End-to-End Interpretation of the French Street Name Signs Dataset

  • Raymond Smith
  • Chunhui Gu
  • Dar-Shyang Lee
  • Huiyi Hu
  • Ranjith Unnikrishnan
  • Julian Ibarz
  • Sacha Arnoud
  • Sophia Lin
Conference paper

DOI: 10.1007/978-3-319-46604-0_30

Part of the Lecture Notes in Computer Science book series (LNCS, volume 9913)
Cite this paper as:
Smith R. et al. (2016) End-to-End Interpretation of the French Street Name Signs Dataset. In: Hua G., Jégou H. (eds) Computer Vision – ECCV 2016 Workshops. ECCV 2016. Lecture Notes in Computer Science, vol 9913. Springer, Cham

Abstract

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.

Keywords

Deep networks End-to-end networks Image dataset Multiview dataset 

Copyright information

© Springer International Publishing Switzerland 2016

Authors and Affiliations

  • Raymond Smith
    • 1
  • Chunhui Gu
    • 1
  • Dar-Shyang Lee
    • 1
  • Huiyi Hu
    • 1
  • Ranjith Unnikrishnan
    • 1
  • Julian Ibarz
    • 1
  • Sacha Arnoud
    • 1
  • Sophia Lin
    • 1
  1. 1.Google Inc.Mountain ViewUSA

Personalised recommendations