Inferotemporal network model for 3D object recognition

Author

Efremova, Natalia ; Asakura, Nobuhiko ; Inui, Toshio ; Abdikeev, Niyaz

Author_Institution

Dept. of Intell. Sci. & Technol., Kyoto Univ., Kyoto, Japan

fYear

2011

Firstpage

555

Lastpage

560

Abstract

One of the essential cognitive abilities of the human brain is the ability to recognize 3D objects. However, the exact neural mechanism is still unclear. In this study, a model of the inferior temporal cortex for object recognition is proposed. The architecture of the model is based on the modular network SOM. The model has been trained to perform object recognition and classification tasks that have been reported to occur in the TE area in the brain of macaque monkeys. We show by simulation that the model is not only capable of classifying artificial 3D objects according to their structural similarity, but also capable of achieving view-invariant recognition of the objects by incorporating a mental-rotation type mechanism.

Keywords

brain models; cognition; medical computing; neurophysiology; object recognition; self-organising feature maps; 3D object recognition; cognitive abilities; human brain; inferior temporal cortex; inferotemporal network model; macaque monkeys; mental-rotation type mechanism; modular network SOM; neural mechanism; object classification; structural similarity; view-invariant recognition; Educational institutions; Visualization; inferotemporal cortex; mental rotation; neural network model; object recognition;

fLanguage

English

Publisher

ieee

Conference_Titel

Complex Medical Engineering (CME), 2011 IEEE/ICME International Conference on

Conference_Location

Harbin Heilongjiang

Print_ISBN

978-1-4244-9323-4

Type

conf

DOI

10.1109/ICCME.2011.5876803

Filename

5876803