Biologically inspired Object Recognition System

Robust object recognition with Cortex-like Mechanisms
source: NewSciTech

Learning scene using biological feature

Abstract—A new general framework for the recognition of complex visual scenes motivated by biology is introduced: using a hierarchical system that closely follows the organization of visual cortex and builds an increasingly complex and invariant feature representation by alternating between a template matching and a maximum pooling operation. The framework is demonstrated using a range of recognition tasks: From invariant single object recognition in clutter to multiclass categorization problems and complex scene understanding tasks that rely on the recognition of both shape-based as well as texture-based objects. Given the biological constraints that the system had to satisfy, the approach performs surprisingly well: It has the capability of learning from only a few training examples and competes with state-of-the-art systems.

Paper: view

Leave a Reply