CORC  > 厦门大学  > 数学科学-已发表论文
基于Co-training的图像自动标注; Automatic Image Annotation Based on Co-training
柯逍 ; 李绍滋 ; 陈国龙
2013-07-28
关键词图像自动标注 Co-training算法 统一框架 相关模型 automatic image annotation Co-training algorithm unified framework relevance model
英文摘要图像自动标注是图像理解与模式识别等领域中具有挑战性的关键研究问题.目前图像自动标注领域存在着一些问题,如未标注数据规模要远大于标注数据规模,只能单独使用某种图像分割策略与某类图像表示方法.针对上述问题,提出了基于CO-TrAInIng的图像自动标注方法,通过构建4个独立的特征属性进而建立4个子分类器,将不同的图像分割方法与特征表示方法整合到一个统一框架中,利用提出的基于投票与一致性相结合的自适应算法扩展原始训练集.该方法通过使用CO-TrAInIng算法,利用大量未标注数据来提升图像自动标注的性能.通过在COrEl 5k数据库上进行实验,验证了提出方法的有效性.; Automatic image annotation is a critical and challenging problem in pattern recognition and image understanding areas.There are some problems in existing automatic image annotation areas.For example,the size of unlabeled data is much larger than the labeled data.Besides,most image annotation models can only use one kind of image segmentation strategy and certain image description method.According to above problems,an automatic image annotation model based on Co-training is proposed.In this model,four independent feature properties are constructed and then four corresponding sub-classifiers are built.In this way,different image segmentation strategies and feature representation methods can be integrated into a unified framework.An adaptive algorithm based on vote and consistency is proposed to extend the training dataset.The proposed method use Co-training algorithm and mass unlabeled data to improve the performance of automatic image annotation.Experiments conducted on Corel 5K dataset verify the effectiveness of proposed method.; 国家自然科学基金项目(60873179;60803078;10871221); 高等学校博士学科点专项科研基金项目(20090121110032); 福建省自然科学基金项目(2013J05088)
语种zh_CN
内容类型期刊论文
源URL[http://dspace.xmu.edu.cn/handle/2288/119860]  
专题数学科学-已发表论文
推荐引用方式
GB/T 7714
柯逍,李绍滋,陈国龙. 基于Co-training的图像自动标注, Automatic Image Annotation Based on Co-training[J],2013.
APA 柯逍,李绍滋,&陈国龙.(2013).基于Co-training的图像自动标注..
MLA 柯逍,et al."基于Co-training的图像自动标注".(2013).
个性服务
查看访问统计
相关权益政策
暂无数据
收藏/分享
所有评论 (0)
暂无评论
 

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。


©版权所有 ©2017 CSpace - Powered by CSpace