最优种子提取与局部平滑标签传播提升显着性检测模型.PDFVIP

29 10 Vol.29 No.10 2017 10 Journal of Computer-Aided Design Computer Graphics Oct. 2017 最优种子提取与局部平滑标签传播提升显著性检测模型 1) 1,2) 1) 李 红 , 吴恩华 , 吴 雯 1) (澳门大学科技学院电脑与资讯科学系 澳门 999078) 2) ( 中国科学院软件研究所计算机科学国家重点实验 北京 100190) (hong.li.leon@connect.umac.mo) : 为了提高显著性检测的鲁棒性, 提出一种基于最优种子选取及局部平滑标签传播的显著性检测模型. 首先 计算初始背景图并进行优化, 对优化后的背景图进行随机采样来提取最优背景种子点; 然后融合 2 种不同方式下获 得的先验图来得到物体先验图, 通过对此先验图进行阈值化来提取最优前景种子点; 最后基于上述提取策略得到的 种子点, 应用局部平滑标签传播模型预测其他区域的标签信息, 从而获得显著图. 在3 个被广泛应用的数据集上进行 定性与定量的实验结果表明, 该模型能够有效地提升检测效果. ：显著性区域检测; 背景先验; 标签传播; 局部平滑 ：TP391.41 Optimal Seeds Extraction and Locally Smoothed Label Propagation for Salient Region Detection Li Hong1), Wu Enhua1,2), and Wu Wen1) 1) (Department of Computer and Information Science, Faculty of Science and Technology, University of Macau, Macau 999078) 2) (State Key Laboratory of Computer Science, Institute of Software Chinese Academy of Sciences, Beijing 100190) Abstract: To improve the robustness of salient region detection, this paper proposes a salient region detection model based on optimal seeds extraction and locally smoothed label propagation. By the model, the first step is to calculate a refined background map and extract optimal background seeds by random sampling in the map. Then an object prior map is generated by fusing two different prior maps. The optimal foreground seeds are extracted by thresholding. Finally, locally smoothed label propagation is proposed to predict labels of other regions by treating previously obtained seeds as initial labels and final saliency map is generated according to the predicted labels. Both quantitative and qualitative evaluations on three widely used