Fine-grained classification of identity document types with only one example
- 1 May 2015
- conference paper
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 126-129
- https://doi.org/10.1109/mva.2015.7153149
Abstract
In this paper, we tackle the task of recognizing types of partly very similar identity documents using state-of-the-art visual recognition approaches. Given a scanned document, the goal is to identify the country of issue, the type of document, and its version. Whereas recognizing the individual parts of a document with known standardized layout can be done reliably, identifying the type of a document and therefore also its layout is a challenging problem due to the large variety of documents. In our paper, we develop and evaluate different techniques for this application including feature representations based on recent achievements with convolutional neural networks. On a dataset with 74 different classes and using only one training image per class, our best approach achieves a mean class-wise accuracy of 97.7%.Keywords
This publication has 11 references indexed in Scilit:
- A fully visual based business document classification systemPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2014
- Unsupervised Classification of Structurally Similar Document ImagesPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2013
- Visual appearance based document image classificationPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2010
- Object Detection with Discriminatively Trained Part-Based ModelsIeee Transactions On Pattern Analysis and Machine Intelligence, 2009
- Representing shape with a spatial pyramid kernelPublished by Association for Computing Machinery (ACM) ,2007
- Image classification: Classifying distributions of visual featuresPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2006
- Document page similarity based on layout visual saliency: application to query by example and document classificationPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2005
- Hidden tree markov models for document image classificationIeee Transactions On Pattern Analysis and Machine Intelligence, 2003
- Fine-grained document genre classification using first order random graphsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Classification of document pages using structure-based featuresInternational Journal on Document Analysis and Recognition (IJDAR), 2001