A Novel Salient Object Detection Method Using Bag-of-features
A novel salient object detection algorithm via bag-of-features (BoF) is proposed. Specifically, it uses objectness to compute the prior saliency map. Then, BoF model is constructed in each superpixel and the conditional probabilities map is calculated. The prior and conditional probabilities saliency maps are finally fused by Bayes0 theorem. Extensive experiments against state-of-art methods are carried out on ASD, SED and SOD benchmark datasets. Experimental results show that the proposed method performs favorably against the sixteen state-of-art methods in terms of precision and recall, and highlights the salient ob jects more effectively.
国家科技期刊平台
NSTL
万方数据
维普
