and we report interesting results allowing a better understanding of the specificity of such data. We are especially interested in deep learning approaches, showing good transfer capabilities and high performances.
Complete list of metadatas

Cited literature [26 references]  Display  Hide  Download

https://hal.inria.fr/hal-01503541
Contributor : Ronan Sicre <>
Submitted on : Thursday, April 27, 2017 - 5:09:19 PM
Last modification on : Thursday, November 15, 2018 - 11:59:01 AM
Long-term archiving on : Friday, July 28, 2017 - 1:35:27 PM

File

id_doc_classif2.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-01503541, version 2

Citation

Ronan Sicre, Ahmad Awal, Teddy Furon. Identity documents classification as an image classification problem. [Technical Report] RT-0488, Inria Rennes - Bretagne Atlantique; IRISA; AriadNext. 2017. ⟨hal-01503541v2⟩

Share

Metrics

Record views

547

Files downloads

2084