An empirical evaluation of local descriptors in object recognition

Feature descriptors play a vital role in object recognition. In this paper, an empirical evaluation of various local descriptors used for object recognition is presented. COIL-100 dataset is used to perform the experimental analysis. The descriptors are evaluated on the basis of the number (size) of features extracted and the time taken for their execution. Experimental results using these descriptors are shown with conclusion and future research directions.