一种多层次抽象语义决策图像分类方法

刘鹏; 叶志鹏; 赵巍; 唐降龙

doi:10.16383/j.aas.2015.c140238

一种多层次抽象语义决策图像分类方法

doi: 10.16383/j.aas.2015.c140238

1.
哈尔滨工业大学计算机科学与技术学院模式识别与智能系统研究中心哈尔滨 150001

基金项目:

国家自然科学基金(61171184, 61201309, 61440025) 资助

详细信息

作者简介:
叶志鹏哈尔滨工业大学计算机科学与技术学院博士研究生. 2013 年获得哈尔滨工业大学计算机应用技术硕士学位.主要研究方向为模式识别, 机器学习.E-mail: yezhipeng@hit.edu.cn

通讯作者:
唐降龙哈尔滨工业大学计算机科学与技术学院教授. 1995 年获得哈尔滨工业大学计算机应用技术博士学位. 主要研究方向为模式识别, 图像处理, 机器学习.E-mail: tangxl@hit.edu.cn

计量
- 文章访问数: 1481
- HTML全文浏览量: 66
- PDF下载量: 1101
- 被引次数: 0
出版历程
- 收稿日期: 2014-04-23
- 修回日期: 2015-01-06
- 刊出日期: 2015-05-20

A Multiple Layer Abstract Semantic Decision Method for Image Classification

1.
Pattern Recognition and Intelligent System Research Center, School of Computer Science and Technology, Harbin Institute of Technology, Harbin 150001

Funds:

Supported by National Natural Science Foundation of China (61171184, 61201309, 61440025)

摘要

摘要: 视觉词包(Bag-of-visual-words, BoVW) 模型是一种有效的图像分类方法. 本文提出一种基于语义抽象的多层次决策(Multiple layer decision, MLD) 方法,通过在BoVW 中引入抽象语义进行多层次扩展,采用语义保留方法生成具有语义的视觉词典,利用自底向上的方式逐层传递语义, 训练上层语义分类器;分类时采用自顶向下方式逐层判断待测样本的类别. 用标准数据集验证方法的分类性能. 结果表明,本文提出的方法与主流分类方法相比具有更好的分类性能.
- 图像分类 /
- 图像模糊分类 /
- 视觉词包模型 /
- 决策树 /
- 多层次决策
Abstract: Bag-of-visual-words (BoVW) is an effective method in image categorizing and retrieving task. A multiple layer decision method (MLD), which introduces abstract semantics of image categories into BoVW to carry out middle-level and upper-level extensions, is proposed in this paper. Semantics is preserved at the stage of generating visual vocabulary, based on which classifiers are trained in a bottom-up way. Abstract semantics is transferred during the training step. After that, the category of a test image is estimated gradually by classifier through each layer in a top-down way. Experiments on standard datasets show that the proposed method achieves better performance compared with mainstream classification methods.
- Image classification /
- image fuzzy classification /
- bag-of-visual-words (BoVW) /
- decision tree /
- multiple layer decision (MLD)

HTML全文

参考文献(37)

