Image Signature: Highlighting Sparse Salient Regions

Authors:
Xiaodi Hou;Jonathan Harel;Christof Koch
Affiliations:
Caltech, Pasadena;Caltech, Pasadena;Caltech, Pasadena
Venue:
IEEE Transactions on Pattern Analysis and Machine Intelligence
Year:
2012

Citing 0
Cited 13

Security-oriented picture-in-picture visual modifications

Proceedings of the 2nd ACM International Conference on Multimedia Retrieval
Quaternion-Based spectral saliency detection for eye fixation prediction

ECCV'12 Proceedings of the 12th European conference on Computer Vision - Volume Part II
Saliency modeling from image histograms

ECCV'12 Proceedings of the 12th European conference on Computer Vision - Volume Part VII
Visual saliency detection with center shift

Neurocomputing
Efficient visual attention based framework for extracting key frames from videos

Image Communication
Visual saliency detection using information divergence

Pattern Recognition
Optimal contrast based saliency detection

Pattern Recognition Letters
Spatiotemporal saliency detection and salient region determination for H.264 videos

Journal of Visual Communication and Image Representation
Selection of a best metric and evaluation of bottom-up visual saliency models

Image and Vision Computing
A survey on recent object detection techniques useful for monocular vision-based planetary terrain classification

Robotics and Autonomous Systems
Saliency detection based on integrated features

Neurocomputing
A New Framework for Multiscale Saliency Detection Based on Image Patches

Neural Processing Letters
Ensemble dictionary learning for saliency detection

Image and Vision Computing

Quantified Score

Hi-index	0.14

Visualization

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 data set and does so in much shorter running time. In a related experiment, we demonstrate with a change blindness data set 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.