Code.zip (3.74 MB)
A Matlab code that runs a proposed biologically-inspired hierarchical architecture for object and scene recognition
softwareposted on 2019-12-12, 10:18 authored by Ali AlameerAli Alameer, Patrick Degenaar, Kianoush Nazarpour
This Matlab code runs our recently-developed model, that is, the elastic net-regularized hierarchical MAX (En-HMAX). With this model, classification accuracies of up to 90% for objects and scenes image datasets were possible. Modelling human experiments, window and scotoma analysis with the En-HMAX model revealed that object and scene recognition are sensitive to the availability of data in the centre and the periphery of the images, respectively. The En-HMAX model adopts a relative order of importance, similar to the human visual system, depending on the image category.