期刊
IEEE TRANSACTIONS ON BIG DATA
卷 3, 期 1, 页码 44-54出版社
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/TBDATA.2016.2566664
关键词
Object retrieval; object proposal; partitioning; reranking
资金
- National Natural Science Foundation of China [61572493, U1536203]
- 100 Talents Programme of The Chinese Academy of Sciences
- Strategic Priority Research Program of the Chinese Academy of Sciences [XDA06010701]
Retrieving objects from large image collection is challenging due to the so-called background-interference, i.e., matching between query object and reference images is usually confused by cluttered background, especially when objects are small. In this paper, we propose an object retrieval technique addressing this problem by partitioning the images. Specifically, several object proposals are partitioned from the images by jointly optimizing their objectness and coverage. The proposal set with maximum objectness score and minimum redundancy is obtained. Therefore, the interference of cluttered background is greatly reduced. Next, the objects are retrieved based on the partitioned proposals, separately and independently to the background. Our method is featured by the fine partitioning, which not only removes interferences from background, but also significantly reduces the number of objects to index. In this way, the effectiveness and efficiency are both achieved, which better suits big data retrieval. Subsequently, feature coding on partitioned objects generates much meaningful representation, and object level connectivity also introduces novel clues into the reranking. Extensive experiments on three popular object retrieval benchmark datasets (Oxford Buildings, Paris, Holiday) show the effectiveness of our method in retrieving small objects out of big data.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据