Deep Neural Networks for Text Detection and Recognition in Historical Maps

Jerod Weinman, Ziwen Chen, Ben Gafford, Nathan Gifford, Abyaya Lamsal, Liam Niehus-Staab

Abstract: We introduce deep convolutional and recurrent neural networks for end-to-end, open-vocabulary text reading on historical maps. A text detection network predicts word bounding boxes at arbitrary orientations and scales. The detected word images are then normalized for a robust recognition network. Because accurate recognition requires large volumes of training data but manually labeled data is relatively scarce, we introduce a dynamic map text synthesizer providing a practically infinite stream of training data. Results are evaluated on a labeled data set of 30 maps featuring over 30,000 text labels.