Connectionists: Rapid image categorization via edge co-occurrences

[James A. Bednar]

We are pleased to announce the publication of an open-access paper
demonstrating a novel method for categorizing images using the
statistics of their edge co-occurrences.

The success of this low-level method in matching both correct and
incorrect classifications by humans suggests a reinterpretation of
longstanding claims for rapid hierarchical processing in the visual
cortex.

Laurent U. Perrinet 
Institut de Neurosciences de la Timone
Aix Marseille Universite, CNRS

James A. Bednar
Institute for Adaptive and Neural Computation
University of Edinburgh

_______________________________________________________________________________

Laurent U. Perrinet and James A. Bednar. Edge co-occurrences can
account for rapid categorization of natural versus animal images. 
Scientific Reports, Nature Publishing Group, 5:11400, 2015.

http://dx.doi.org/10.1038/srep11400

Abstract: Making a judgment about the semantic category of a visual
scene, such as whether it contains an animal, is typically assumed to
involve high-level associative brain areas. Previous explanations
require progressively analyzing the scene hierarchically at increasing
levels of abstraction, from edge extraction to mid-level object
recognition and then object categorization. Here we show that the
statistics of edge co-occurrences alone are sufficient to perform a
rough yet robust (translation, scale, and rotation invariant) scene
categorization. We first extracted the edges from images using a
scale-space analysis coupled with a sparse coding algorithm. We then
computed association for different categories (natural, man-made, or
containing an animal) by computing the statistics of edge
co-occurrences. These differed strongly, with animal images having
more curved configurations. We show that this geometry alone is
sufficient for categorization, and that the pattern of errors made by
humans is consistent with this procedure. Because these statistics
could be measured as early as the primary visual cortex, the results
challenge widely held assumptions about the flow of computations in
the visual system. The results also suggest new algorithms for image
classification and signal processing that exploit correlations between
low-level structure and the underlying semantic category.

-- 
The University of Edinburgh is a charitable body, registered in
Scotland, with registration number SC005336.