BIOMAT Database Logo BIOMAT Database Logo

Computational theories of object recognition. 1997

S Edelman

This paper examines four current theoretical approaches to the representation and recognition of visual objects: structural descriptions, geometric constraints, multidimensional feature spaces and shape-space approximation. The strengths and weaknesses of the four theories are considered, with a special focus on their approach to categorization - a computationally challenging task which is not widely addressed in computer vision, where the stress is rather on the generalization of recognition across changes of viewpoint.

UI MeSH Term Description Entries

Related Publications

S Edelman
Agnosia for object orientation: implications for theories of object recognition.
February 1997, Neuropsychologia,
S Edelman
Object recognition and image understanding: theories of everything?
January 2000, Spatial vision,
S Edelman
Computational object recognition: a biologically motivated approach.
January 2009, Biological cybernetics,
S Edelman
A biologically plausible computational model for auditory object recognition.
January 2009, Journal of neurophysiology,
S Edelman
Invariance in visual object recognition requires training: a computational argument.
April 2010, Frontiers in neuroscience,
S Edelman
Comparing theories of consciousness: Object position, not probe modality, reliably influences experience and accuracy in object recognition tasks.
September 2020, Consciousness and cognition,
S Edelman
A Computational Approach towards Visual Object Recognition at Taxonomic Levels of Concepts.
January 2015, Computational intelligence and neuroscience,
S Edelman
The Müller-Lyer Illusion in a computational model of biological object recognition.
January 2013, PloS one,
S Edelman
Computational theories of vision.
October 2002, Current biology : CB,
S Edelman
Three-dimensional color object visualization and recognition using multi-wavelength computational holography.
July 2007, Optics express,
Copied contents to your clipboard!