# Attention-based Extraction of Structured Information from Street View Imagery

## TL;DR

This paper introduces a neural network with attention mechanism that effectively extracts structured information from street view images, outperforming previous methods in accuracy and demonstrating versatility across datasets.

## Contribution

The authors propose a novel attention-based neural network model that is simpler, more accurate, and more general than prior approaches for extracting information from street view imagery.

## Key findings

- Achieves 84.2% accuracy on FSNS dataset, surpassing previous state-of-the-art.
- Performs well on Google Street View dataset for business name extraction.
- Deeper CNN feature extractors do not always improve accuracy or speed.

## Abstract

We present a neural network model - based on CNNs, RNNs and a novel attention mechanism - which achieves 84.2% accuracy on the challenging French Street Name Signs (FSNS) dataset, significantly outperforming the previous state of the art (Smith'16), which achieved 72.46%. Furthermore, our new method is much simpler and more general than the previous approach. To demonstrate the generality of our model, we show that it also performs well on an even more challenging dataset derived from Google Street View, in which the goal is to extract business names from store fronts. Finally, we study the speed/accuracy tradeoff that results from using CNN feature extractors of different depths. Surprisingly, we find that deeper is not always better (in terms of accuracy, as well as speed). Our resulting model is simple, accurate and fast, allowing it to be used at scale on a variety of challenging real-world text extraction problems.