Ontological supervision for fine grained classification of Street View storefronts
Authors:
- 1 June 2015
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- No. 10636919,p. 1693-1702
Abstract
Modern search engines receive large numbers of business related, local aware queries. Such queries are best answered using accurate, up-to-date, business listings, that contain representations of business categories. Creating such listings is a challenging task as businesses often change hands or close down. For businesses with street side locations one can leverage the abundance of street level imagery, such as Google Street View, to automate the process. However, while data is abundant, labeled data is not; the limiting factor is creation of large scale labeled training data. In this work, we utilize an ontology of geographical concepts to automatically propagate business category information and create a large, multi label, training dataset for fine grained storefront classification. Our learner, which is based on the GoogLeNet/Inception Deep Convolutional Network architecture and classifies 208 categories, achieves human level accuracy.Keywords
This publication has 19 references indexed in Scilit:
- CNN Features Off-the-Shelf: An Astounding Baseline for Recognition2014
- Video text detection and recognition: Dataset and benchmark2014
- Style-Aware Mid-level Representation for Discovering Visual Connections in Space and Time2013
- Accurate Image Localization Based on Google Maps Street View2010
- 3D Urban Scene Modeling Integrating Recognition and ReconstructionInternational Journal of Computer Vision, 2007
- A review of ontology based query expansionInformation Processing & Management, 2007
- Why Restaurants FailCornell Hospitality Quarterly, 2005
- Semantic integrationACM SIGMOD Record, 2004
- Gradient-based learning applied to document recognitionProceedings of the IEEE, 1998
- Neocognitron: A self-organizing neural network model for a mechanism of pattern recognition unaffected by shift in positionBiological Cybernetics, 1980