| | |
Summary: IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE 1
Image Signature: Highlighting sparse salient regions
Xiaodi Hou, Jonathan Harel, and Christof Koch
Abstract-- We introduce a simple image descriptor referred
to as the image signature. We show, within the theoretical
framework of sparse signal mixing, that this quantity spatially
approximates the foreground of an image. We experimentally
investigate whether this approximate foreground overlaps with
visually conspicuous image locations by developing a saliency
algorithm based on the image signature. This saliency algorithm
predicts human fixation points best among competitors on the
Bruce and Tsotsos [1] benchmark dataset and does so in much
shorter running time. In a related experiment, we demonstrate
with a change blindness dataset that the distance between images
induced by the image signature is closer to human perceptual
distance than can be achieved using other saliency algorithms,
pixel-wise or GIST [2] descriptor methods.
Index Terms-- Saliency, visual attention, change blindness, sign
function, sparse signal analysis.
I. INTRODUCTION
|
