激光与光电子学进展, 2019, 56 (16): 161010, 网络出版: 2019-08-05
贝叶斯融合多核学习的图像显著性检测 下载: 942次
Image Saliency Detection of Bayesian Integration Multi-Kernel Learning
图像处理 贝叶斯公式融合 显著性检测 compactness先验 初级显著图 多核学习 次级显著图 image processing Bayesian formula integration saliency detection compactness prior primary saliency map multi-kernel learning secondary saliency map
摘要
针对当前图像显著性检测算法存在的检测不准确和边缘不清晰问题,提出基于改进的贝叶斯公式融合算法。采用compactness先验得到初级显著图,并以初级显著图作为训练样本,采用多核学习方式得到次级显著图,而后基于贝叶斯公式以一定的比例融合初级和次级显著图,最终获得精确的显著性检测图。实验结果表明,算法在2个公开数据集上进行检测时,所得结果能够有效地突出目标物体,去除边缘模糊的现象,且实验结果在3个数据指标(精确度、召回率和F -measure值)方面均优于其他8种算法,算法运行速度较快,实验结果也更为精确。
Abstract
An improved fusion algorithm based on Bayesian formula is proposed for addressing inaccurate detection and unclear edge problems in existing image saliency detection algorithms. First, compactness prior is used for obtaining the primary saliency map. Then, the secondary saliency map is obtained via multi-kernel learning using primary saliency maps as training samples. Finally, a Bayesian formula is used to integrate the primary saliency map with the secondary saliency map at a certain proportion to obtain an accurate saliency map. Experimental results obtained on two public datasets demonstrate that the proposed algorithm can effectively highlight the target object and remove blurred edges. The proposed algorithm is superior to eight existing algorithms from the viewpoint of accuracy, recall rate, and F-measure value. Furthermore, the running speed of the proposed algorithm is faster, and it demonstrates more accurate experimental results.
陈雪敏, 唐红梅, 韩力英, 高振斌. 贝叶斯融合多核学习的图像显著性检测[J]. 激光与光电子学进展, 2019, 56(16): 161010. Xuemin Chen, Hongmei Tang, Liying Han, Zhenbin Gao. Image Saliency Detection of Bayesian Integration Multi-Kernel Learning[J]. Laser & Optoelectronics Progress, 2019, 56(16): 161010.