This paper presents an approach for real-time training and testing for document image classification. In pro- duction environments, it is crucial to perform accurate and (time-)efficient training. Existing deep learning approaches for classifying documents do not meet these requirements, as they require much time for training and fine-tuning the deep architec- tures. Motivated from Computer Vision, we propose a two-stage approach. The first stage trains a deep network that works as feature extractor and in the second stage, Extreme Learning Ma- chines (ELMs) are used for classification. The proposed approach outperforms all previously reported structural and deep learning based methods with a final accuracy of 83.24 % on Tobacco- 3482 dataset, leading to a relative error reduction of 25 % when compared to a previous Convolutional Neural Network (CNN) based approach (DeepDocClassifier). More importantly, the training time of the ELM is only 1.176 seconds and the overall prediction time for 2, 482 images is 3.066 seconds. As such, this novel approach makes deep learning-based document classification suitable for large-scale real-time applications.
Date: Nov 5, 2017
Author: Andreas Kölsch, Muhammad Zeshan Afzal, Markus Ebbecke, Marcus Liwicki
Categories: projectdocument classificationdeep learning architectures