Computational Neuroscience
Naser Sadeghnejad; Mehdi Ezoji; Reza Ebrahimpour
Volume 14, Issue 1 , May 2020, , Pages 69-79
Abstract
Object recognition is one of the main cognitive abilities of human and animals. Human visual system, as a fast and accurate system can be a source of inspiration for the computational models of object recognition. Studies on the human visual system have emphasized its processing over time, whereas it ...
Read More
Object recognition is one of the main cognitive abilities of human and animals. Human visual system, as a fast and accurate system can be a source of inspiration for the computational models of object recognition. Studies on the human visual system have emphasized its processing over time, whereas it is not considered in the conventional computational models of object recognition. In this paper, we attempt to present a time-based multilevel model for object recognition. In the first layer of the model, the input image information is sent to the next layer in a temporal representation. In the middle layer of the model, a deep neural network is used as a feature extractor. Finally, in contrast to the popular computational models for object recognition, a decision-making model such as drift-diffusion model is proposed based on the neuronal decision-making mechanisms in the brain. In other words, adaption to the human visual system has been considered in all of three layers. Several experiments have been conducted to evaluate the performance of the proposed computational model in object recognition. The experimental results show that as the input image becomes more complicated, noise increases, or occlusion occurs, the performance/reaction time of the model decreases/increases, which is consistent with the behavior of human visual system. The performance of the model for object recognition and base-level categorization is also investigated for application of the original images and the inverted images. The results show the difference between the processes of the object recognition and base-level categorization, which is consistent with the behavior of human visual system reported in the referenced papers.