Skip to Main content Skip to Navigation
Journal articles

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

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.
Document type :
Journal articles
Complete list of metadata

Cited literature [20 references]  Display  Hide  Download
Contributor : Administrateur HAL AMU Connect in order to contact the contributor
Submitted on : Monday, September 21, 2015 - 10:20:38 AM
Last modification on : Wednesday, November 24, 2021 - 9:54:07 AM


Publisher files allowed on an open archive




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



Record views


Files downloads