Abstract
It is debated whether the representation of objects in inferior temporal (IT) cortex is distributed over activities of many neurons or there are restricted islands of neurons responsive to a specific set of objects. There are lines of evidence demonstrating that fusiform face area (FFA-in human) processes information related to specialized object recognition (here we say within category object recognition such as face identification). Physiological studies have also discovered several patches in monkey ventral temporal lobe that are responsible for facial processing. Neuronal recording from these patches shows that neurons are highly selective for face images whereas for other objects we do not see such selectivity in IT. However, it is also well-supported that objects are encoded through distributed patterns of neural activities that are distinctive for each object category. It seems that visual cortex utilize different mechanisms for between category object recognition (e.g., face vs. non-face objects) vs. within category object recognition (e.g., two different faces). In this study, we address this question with computational simulations. We use two biologically inspired object recognition models and define two experiments which address these issues. The models have a hierarchical structure of several processing layers that simply simulate visual processing from V1 to aIT. We show, through computational modeling, that the difference between these two mechanisms of recognition can underlie the visual feature and extraction mechanism. It is argued that in order to perform generic and specialized object recognition, visual cortex must separate the mechanisms involved in within category from between categories object recognition. High recognition performance in within category object recognition can be guaranteed when class-specific features with intermediate size and complexity are extracted. However, generic object recognition requires a distributed universal dictionary of visual features in which the size of features does not have significant difference.
Highlights
Object recognition is rapidly and robustly performed by human and primate visual system
The results show that face identification, as a within category object recognition task, requires class-specific features, extracted from individual faces, to distinguish between very similar objects with fine differences in features within a class, but we need to increase the size of prototype up to intermediate sizes to achieve higher recognition performance
We have selected the Stable model (Rajaei et al, 2012) and HMAX model (Serre et al, 2007) to examine how different visual features perform in specialized vs. generic object recognition
Summary
Object recognition is rapidly and robustly performed by human and primate visual system. This task is still a real computational challenge for most computer vision systems despite recent amazing progresses (e.g., Serre et al, 2007; Coates et al, 2012; Krizhevsky et al, 2012). We can effortlessly and swiftly recognize virtually unlimited numbers of objects categories even in cluttered backgrounds with changes in illumination, viewpoint, position, and scale. We can and accurately recognize objects within a specific category that objects have very similar features (e.g., two similar faces) even in rotated views. Decades of studies on this remarkable system have revealed that object recognition is performed by the ventral visual pathway (Logothetis and Sheinberg, 1996). Object images, which are first projected on the retina, are spatially sampled based on a cortical magnification factor (Tootell et al, 1982; Van Essen et al, 1984)
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
