End-to-End Interpretation of the French Street Name Signs Dataset
This work addresses the problem of street name extraction for mapping and navigation applications, but it is incremental as it applies existing deep learning methods to a new dataset.
The authors introduced the French Street Name Signs (FSNS) Dataset, a large-scale collection of over a million images of street name signs from France, and presented an end-to-end network for extracting text from these images, achieving results on this new dataset.
We introduce the French Street Name Signs (FSNS) Dataset consisting of more than a million images of street name signs cropped from Google Street View images of France. Each image contains several views of the same street name sign. Every image has normalized, title case folded ground-truth text as it would appear on a map. We believe that the FSNS dataset is large and complex enough to train a deep network of significant complexity to solve the street name extraction problem "end-to-end" or to explore the design trade-offs between a single complex engineered network and multiple sub-networks designed and trained to solve sub-problems. We present such an "end-to-end" network/graph for Tensor Flow and its results on the FSNS dataset.