This article explains the improvement of Google Maps through the process of a deep learning model. The model, created by Google’s Ground Truth team, streamlines developers’ abilities to seamlessly identify street names, exemplified by the French Street Names data sets referred to in the article. The deep learning process proves to provide an easier way to yield accurate mapping.
- Google maps wants to create a system to automatically extract information from their street view photos.
- Factors like distortion, occlusions, directional blur, cluttered background or different viewpoints make the extraction of text from natural scenes more challenging
- Deep learning model’s goal is to automatically normalize text to be consistent with naming conventions, and ignores extraneous text that’s not relevant for the data analytics.
“The new deep neural network model, now publicly available for use by developers, achieved a higher deep neural network (84.2%) in reading street names out of Street View images from the French Street Name Signs (FSNS) dataset.”