Evaluation of Deep Convolutional Nets for Document Image Classification and Retrieval
Preprint
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 hand-crafted alternatives. Experiments also 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, useful for training new CNNs for document analysis.Keywords
All Related Versions
This publication has 22 references indexed in Scilit:
- Structural similarity for document image classification and retrievalPattern Recognition Letters, 2014
- Neural Codes for Image Retrieval2014
- Multi-scale Orderless Pooling of Deep Convolutional Activation Features2014
- 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
- Modeling the Shape of the Scene: A Holistic Representation of the Spatial EnvelopeInternational Journal of Computer Vision, 2001
- Classification of document pages using structure-based featuresInternational Journal on Document Analysis and Recognition (IJDAR), 2001
- Comparison and Classification of Documents Based on Layout SimilarityInformation Retrieval Journal, 2000
- 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