A proposal of biologically inspired hierarchical approach to object recognition

In this article a biologically-inspired algorithm for object recognition is presented. The approach is based on a hierarchical HMAX cortex model that was initially proposed by Riesenhuber and Poggio [12] and later extended by Serre et al [13]. The results show that despite the modification that were undertaken to simplify the HMAX model (in order to make it feasible for a real-time solutions) it is possible to achieve high effectiveness for a one-class detection problems. Moreover, it is also demonstrated how the proposed algorithm can be successfully deployed on a low-cost Android smartphone.