The Human in the Loop: EEG-driven Photo Optimization

This paper investigates the brain’s response to appealing and unappealing versions of images. We present results from several ElectroEncephaloGraph (EEG) experiments using images with varying levels of ‘pleasingness’ as stimuli, which shed light on the preference and perception of pleasing and displeasing image versions. An analysis of the EEG data shows a distinct and reliable difference in the neural response to image versions with the same content but different parameter values for saturation, contrast and brightness. We use this EEG data to create a neuralfeedback loop to automatically optimize these parameters to render more pleasing image variations.