Active object recognition using hierarchical local-receptive-field-based extreme learning machine

In this paper, we develop a meihod to actively recognize objects by choosing a sequence of actions for an active camera thai helps to discriminate between the objects in a dataset. Hierarchical local-receptive-field-based extreme learning machine architecture is developed to jointly learn the state representation and the reinforcement learning strategy. Experimental validation on the publicly available GERMS dataset shows the effectiveness of the proposed method.