Local co-occurrence features in subspace obtained by KPCA of local blob visual words for scene classification

This paper presents a scene classification method based on local co-occurrence in a KPCA space of local blob words. Scene classification based on local correlation of binarized projection lengths in subspaces obtained by Kernel Principal Component Analysis (KPCA) of visual words has been recently proposed, and its effectiveness has been demonstrated. However, the local correlation of two binary features (0 or 1) becomes 1 only when both features take a value of 1. The local correlation becomes 0 in all other cases ((0,1), (1,0) and (0,0)), which might lead to the loss of useful information for effective classification. In this study, all combinations of co-occurrence of binary features are used instead of local correlation. We conducted the experiments using a database containing 13 scene categories and found that the proposed method using local co-occurrence features achieves an accuracy of more than 84%, which is higher than the accuracy of conventional methods based on local correlation features.

► Local co-occurrence feature is proposed to use the information discarded by local correlation of binary features.
► Local blob visual words and local norm normalization also improve the accuracy.
► The accuracy achieves more than 84% by these three devices.