Adapting off-the-shelf CNNs for word spotting & recognition
Authors:
- 1 August 2015
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 9, 986-990
Abstract
The word spotting approach is extremely useful for searching and annotating documents for which robust recognizers are unavailable. Traditionally, hand-designed features were used to represent the word images for spotting. In this paper, we learn a data-driven representation for word-images from Convolutional Neural Networks (CNNs). Previous approaches that learn deep neural networks for a particular task/dataset are difficult to design and train for generic word spotting. Instead, by “adapting” a CNN trained for a different problem, we show tremendous speedup in the training phase. Our experiments show that features extracted from an adapted-CNN handsomely outperform hand-designed features on both spotting and recognition tasks for printed (English and Telugu) and handwritten (IAM) document collections.Keywords
This publication has 12 references indexed in Scilit:
- Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation2014
- CNN Features Off-the-Shelf: An Astounding Baseline for Recognition2014
- Whole is Greater than Sum of Parts: Recognizing Scene Text Words2013
- Feature Extraction with Convolutional Neural Networks for Handwritten Word Recognition2013
- Large scale document image retrieval by automatic word annotationInternational Journal on Document Analysis and Recognition (IJDAR), 2013
- An Efficient Framework for Searching Text in Noisy Document Images2012
- Convolutional Neural Network Committees for Handwritten Character Classification2011
- Word spotting for historical documentsInternational Journal on Document Analysis and Recognition (IJDAR), 2006
- Best practices for convolutional neural networks applied to visual document analysis2005
- Gradient-based learning applied to document recognitionProceedings of the IEEE, 1998