Cutting the Error by Half: Investigation of Very Deep CNN and Advanced Training Strategies for Document Image Classification

We present an exhaustive investigation of recent Deep Learning architectures, algorithms, and strategies for the task of document image classification to finally reduce the error by more than half. Existing approaches, such as the DeepDoc-Classifier, apply standard Convolutional Network architectures with transfer learning from the object recognition domain. The contribution of the paper is threefold: First, it investigates recently introduced very deep neural network architectures (GoogLeNet, VGG, ResNet) using transfer learning (from real images). Second, it proposes transfer learning from a huge set of document images, i.e. 400; 000 documents. Third, it analyzes the impact of the amount of training data (document images) and other parameters to the classification abilities. We use two datasets, the Tobacco-3482 and the large-scale RVL-CDIP dataset. We achieve an accuracy of 91:13% for the Tobacco-3482 dataset while earlier approaches reach only 77:6%. Thus, a relative error reduction of more than 60% is achieved. For the large dataset RVL-CDIP, an accuracy of 90:97% is achieved, corresponding to a relative error reduction of 11:5%.

Project Details

Date: May 23, 2017

Author: Muhammad Zeshan Afzal, Andreas Kölsch, Sheraz Ahmed, Marcus Liwicki

Categories: projectdocument classificationdeep learning architectures

Website: https://arxiv.org/abs/1704.03557

Related Works.

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

Cutting the Error by Half: Investigation of Very Deep CNN and Advanced Training Strategies for Document Image Classification

TAC-GAN - Text Conditioned Auxiliary Classifier Generative Adversarial Network

Multilevel Context Representation for Improving Object Recognition

Music Information Retrieval

About

We believe that creativity comes with freedom and to solve challenging problems in AI we need to have freedom and creative thinking. We provide an unconstrained environment to highly motivated students to do whatever that comes to their minds and explore deep learning.

Social Links

Our Bunker

Rooms 36-(307/309/310),
TU Kaiserslautern,
Paul-Ehrlich-Str. 36,
67663 Kaiserslautern,
Germany