吉林大学学报(工学版) ›› 2014, Vol. 44 ›› Issue (4): 1126-1134.doi: 10.13229/j.cnki.jdxbgxb201404034

• • 上一篇    下一篇

基于密度聚类和多示例学习的图像分类方法

陈涛, 邓辉舫, 刘靖   

  1. 华南理工大学 计算机科学与工程学院, 广州 510006
  • 收稿日期:2013-02-28 出版日期:2014-07-01 发布日期:2014-07-01
  • 作者简介:陈涛(1979-), 男, 博士研究生.研究方向:机器学习, 图像分类.E-mail:c.tao01@mail.scut.edu.cn
  • 基金资助:
    国家自然科学基金项目(61003174)

Image categorization method using density clustering on region features and multi-instance learning

CHEN Tao, DENG Hui-fang, LIU Jing   

  1. School of Computer Science and Engineering, South China University of Technology, Guangzhou 510006, China
  • Received:2013-02-28 Online:2014-07-01 Published:2014-07-01

摘要: 针对图像的低级特征表示与高级概念之间的语义鸿沟, 本文利用密度聚类获得的簇分布信息和多示例学习框架在区分歧义性对象上的特点, 提出了一个基于区域特征密度聚类和多示例学习的图像分类方法(DCRF-MIL)。该方法首先将每个图像分割为多个区域, 将所有区域组成一个集合, 在这个区域集合上, 使用密度聚类算法学习到区域特征的簇分布信息;然后, 将图像看作包, 区域看作包中的示例, 基于区域特征的簇分布信息, 将包映射为簇分布空间上的一个向量作为包的特征, 使得包特征带有图像区域的语义信息;最后, 使用支持向量机算法, 在带有包特征的训练集上训练分类器, 对测试图像进行分类。在Corel图像集和MUSK分子活性预测数据集上的实验表明, DCRF-MIL算法具有分类精度高和参数易于选择等特点。

关键词: 人工智能, 图像分类, 多示例学习, 密度聚类, 支持向量机

Abstract: In order to narrow the semantic gap between low-level visual features and high-level semantic concepts in image categorization, the clustering information from a density clustering algorithm and the characteristics of multi-instance learning framework in distinguishing ambiguous object are exploited. An image categorization method is proposed using Density Clustering on Region Features and Multi-Instance Learning (DCRF-MIL). First, the DCRF-MIL divides each image into number of regions and relines up all regions into a collection; then it uses a density clustering algorithm to learn the potential distribution information of the region features in the collection. Second, it treats an image as a bag and the regions as instances in the bag. Based on the cluster distribution information of region features, the bag is mapped into a vector in the cluster distribution space. Finally, a support vector machine classifier is constructed to predict the class label of the unlabeled image. The experiments on the Corel image data set and MUSK molecular activity prediction data set show that the DCRF-MIL method has high classification accuracy and it is easy to select its parameters.

Key words: artificial intelligence, image categorization, multi-instance learning, density clustering, support vector machine

中图分类号: 

