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. |
Year | DOI | Venue |
---|---|---|
2012 | 10.1109/TPAMI.2011.146 | IEEE Trans. Pattern Anal. Mach. Intell. |
Keywords | Field | DocType |
image processing,change blindness data,change blindness,descriptor method,saliency algorithm,image foreground,sparse signal mixing,human fixation point,benchmark data,sparse signal analysis.,sparse salient regions,highlighting sparse salient regions,simple image descriptor,visual attention,digital signatures,saliency,human perceptual distance,sign function,conspicuous image location,approximate foreground overlap,image descriptor,image signature,signal analysis,discrete cosine transform,prediction algorithms,gaussian distribution,pixel,image reconstruction | Iterative reconstruction,Computer vision,Pattern recognition,Computer science,Salience (neuroscience),Image processing,Digital signature,Pixel,Artificial intelligence,Sign function,Change blindness,Salient | Journal |
Volume | Issue | ISSN |
34 | 1 | 1939-3539 |
Citations | PageRank | References |
319 | 8.00 | 9 |
Authors | ||
3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Xiaodi Hou | 1 | 2069 | 72.53 |
Jonathan Harel | 2 | 912 | 38.93 |
Christof Koch | 3 | 7248 | 973.47 |