Edge co-occurrences can account for rapid categorization of natural versus animal images - Archive ouverte HAL Access content directly
Journal Articles Scientific Reports Year : 2015

Edge co-occurrences can account for rapid categorization of natural versus animal images

(1) , (2)
1
2

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 the "association field" 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.
Fichier principal
Vignette du fichier
srep11400.pdf (635.88 Ko) Télécharger le fichier
Origin : Publisher files allowed on an open archive
Loading...

Dates and versions

hal-01202447 , version 1 (21-09-2015)

Identifiers

Cite

Laurent U Perrinet, James A. Bednar. Edge co-occurrences can account for rapid categorization of natural versus animal images. Scientific Reports, 2015, ⟨10.1038/srep11400⟩. ⟨hal-01202447⟩

Collections

CNRS UNIV-AMU INT
67 View
90 Download

Altmetric

Share

Gmail Facebook Twitter LinkedIn More