Abstract | ||
---|---|---|
Computer vision approaches to saliency are based, among others, on uniqueness [1], local complexity [2], distinctiveness [3,4], spectral variation [5], and irregularity [6]. Saliency can also be viewed as the information in the data relative to a representation or model [7]. When a representation is built, a residual error is often minimised. The residual can be used to obtain saliency maps for solving challenging tasks of image and video processing. We introduce the notion of the resonant SVD and demonstrate that the SVD residual at the resonant spacing is selective to defects in spatially periodic surface textures and events in time-periodic videos. Examples with real-world images and videos are shown and discussed. |
Year | DOI | Venue |
---|---|---|
2008 | 10.1007/978-3-642-02345-3_15 | ICCVG |
Keywords | Field | DocType |
spectral variation,salient feature,resonant svd,challenging task,spatially periodic surface texture,local complexity,resonant spacing,residual error,real-world image,computer vision approach,saliency map,texture,surface texture,svd,video processing,saliency,computer vision | Uniqueness,Residual,Computer vision,Singular value decomposition,Video processing,Pattern recognition,Computer science,Salience (neuroscience),Artificial intelligence,Periodic graph (geometry),Optimal distinctiveness theory,Salient | Conference |
Volume | ISSN | Citations |
5337 | 0302-9743 | 3 |
PageRank | References | Authors |
0.43 | 20 | 1 |
Name | Order | Citations | PageRank |
---|---|---|---|
Chetverikov, D. | 1 | 956 | 99.89 |