Indoor/outdoor image classification using GIST image features and neural network classifiers

We show that holistic image features, specifically GIST, can be used for semantic scene categorization. In our study, the problem of indooroutdoor scene classification is addressed. We first propose a simple yet efficient pipeline in which the GIST vector of an image is initially computed. For the classification task, a feedforward neural network is trained with a comprehensive training dataset. The evaluation shows that our approach outperforms many state of the art algorithms in terms of classification accuracy. Due to computational limitation on mobile devices, the final classification pipeline was deployed on an Amazon EC2 server for a live smartphone application.