[1]	Csurka G, Dance C R, Fan L X, Willamowski J, Bray C. Visual categorization with bags of keypoints. In: Proceedings of the 2004 Workshop on Statistical Learning in Computer Vision, European Conference on Computer Vision. Berlin, Germany: Springer Berlin Heidelberg, 2004. 1-2
[2]	Zhang Su-Lan, Guo Ping, Zhang Ji-Fu, Hu Li-Hua. Automatic semantic image annotation with granular analysis method. Acta Automatica Sinica, 2012, 38(5): 688-697(张素兰, 郭平, 张继福, 胡立华. 图像语义自动标注及其粒度分析方法. 自动化学报, 2012, 38(5): 688-697)
[3]	[3] Qin J Z, Yung N H C. Scene categorization via contextual visual words. Pattern Recognition, 2010, 43(5): 1874-1888
[4]	[4] Elfiky N M, Khan F S, van De Weijer J, Gonzlez J. Discriminative compact pyramids for object and scene recognition. Pattern Recognition, 2012, 45(4): 1627-1636
[5]	[5] Wang F, Jiang Y G, Ngo C W. Video event detection using motion relativity and visual relatedness. In: Proceedings of the 16th ACM International Conference on Multimedia. NY, USA: ACM, 2008. 239-248
[6]	[6] Liu J E, Yang Y, Saleemi I, Shah M. Learning semantic features for action recognition via diffusion maps. Computer Vision and Image Understanding, 2012, 116(3): 361-377
[7]	[7] Lazebnik S, Schmid C, Ponce J. Beyond bags of features: spatial pyramid matching for recognizing natural scene categories. In: Proceedings of the 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. New York, USA: IEEE, 2006. 2169-2178
[8]	[8] Yuan J S, Wu Y, Yang M. Discovery of collocation patterns: from visual words to visual phrases. In: Proceedings of the 2007 IEEE Conference on Computer Vision and Pattern Recognition. Minneapolis, MN: IEEE, 2007. 1-8
[9]	[9] Du R, Wu Q, He X J, Yang J. Object categorization based on a supervised mean shift algorithm. In: Proceedings of the Computer Vision EECV 2012 Workshops and Demonstrations. Berlin, Germany: Springer Berlin Heidelberg, 2012. 611-614
[10]	Chai Y N, Rahtu E, Lempitsky V, van Gool L, Zisserman A. TriCoS: a tri-level class-discriminative co-segmentation method for image classification. In: Proceedings of the 2012 European Conference on Computer Vision. Berlin, Germany: Springer Berlin Heidelberg, 2012. 794-807
[11]	Krapac J, Verbeek J, Jurie F. Modeling spatial layout with fisher vectors for image categorization. In: Proceedings of the 2011 IEEE International Conference on Computer Vision (ICCV). Barcelona, Spain: IEEE, 2011. 1487-1494
[12]	Bolovinou A, Pratikakis I, Perantonis S. Bag of spatio-visual words for context inference in scene classification. Pattern Recognition, 2013, 46(3): 1039-1053
[13]	Wang J J, Yang J C, Yu K, Lv F J, Huang T, Gong Y H. Locality-constrained linear coding for image classification. In: Proceedings of the 2010 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). San Francisco, CA: IEEE, 2010. 3360-3367
[14]	van Gemert J C, Veenman C J, Smeulders A W M, Geusebroek J M. Visual word ambiguity. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2010, 32(7): 1271-1283
[15]	Liu J, Zhang C J, Tian Q, Xu C S, Lu H Q, Ma S D. One step beyond bags of features: visual categorization using components. In: Proceedings of the 18th IEEE International Conference on Image Processing (ICIP). Brussels, Belgium: IEEE, 2011. 2417-2420
[16]	Avrithis Y, Kalantidis Y. Approximate Gaussian mixtures for large scale vocabularies. In: Proceedings of the 12th European Conference on Computer Vision. Berlin, Germany: Springer-Verlag Berlin, Heidelberg, 2012. 15-28
[17]	Mikulk A, Perdoch M, Chum O, Matas J. Learning a fine vocabulary. In: Proceedings of the 11th European Conference on Computer Vision. Berlin, Germany: Springer-Verlag Berlin, Heidelberg, 2010. 1-14
[18]	Tang J H, Zha Z J, Tao D C, Chua T S. Semantic-gap-oriented active learning for multilabel image annotation. IEEE Transactions on Image Processing, 2012, 21(4): 2354-2360
[19]	Wu L, Hoi S C H, Yu N H. Semantics-preserving bag-of-words models and applications. IEEE Transactions on Image Processing, 2010, 19(7): 1908-1920
[20]	Ji C J, Zhou X D, Lin L, Yang W D. Labeling images by integrating sparse multiple distance learning and semantic context modeling. In: Proceedings of the 12th European Conference on Computer Vision. Berlin, Germany: Springer-Verlag Berlin, Heidelberg, 2012. 688-701
[21]	Liu J E, Yang Y, Shah M. Learning semantic visual vocabularies using diffusion distance. In: Proceedings of the 2009 IEEE Conference on Computer Vision and Pattern Recognition. Miami, FL: IEEE, 2009. 461-468
[22]	Penatti O A B, Silva F B, Valle E, Gouet-Brunet V, Torres R S. Visual word spatial arrangement for image retrieval and classification. Pattern Recognition, 2014, 47(2): 705-720
[23]	Li L J, Wang C, Lim Y, Blei D M, Li F F. Building and using a semantivisual image hierarchy. In: Proceedings of the 2010 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). San Francisco, CA: IEEE, 2010. 3336-3343
[24]	Bannour H, Hudelot C. Building semantic hierarchies faithful to image semantics. In: Proceedings of the 18th International Conference on Advances in Multimedia Modeling. Berlin, Germany: Springer-Verlag Berlin, Heidelberg, 2012. 4-15
[25]	Bannour H, Hudelot C. Hierarchical image annotation using semantic hierarchies. In: Proceedings of the 21st ACM International Conference on Information and Knowledge Management. New York, NY, USA: ACM, 2012. 2431-2434
[26]	Deng J, Berg A C, Li K, Li F F. What does classifying more than 10000 image categories tell us? In: Proceedings of the 11th European Conference on Computer Vision. Berlin, Germany: Springer-Verlag Berlin, Heidelberg, 2010. 71-84
[27]	Lorenza S, Jean-Daniel Z. Abstraction in Artificial Intelligence and Complex Systems. New York: Springer-Verlag New York Inc., 2013. 273-325
[28]	Everingham M, Van Gool L, Williams C K I, Winn J, Zisserman A. The pascal visual object classes (voc) challenge. International Journal of Computer Vision, 2010, 88(2): 303-338
[29]	Li F F, Fergus R, Perona P. Learning generative visual models from few training examples: an incremental Bayesian approach tested on 101 object categories. Computer Vision and Image Understanding, 2007, 106(1): 59-70
[30]	Fan R E, Chang K W, Hsieh C J, Wang X R, Lin C J. LIBLINEAR: A library for large linear classification. Journal of Machine Learning Research, 2008, 9: 1871-1874
[31]	Zhang Lin-Bo, Wang Chun-Heng, Xiao Bo-Hua, Shao Yun-Xue. Image representation using bag-of-phrases. Acta Automatica Sinica, 2012, 38(1): 46-54 (张琳波, 王春恒, 肖柏华, 邵允学. 基于Bag-of-phrases的图像表示方法. 自动化学报, 2012, 38(1): 46-54)
[32]	Fernando B, Fromont E, Muselet D, Sebban M. Supervised learning of Gaussian mixture models for visual vocabulary generation. Pattern Recognition, 2012, 45(2): 897-907
[33]	Su Y, Jurie F. Improving image classification using semantic attributes. International Journal of Computer Vision, 2012, 100(1): 59-77
[34]	Perronnin F, Snchez J, Mensink T. Improving the Fisher kernel for large-scale image classification. In: Proceedings of the 11th European Conference on Computer Vision. Berlin, Germany: Springer-Verlag Berlin, Heidelberg, 2010. 143-156
[35]	Zhong J, Wang J, Su Y T, Song Z J, Xing S K. Balance between object and background: object-enhanced features for scene image classification. Neurocomputing, 2013, 120: 15-23
[36]	Maji S, Berg A C, Malik J. Efficient classification for additive kernel SVMs. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2013, 35(1): 66-77
[37]	Bilen H, Namboodiri V P, Van Gool L J. Object and action classification with latent window parameters. International Journal of Computer Vision, 2014, 106(3): 237-251

