Novel patch selection based on object detection in HMAX for natural image classification

The human visual system (HVS) can effectively recognize objects in complex natural scenes with high speed and accuracy. Many models have been proposed based on HVS among which HMAX is one of the superior models. In HMAX, the random extraction of a large volume of training samples, called patches, has two drawbacks. First, patches from background, in addition to high computational cost, can produce wrong output. Second, patches with low information from objects may provide poor performance. In this paper, an optimum method, with two steps, is proposed to select patches with high discriminative information. First, a pool of patches is extracted from objects based on an unsupervised object detection method. Second, patches with high discriminative information were selected from the pool based on patch ranking. Further, complement of optimum patch for each class is considered as a new patch for other classes to increase the recognition rate. Experimental results with Caltech5, Caltech101 and Graz-01 databases show that the proposed model provides a significant performance improvement over the HMAX and other state-of-the-art models, in terms of speed, sensitivity, specificity and classification accuracy.