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.
Biomimetics
Hiwa Sufikarimi; Karim Mohammadi
Volume 11, Issue 4 , February 2018, , Pages 337-349
Abstract
In this paper, we tried to present a robust and reliable approach to object recognition by inspiring human visual system. A famous model, inspiring mammalian visual system, is HMAX (Hierarchical Model and X). It shows significant accuracy rates on object recognition tasks. However, there are some differences ...
Read More
In this paper, we tried to present a robust and reliable approach to object recognition by inspiring human visual system. A famous model, inspiring mammalian visual system, is HMAX (Hierarchical Model and X). It shows significant accuracy rates on object recognition tasks. However, there are some differences between this model and human visual system. Indeed cortex's functions are not properly modeled. Unrepeatability under fixed conditions, redundancy, high computing load and being slow are some drawbacks of HMAX. By modeling the secondary visual cortex and adding to the HMAX, we tried to introduce a more accurate model of the human visual system and cover the drawbacks of the previous models. The proposed approach functionally mimics the secondary visual cortex. Attending to high-level features, selecting discriminative and repeatable features, it has higher performance than standard HMAX. The added parts have negligible computation load. Therefore, it does not slow down this model. On the contrary, by selecting brief and useful features, the speed of the model is increased. The proposed approach is compared to the standard HMAX in terms of speed and accuracy rate. The results showed the advantage of proposed approach rather than the standard HMAX. In addition, the effect of the number of features and training images on their performance was shown. It is shown that the proposed approach has a better performance than the standard HMAX especially when the number of feature and training images is small.
Biological Computer Modeling / Biological Computer Simulation
Mohammad Jazlaeiyan; Hadi Shahriar Shahhoseini
Volume 8, Issue 4 , February 2015, , Pages 371-383
Abstract
Human visual system operates superior than best machine vision systems in object recognition. So, researchers in machine vision and neuroscience try to model human visual system in order to employ it in machine. HMAX is one of the best operating models in this area. It is based on the function of brain ...
Read More
Human visual system operates superior than best machine vision systems in object recognition. So, researchers in machine vision and neuroscience try to model human visual system in order to employ it in machine. HMAX is one of the best operating models in this area. It is based on the function of brain cells in the ventral stream of visual cortex and contains four computational layers. In the learning stage, many image partitions called image patches are extracted randomly with different sizes from training images. This random selection of image patches is one of the drawbacks of HMAX which decreases the performance and increases the computational complexity of the algorithm. In this paper, a novel patch selection from the set of random patches is proposed. In this method, using a recursive approach, optimal patches are selected from optimal features of training images by mutual information maximization feature selection. The performance of proposed algorithm in binary classification (existence or non-existence of objects in the images) is compared with HMAX and the superiority is proved.