Combining MSCR detector and PCA-SIFT descriptor for scene recognition

This paper introduces a novel scene recognition algorithm to perform reliable scene recognition. Firstly, to construct the maximally stable regions, we exploit the maximally stable color regions (MSCR) detector for improving the identification of stable regions. Secondly, each detected region is processed properly by using the method of mathematics morphology. Finally, the descriptor is computed by using the Principal Components Analysis (PCA) based scale invariant feature transform (SIFT) descriptors, with the detected MSCR regions as input. Our experiments demonstrate that this algorithm wins high recognition accuracy, is more robust to image deformations and is both significantly more accurate and much faster than the standard SIFT descriptor based algorithm. Also we compare our algorithm to the global appearance based method, and show through experiments in both indoor and outdoor environments that our approach performs better.