基于标签集相关性学习的大规模网络图像在线标注  

Large Scale Web Image Online Annotation by Learning Label Set Relevance

作　　者：田枫[1,2] 沈旭昆[1] 

机构地区：[1]北京航空航天大学虚拟现实技术与系统国家重点实验室,北京100191 [2]东北石油大学计算机与信息技术学院,大庆163318

出　　处：《自动化学报》2014年第8期1635-1643,共9页Acta Automatica Sinica

基　　金：国家高技术研究发展计划(863计划)(2009AA012103);国家自然科学基金(60533070);东北石油大学青年科学基金(2013NQ120)资助~~

摘　　要：传统的网络图像标注方法忽视了标签集整体相关性对标注结果的影响,导致标签集整体相关性缺乏和语义冗余.为了解决上述问题,提出了一种基于标签集相关性学习的大规模网络图像在线语义标注方法.给出了标签集对图像相关性和标签集内部相关性的概率估计算法,将上述约束形成一个优化问题,采用贪心搜索策略获取近似最优解,找到能合理地平衡上述因素的标签集,并针对大规模图像集和概念集进行了优化.真实环境下大规模网络图像集上的测试表明,相比于目前的代表性网络图像标注方法,该方法获得的标签集能够更好的描述图像语义,性能提升明显.Traditional web image annotation methods neglect the relevance of the assigned label set as a whole, resulting in the label relevance deficiency and redundancy. To solve the above problems, a novel web image annotation method by learning the label set relevance is proposed, which considers both the relevance of label set to image and the label set internal correlation. Measures that can estimate the above factors are designed, and both the constraints are formulated into a joint framework. Meanwhile, an effective greedy search algorithm is proposed for an approximate optimal label set, which reaches a reasonable trade-off between the relevance of label set to image and internal correlation, and makes the framework more applicable to the data set that contains the large scale concept and images. Experiments on real world web image data sets demonstrate the general applicability of our algorithm. In comparison to the state-of-the-art methods, the proposed approach yields better performance.

关 键 词：网络图像标注 图像语义标注 标签集相关性 标签相关性学习 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]