Keywords
metric tensor, curvature, template, image classification, kernel
Abstract
Visual operators (e.g. edge detectors) are classically modelled using small circuits involving canonical computations, such as template-matching and gain control. Circuit models explain many aspects of the empirical descriptors that are used to characterize local visual operators, from sensitivity to classification images. Notwithstanding their utility, these models fail to provide a unified framework encompassing the variety of effects observed experimentally, such as the impact of contrast, SNR, and attention on the above descriptors. My goal is to start with a simple, plausible geometrical representation of the perceptual operation carried out by the observer, and to show that this representation is sufficiently expressive to capture a wide range of empirical effects associated with elementary visual computations. The resulting geometrical framework offers a new perspective on specific empirical descriptors, such as classification images and their second-order variants. For example, it relates these descriptors to notions of flatness and curvature in perceptual space
Start Date
16-5-2024 9:30 AM
End Date
16-5-2024 10:00 AM
Included in
Applied Behavior Analysis Commons, Behavioral Neurobiology Commons, Cognitive Neuroscience Commons, Computational Neuroscience Commons, Other Applied Mathematics Commons, Systems Neuroscience Commons
Local geometry of elementary visual computations
Visual operators (e.g. edge detectors) are classically modelled using small circuits involving canonical computations, such as template-matching and gain control. Circuit models explain many aspects of the empirical descriptors that are used to characterize local visual operators, from sensitivity to classification images. Notwithstanding their utility, these models fail to provide a unified framework encompassing the variety of effects observed experimentally, such as the impact of contrast, SNR, and attention on the above descriptors. My goal is to start with a simple, plausible geometrical representation of the perceptual operation carried out by the observer, and to show that this representation is sufficiently expressive to capture a wide range of empirical effects associated with elementary visual computations. The resulting geometrical framework offers a new perspective on specific empirical descriptors, such as classification images and their second-order variants. For example, it relates these descriptors to notions of flatness and curvature in perceptual space