  • TP391.4
[1] Binder A, Mueller K R, Kawanabe M. On taxonomies for multi-class image categorization[J]. International Journal of Computer Vision, 2012, 99(3):281-301.
[2] Hu Xiao-hong, Xu Qian, Ma Xin-ming, et al. A novel region-based image annotation using multi-instance learning[C]∥Proceedings of the Second International Workshop on Knowledge Discovery and Data Mining, 2009:602-605.
[3] Song Xiang-fa, Jiao L C, Yang Shu-yuan. Sparse coding and classifier ensemble based multi-instance learning for image categorization[J]. Signal Processing, 2013, 93(1):1-11.
[4] Dietterich T G, Lathrop R H, Lozano-Pérez T. Solving the multiple-instance problem with axis-parallel rectangles[J]. Artificial Intelligence, 1997, 89(1/2): 31-71.
[5] Foulds James, Frank Eibe. A review of multi-instance learning assumptions[J]. Knowledge Engineering Review, 2010, 25(1):1-25.
[6] Fu Zhou-yu, Robles-Kelly A, Zhou Jun. Multiple instance learning with instance selection[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2011, 33(5):958-977.
[7] Babenko B, Verma N, Dollár P, et al. Multiple instance learning with manifold bags[C]∥Proceedings of the 28th International Conference on Machine Learning, ICML 2011:81-88.
[8] 陈绵书, 杨树媛, 赵志杰, 等.多点多样性密度算法及其在图像检索中的应用[J].吉林大学学报:工学版, 2011, 41(5):1456-1460. Chen Mian-shu, Yang Shu-yuan, Zhao Zhi-jie, et al.Multi-points diverse density learning algorithm and its application in image retrieval[J]. Journal of Jilin University(Engineering and Technology Edition), 2011, 41(5):1456-1460.
[9] Maron O, Lozano-Pérez T. A framework for multiple-instance learning[J]. Advances in Neural Information Processing Systems, Cambridge, MA: MIT Press, 1998: 570-576.
[10] Zhang Q, Goldman S A. EM-DD: an improved multiple-instance learning technique[J]. Advances in Neural Information Processing Systems, Cambridge, CA: MIT Press, 2002: 1073-1080.
[11] 李展, 彭进业, 温超. 基于谱聚类和多示例学习的图像检索方法[J].华南理工大学学报:自然科学版, 2011, 39(7): 156-162. Li Zhan, Peng Jin-ye, Wen Chao. Image retrieval based on spectral clustering and multiple instance learning[J]. Journal of South China University of Technology (Natural Science Edition), 2011, 39(7): 156-162.
[12] Andrews S, Tsochantaridis I, Hofmann T. Support vector machines for multiple instance learning[C]∥Advances in Neural Information Processing Systems, Cambridge, MA: MIT Press, 2003:561-568.
[13] Yang Chang-bo, Dong Ming, Hua Jing. Region-based image annotation using asymmetrical support vector machine-based multiple-Instance learning[C]∥Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2006, 2: 2057-2063.
[14] 路晶, 马少平. 使用多例学习的启发式SVM算法的图像自动标注[J]. 计算机研究与发展, 2009, 46(5): 864-871. Lu Jing, Ma Shao-ping. Region-based image annotation using heuristic support vector machine in multiple-instance learning[J]. Journal of Computer Research and Development, 2009, 46(5):864-871.
[15] Chen Y X, Wang J Z。 Image categorization by learning and reasoning with regions[J]. Journal of Machine Learning Research, 2004, 5: 913-939.
[16] Chen Y X, Bi J, Wang J Z. MILES: Multiple-instance learning via embedded instance selection[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2006, 28(12):1931-1947.
[17] Zhou Zhi-Hua。 Multi-instance learning from supervised view[J]. Journal of Computer Science and Technology, 2006, 6(5):800-809.
[18] Wang J Z, Li J, Wiederhold G.SIMPLIcity: Semantics-sensitive integrated matching for picture libraries[J].IEEE Transactions on Pattern Analysis and Machine Intelligence, 2001, 23(9):947-963.
[19] Yang Christopher C, Ng Tobun Dorbin.Analyzing and visualizing web opinion development and social interactions with density-based clustering[J]. IEEE Transactions on Systems, Man, and Cybernetics Part A: Systems and Humans, 2011, 41(6): 1144-1155.
[20] Kundakcioglu O E, Seref O, Pardalos P M.Multiple instance learning via margin maximization [J].Applied Numerical Mathematics, 2010, 60(4): 14-23.
[21] Yang Jun, Jiang Yu-gang, Hauptmann Alexander G, et al. Evaluating bag-of-visual-words representations in scene classification[C]∥Proceedings of the 9th ACM SIG Multimedia International Workshop on Multimedia Information Retrieval, 2007:197-206.
[1] 隗海林, 包翠竹, 李洪雪, 李明达. 基于最小二乘支持向量机的怠速时间预测[J]. 吉林大学学报(工学版), 2018, 48(5): 1360-1365.
[2] 董飒, 刘大有, 欧阳若川, 朱允刚, 李丽娜. 引入二阶马尔可夫假设的逻辑回归异质性网络分类方法[J]. 吉林大学学报(工学版), 2018, 48(5): 1571-1577.
[3] 顾海军, 田雅倩, 崔莹. 基于行为语言的智能交互代理[J]. 吉林大学学报(工学版), 2018, 48(5): 1578-1585.
[4] 王旭, 欧阳继红, 陈桂芬. 基于垂直维序列动态时间规整方法的图相似度度量[J]. 吉林大学学报(工学版), 2018, 48(4): 1199-1205.
[5] 张浩, 占萌苹, 郭刘香, 李誌, 刘元宁, 张春鹤, 常浩武, 王志强. 基于高通量数据的人体外源性植物miRNA跨界调控建模[J]. 吉林大学学报(工学版), 2018, 48(4): 1206-1213.
[6] 黄岚, 纪林影, 姚刚, 翟睿峰, 白天. 面向误诊提示的疾病-症状语义网构建[J]. 吉林大学学报(工学版), 2018, 48(3): 859-865.
[7] 李雄飞, 冯婷婷, 骆实, 张小利. 基于递归神经网络的自动作曲算法[J]. 吉林大学学报(工学版), 2018, 48(3): 866-873.
[8] 刘杰, 张平, 高万夫. 基于条件相关的特征选择方法[J]. 吉林大学学报(工学版), 2018, 48(3): 874-881.
[9] 耿庆田, 于繁华, 王宇婷, 高琦坤. 基于特征融合的车型检测新算法[J]. 吉林大学学报(工学版), 2018, 48(3): 929-935.
[10] 蔡振闹, 吕信恩, 陈慧灵. 基于反向细菌优化支持向量机的躯体化障碍预测模型[J]. 吉林大学学报(工学版), 2018, 48(3): 936-942.
[11] 陈绵书, 苏越, 桑爱军, 李培鹏. 基于空间矢量模型的图像分类方法[J]. 吉林大学学报(工学版), 2018, 48(3): 943-951.
[12] 王旭, 欧阳继红, 陈桂芬. 基于多重序列所有公共子序列的启发式算法度量多图的相似度[J]. 吉林大学学报(工学版), 2018, 48(2): 526-532.
[13] 杨欣, 夏斯军, 刘冬雪, 费树岷, 胡银记. 跟踪-学习-检测框架下改进加速梯度的目标跟踪[J]. 吉林大学学报(工学版), 2018, 48(2): 533-538.
[14] 刘雪娟, 袁家斌, 许娟, 段博佳. 量子k-means算法[J]. 吉林大学学报(工学版), 2018, 48(2): 539-544.
[15] 范敏, 韩琪, 王芬, 宿晓岚, 徐浩, 吴松麟. 基于多层次特征表示的场景图像分类算法[J]. 吉林大学学报(工学版), 2017, 47(6): 1909-1917.
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
No Suggested Reading articles found!