融合判别区域特征与标签传播的显著性目标检测  

Salient object detection by integrating discriminative region feature and label propagation

作　　者：王明 崔冬[1,2] 李刚 顾广华[1,2] WANG Ming;CUI Dong;LI Gang;GU Guanghua(School of Information Science and Engineering,Yanshan University,Qinhuangdao,Hebei 066004,China;Hebei Provincial Key Laboratory of Information Transmission and Signal Processing,Qinhuangdao,Hebei 066004,China)

机构地区：[1]燕山大学信息科学与工程学院,河北秦皇岛066004 [2]河北省信息传输与信号处理重点实验室,河北秦皇岛066004

出　　处：《燕山大学学报》2019年第5期455-461,共7页Journal of Yanshan University

基　　金：国家自然科学基金资助项目(61303128);河北省自然科学基金资助项目(F2017203169,F2018203239);河北省高等学校科学研究重点项目(ZD2017080);河北省留学回国人员科技活动项目(CL201621)

摘　　要：为了提高图片在复杂场景下检测的准确率与鲁棒性,本文提出了一种融合判别区域特征与标签传播的显著性目标检测算法。首先利用判别区域特征方法形成一个判别区域特征显著图;然后利用标签传播算法得到标签传播显著图;最后,通过一个指数函数将两者融合形成最终的目标显著图。本文提出的方法在公开的数据集中测试并与现有的6种算法进行比较,实验结果证明了本文算法的有效性和可靠性。To improve the accuracy and robustness of image detection in complex scenes,a salient object detection method is proposed by integrating the discriminative regional feature and the label propagation in this paper.Firstly,the discriminative region feature saliency map is formed by a discriminative region feature method.Then the label propagation saliency map is obtained by a label propagation algorithm.Finally,an exponential function is used to fuse the two maps to form the final object saliency map.The proposed method is tested on public datasets and compared with the existing six algorithms.The experimental results demonstrate the effectiveness and reliability of the proposed algorithm.

关 键 词：显著性检测 判别区域特征 标签传播 指数融合 

分 类 号：TP391.4[自动化与计算机技术—计算机应用技术]