On the role of context in probabilistic models of visual saliency
ICIP'09 Proceedings of the 16th IEEE international conference on Image processing
| Hi-index | 0.00 |
The properties of local image statistics are analyzed in a classic information theoretic setting. Local spatiochromatic image elements are projected into a space in which constituent components are independent by way of independent component analysis, allowing a fast and tractable means of considering the joint likelihood of such statistics. Observation of this likelihood allows inferences to be made regarding the informativeness of a particular set of statistics. This operation is shown to illuminate a number of perceptually important image properties, allowing figure-ground segmentation, removal of common or expected image elements, and prediction of regions of interest.