Deepdocclassifier: Document classification with deep Convolutional Neural Network
Authors:
- 1 August 2015
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1111-1115
Abstract
This paper presents a deep Convolutional Neural Network (CNN) based approach for document image classification. One of the main requirement of deep CNN architecture is that they need huge number of samples for training. To overcome this problem we adopt a deep CNN which is trained using big image dataset containing millions of samples i.e., ImageNet. The proposed work outperforms both the traditional structure similarity methods and the CNN based approaches proposed earlier. The accuracy of the proposed approach with merely 20 images per class outperforms the state-of-the-art by achieving classification accuracy of 68.25%. The best results on Tobbacoo-3428 dataset show that our proposed method outperforms the state-of-the-art method by a significant margin and achieved a median accuracy of 77.6% with 100 samples per class used for training and validation.Keywords
This publication has 10 references indexed in Scilit:
- Caffe2014
- Convolutional Neural Networks for Document Image Classification2014
- Structural similarity for document image classification and retrievalPattern Recognition Letters, 2014
- Pedestrian Detection with Unsupervised Multi-stage Feature Learning2013
- Building a test collection for complex document information processing2006
- Clustering and classification of document structure-a machine learning approach2002
- Fine-grained document genre classification using first order random graphs2002
- Form classification using DP matching2000
- User-defined template for identifying document type and extracting information from documents1999
- Gradient-based learning applied to document recognitionProceedings of the IEEE, 1998