全部 标题 作者
关键词 摘要

OALib Journal期刊
ISSN: 2333-9721
费用:99美元

查看量下载量

相关文章

更多...

混合迁移学习方法在医学图像检索中的应用

DOI: 10.3969/j.issn.1006-7043.201405015

Keywords: 语义标注, 医学图像检索, 混合迁移, 实例迁移, 特征迁移, 多任务学习, 稀疏非负矩阵分解

Full-Text   Cite this paper   Add to My Lib

Abstract:

针对医学图像的复杂性,将迁移学习理论引入到医学图像的语义映射和检索中,提出了一种以解决多任务学习为目标的混合迁移学习方法。首先,对医学图像目标领域的数据进行部分语义标记,找出源领域和目标领域中具有相同语义标记的医学图像,并对这些图像进行聚类,而后剔除一些在特征上距离较远的图像数据,完成实例迁移;然后,采用在源领域和目标领域中具有相同语义的医学图像数据进行稀疏矩阵分解,完成特征的迁移;最后,完成目标领域中未标记图像数据的语义映射。利用200幅医学图像进行语义标注进行检索,实验表明准确率超过50%的图片数量占了80%以上,验证了方法的可行性。

References

[1]  GAO J, FAN W, JIANG J, et al. Knowledge transfer via multiple model local structure mapping[C]//Proceedings of the 14th ACM International Conference on Knowledge Discovery and Data Mining. LasVegas, USA, 2008:283-291.
[2]  ZHANG Y, YEUNG D Y. Transfer metric learning by learning task relationships[C]//Proceedings of the 16th ACM SIGKDD Conference on Knowledge Discovery and Data Mining. Washington DC, USA, 2010:1199-1208.
[3]  GOLDWASSER D, ROTH D. Active sample selection for named entity transliteration[C]//Proceedings of the 46th Annual Meeting of the Association for Computational Linguistics. Columbus, USA, 2008:53-56.
[4]  吕静.基于实例的迁移算法研究[D].太原:山西财经大学,2013:7-8.LYU Jing. Research of transfer learning algorithm based on instance[D].Taiyuan: Shanxi University of Finance & Economics,2013:7-8.
[5]  覃姜维.迁移学习方法研究及其在跨领域数据分类中的应用[D].广州:华南理工大学, 2011:5-20.TAN Jiangwei. Research of transfer learning and its application in classifying cross-domain data[D].Guangzhou: South China University of Technology,2011:5-20.
[6]  LEE D D, SEUNG H S. Learning the parts of objects by non-negative matrix factorization[J].Nature,1999, 401:788-791.
[7]  宋金歌,杨景,陈平,等.一种非负矩阵分解的快速稀疏算法[J].云南民族大学学报:自然科学版,2011(20):262-266.SONG Jinge, YANG Jing, CHEN Ping, et al. A fast and sparse algorithm for nonnegative matrix factorization[J]. Journal of Yunnan University of Nationalities: Natural Sciences Edition,2011(20):262-266.
[8]  GUPTA S,PHUNG D, ADAMS B. A matrix factorization framework for jointly analyzing multiple nonnegative data sources[C]//Procs of Text Mining Workshop, in conjuction with SIAM Int Conf on Data Mining. Arizona, USA, 2011.
[9]  马帅.基于稀疏非负矩阵分解的图像检索[D].杭州:浙江大学,2012:18-27.MA Shuai. Image retrieval by joint nonnegative matrix factorization with sparse regularization [D].Hangzhou: Zhejiang University,2012:18-27.
[10]  BENTHEM M H V, KEENAN M R. Fast algorithm for the solution of large-scal non-negativity-constrained least squares problems[J]. Journal of Chemometrics, 2004, 18:441-450.
[11]  KIM H, PARK H. Sparse non-negative matrix factorizations via alternating non-negativity-constrained least squares for microarray data analysis[J]. Bioinfonnaties/Computer Applications in The Biosciences, 2007, 23:1495-1502.
[12]  刘继晴.基于多特征融合的视频高层语义概念检测[D].北京:北京邮电大学,2011:25-27.LIU Jiqing. High-level video senmantic concept detection based on multiple features[D]. Beijing: Beijing University of Posts and Telecommunications, 2011:25-27.

Full-Text

Contact Us

service@oalib.com

QQ:3279437679

WhatsApp +8615387084133