Document Image Classification with Intra-Domain Transfer Learning and Stacked Generalization of Deep Convolutional Neural Networks

Document Type

Conference Article

Publication Title

Proceedings - International Conference on Pattern Recognition

Abstract

In this article, a region-based Deep Convolutional Neural Network framework is presented for document structure learning. The contribution of this work involves efficient training of region based classifiers and effective ensembling for document image classification. A primary level of 'inter-domain' transfer learning is used by exporting weights from a pre-trained VGG16 architecture on the ImageNet dataset to train a document classifier on whole document images. Exploiting the nature of region based influence modelling, a secondary level of 'intra-domain' transfer learning is used for rapid training of deep learning models for image segments. Finally, a stacked generalization based ensembling is utilized for combining the predictions of the base deep neural network models. The proposed method achieves state-of-the-art accuracy of 92.21% on the popular RVL-CDIP document image dataset, exceeding the benchmarks set by the existing algorithms.

First Page

3180

Last Page

3185

DOI

10.1109/ICPR.2018.8545630

Publication Date

11-26-2018

Comments

Open Access, Green

This document is currently not available here.

Share

COinS