Optimal feature encoding in early vision

Abstract

Abstract The human visual system processes a massive amount of visual information very rapidly, requiring efficient coding mechanisms to handle such data within physiological constraints. The biological foundations of these mechanisms remain poorly understood. One hypothesis suggests that the visual system prioritizes the encoding of specific features of natural scenes optimized to maximize information transfer while minimizing computational costs (constrained-maximum entropy criteria). This study aims to identify a possible neural marker of this prioritizing mechanism. Participants were briefly shown stimuli with varying proportions of such optimal features, while EEG visual evoked response was recorded. Analysis focused on the C1 component, the earliest visual evoked component commonly considered to mainly reflect the first cortical response in the primary visual cortex (V1). Results revealed that the C1 component peaks earlier when elicited by optimal features, with a proportional speed-up following the gradual increase of their number. This provides evidence for an early efficient selection of optimally informative visual features in humans.