Indoor-outdoor image classification

Abstract

We show how high-level scene properties can be inferred from classification of low-level image features, specifically for the indoor-outdoor scene retrieval problem. We systematically studied the features of: histograms in the Ohta color space; multiresolution, simultaneous autoregressive model parameters; and coefficients of a shift-invariant DCT. We demonstrate that performance is improved by computing features on subblocks, classifying these subblocks, and then combining these results in a way reminiscent of stacking. State of the art single-feature methods are shown to result in about 75-86% performance, while the new method results in 90.3% correct classification, when evaluated on a diverse database of over 1300 consumer images provided by Kodak.