A saliency detection model for approaching the human performance is a challenging research topic. In this paper, a new saliency model is proposed to detect saliency in natural scenes by using a trained convolutional neural network and a region-based validation method. The convolutional neural network (CNN) focuses on image details and local contrast of an image, while the region-based validation method focus on global information. Experimental results show that the two components of the model are complementary for each other in producing high-quality saliency maps. Copyright © 2015 IEEE.
|Title of host publication||2015 11th International Conference on Natural Computation (ICNC 2015)|
|Editors||Zheng XIAO, Zhao TONG, Kenli II, Xingwei WANG, Keqin LI|
|Place of Publication||Piscataway, NJ|
|ISBN (Electronic)||9781467376785, 9781467376792|
|Publication status||Published - 2016|
CitationHu, Y., Liang, Z., Chi, Z., & Fu, H. (2016). A combined convolutional neural network and potential region-of-interest model for saliency detection. In Z. Xiao, Z. Tong, K. Ii, X. Wang, & K. Li (Eds.), 2015 11th International Conference on Natural Computation (ICNC 2015) (pp. 154-158). Piscataway, NJ: IEEE.
- Saliency map
- Saliency detection
- Machine learning
- Convolutional neural networks