施引文献

资源附件(0)

访问统计

点击查看大图

计量

文章访问数: 1481
HTML全文浏览量: 66
PDF下载量: 1101
被引次数: 0

姓名
邮箱
手机号码
标题
留言内容
验证码

留言板

一种多层次抽象语义决策图像分类方法

doi: 10.16383/j.aas.2015.c140238

作者简介:
叶志鹏哈尔滨工业大学计算机科学与技术学院博士研究生. 2013 年获得哈尔滨工业大学计算机应用技术硕士学位.主要研究方向为模式识别, 机器学习.E-mail: yezhipeng@hit.edu.cn

通讯作者:
唐降龙哈尔滨工业大学计算机科学与技术学院教授. 1995 年获得哈尔滨工业大学计算机应用技术博士学位. 主要研究方向为模式识别, 图像处理, 机器学习.E-mail: tangxl@hit.edu.cn

计量

A Multiple Layer Abstract Semantic Decision Method for Image Classification

计量

目录

留言板

一种多层次抽象语义决策图像分类方法

doi: 10.16383/j.aas.2015.c140238

作者简介: 叶志鹏 哈尔滨工业大学计算机科学与技术学院博士研究生. 2013 年获得哈尔滨工业大学计算机应用技术硕士学位.主要研究方向为模式识别, 机器学习.E-mail: yezhipeng@hit.edu.cn

通讯作者: 唐降龙 哈尔滨工业大学计算机科学与技术学院教授. 1995 年获得哈尔滨工业大学计算机应用技术博士学位. 主要研究方向为模式识别, 图像处理, 机器学习.E-mail: tangxl@hit.edu.cn

计量

出版历程

A Multiple Layer Abstract Semantic Decision Method for Image Classification

计量

出版历程

目录

作者简介:
叶志鹏哈尔滨工业大学计算机科学与技术学院博士研究生. 2013 年获得哈尔滨工业大学计算机应用技术硕士学位.主要研究方向为模式识别, 机器学习.E-mail: yezhipeng@hit.edu.cn

通讯作者:
唐降龙哈尔滨工业大学计算机科学与技术学院教授. 1995 年获得哈尔滨工业大学计算机应用技术博士学位. 主要研究方向为模式识别, 图像处理, 机器学习.E-mail: tangxl@hit.edu.cn