Evaluation of deep convolutional nets for document image classification and retrieval
Authors:
Top Cited Papers
- 1 August 2015
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 991-995
Abstract
This paper presents a new state-of-the-art for document image classification and retrieval, using features learned by deep convolutional neural networks (CNNs). In object and scene analysis, deep neural nets are capable of learning a hierarchical chain of abstraction from pixel inputs to concise and descriptive representations. The current work explores this capacity in the realm of document analysis, and confirms that this representation strategy is superior to a variety of popular handcrafted alternatives. Extensive experiments show that (i) features extracted from CNNs are robust to compression, (ii) CNNs trained on non-document images transfer well to document analysis tasks, and (iii) enforcing region-specific feature-learning is unnecessary given sufficient training data. This work also makes available a new labelled subset of the IIT-CDIP collection, containing 400,000 document images across 16 categories.Keywords
All Related Versions
This publication has 15 references indexed in Scilit:
- Convolutional Neural Networks for Document Image Classification2014
- Structural similarity for document image classification and retrievalPattern Recognition Letters, 2014
- Unsupervised Classification of Structurally Similar Document Images2013
- Digital Libraries and Document Image Retrieval Techniques: A Survey2011
- Building a test collection for complex document information processing2006
- A survey of document image classification: problem statement, classifier architecture and performance evaluationInternational Journal on Document Analysis and Recognition (IJDAR), 2006
- Beyond Bags of Features: Spatial Pyramid Matching for Recognizing Natural Scene Categories2006
- Form classification using DP matching2000
- Twenty years of document image analysis in PAMIIEEE Transactions on Pattern Analysis and Machine Intelligence, 2000
- Gradient-based learning applied to document recognitionProceedings of the IEEE, 1998