A novel image annotation feedback model based on internet-search | |
Yu, Jian Song ; Cao, Dong Lin ; Li, Shao Zi ; Lin, Da Zhen ; Li SZ(李绍滋) ; Lin DZ(林达真) ; Cao DL(曹冬林) | |
2012 | |
关键词 | Image analysis Internet Search engines Websites |
英文摘要 | Conference Name:2012 International Conference on Web Information Systems and Mining, WISM 2012. Conference Address: Chengdu, China. Time:October 26, 2012 - October 28, 2012.; Xihua University; Leshan Normal University; We propose an Internet-search-based automatic image annotation feedback model, combining content-based and web-based image annotation, to solve the relevance assumption between the image and text and the limited volume of the database. In this model, we extract candidate labels from search results using web-based texts associated with the image, and then verify the final results by using Internet search results of candidate labels with content-based features. Experimental results show that this method can annotate the large-scale database with high accuracy, and achieve a 5.2% improvement on the basis of web-based automatic image annotation. 漏 Springer-Verlag Berlin Heidelberg 2012. |
语种 | 英语 |
出处 | http://dx.doi.org/10.1007/978-3-642-33469-6_72 |
出版者 | Springer Verlag |
内容类型 | 其他 |
源URL | [http://dspace.xmu.edu.cn/handle/2288/86841] ![]() |
专题 | 信息技术-会议论文 |
推荐引用方式 GB/T 7714 | Yu, Jian Song,Cao, Dong Lin,Li, Shao Zi,et al. A novel image annotation feedback model based on internet-search. 2012-01-01. |
个性服务 |
查看访问统计 |
相关权益政策 |
暂无数据 |
收藏/分享 |
除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。
修改评论