Inferotemporal network model for 3D object recognition

Efremova, Natalia, Asakura, Nobuhiko, Inui, Toshio and Abdikeev, Niyaz (2011) Inferotemporal network model for 3D object recognition. Proceedings of the 2011 IEEEIICME International Conference on Complex Medical Engineering.

[img] PDF - Published Version
Restricted to Repository staff only

Download (1MB)

Abstract

One of the essential cognitive abilities of the human brain is the ability to recognize 3D objects. However, the exact neural mechanism is stilI 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.

Item Type: Article
Keywords: in/erotemporal cortex, object recognition, neural network model, mental rotation
Subject(s): Technology
Centre: Oxford University Centre for Corporate Reputation
Date Deposited: 28 May 2018 12:52
Last Modified: 28 May 2018 12:52
Funders: Grant-in Aid for Scientific Research (S) "Brain mechanisms of dynamic image generation based on body schema"(2022003) from the Japanese Ministry of Education, Science, Technology, Sports and Culture (MEXT)
URI: http://eureka.sbs.ox.ac.uk/id/eprint/6832

Actions (login required)

Edit View Edit View