Abstract | ||
---|---|---|
Saliency mechanism has been considered crucial in the human visual system and helpful to object detection and recognition. This paper addresses a novel feature-based model for visual saliency detection. It consists of two steps: first, using the learned overcomplete sparse bases to represent image patches; and then, estimating saliency information via direct low-rank and sparsity matrix decomposition. We compare our model with the previous methods on natural images. Experimental results show that our model performs competitively for visual saliency detection task, and suggest the potential application of matrix decomposition and convex optimization for image analysis. |
Year | DOI | Venue |
---|---|---|
2010 | 10.1109/ICIP.2010.5652280 | 2010 IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING |
Keywords | Field | DocType |
saliency detection, matrix decomposition, sparse coding, convex optimization | Computer vision,Object detection,Pattern recognition,Kadir–Brady saliency detector,Human visual system model,Neural coding,Computer science,Salience (neuroscience),Matrix decomposition,Artificial intelligence,Sparse matrix,Cognitive neuroscience of visual object recognition | Conference |
ISSN | Citations | PageRank |
1522-4880 | 15 | 1.28 |
References | Authors | |
6 | 5 |
Name | Order | Citations | PageRank |
---|---|---|---|
Junchi Yan | 1 | 891 | 83.36 |
Jian Liu | 2 | 289 | 59.26 |
Yin Li | 3 | 797 | 35.85 |
Zhibin Niu | 4 | 72 | 7.55 |
Yuncai Liu | 5 | 1234 | 185.16 |