Real-Time Document Image Classification using Deep CNN and Extreme Learning Machines

TL;DR

This paper introduces a fast, two-stage deep learning approach combining CNN feature extraction with Extreme Learning Machines for real-time document image classification, achieving high accuracy and significantly reduced training time.

Contribution

It proposes a novel two-stage method that leverages deep CNN features and ELMs, enabling real-time document classification with high accuracy and minimal training time.

Findings

Achieved 83.24% accuracy on Tobacco-3482 dataset.

Reduced training time of ELM to 1.176 seconds.

Overall prediction time for 2,482 images is 3.066 seconds.

Abstract

This paper presents an approach for real-time training and testing for document image classification. In production 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 architectures. 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 Machines (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.