TY  - CONF
AU  - Suman Ghosh
AU  - Ernest Valveny
A2  - ICDAR
PY  - 2017//
TI  - R-PHOC: Segmentation-Free Word Spotting using CNN
BT  - 14th International Conference on Document Analysis and Recognition
KW  - Convolutional neural network
KW  - Image segmentation
KW  - Artificial neural network
KW  - Nearest neighbor search
N2  - arXiv:1707.01294This paper proposes a region based convolutional neural network for segmentation-free word spotting. Our network takes as input an image and a set of word candidate bound- ing boxes and embeds all bounding boxes into an embedding space, where word spotting can be casted as a simple nearest neighbour search between the query representation and each of the candidate bounding boxes. We make use of PHOC embedding as it has previously achieved significant success in segmentation- based word spotting. Word candidates are generated using a simple procedure based on grouping connected components using some spatial constraints. Experiments show that R-PHOC which operates on images directly can improve the current state-of- the-art in the standard GW dataset and performs as good as PHOCNET in some cases designed for segmentation based word spotting.
L1  - http://refbase.cvc.uab.es/files/GhV2017a.pdf
UR  - http://dx.doi.org/10.1109/ICDAR.2017.136
N1  - DAG; 600.121
ID  - Suman Ghosh2017
ER  -