您的位置:山东大学 -> 科技期刊社 -> 《山东大学学报(工学版)》

山东大学学报(工学版) ›› 2016, Vol. 46 ›› Issue (2): 14-21.doi: 10.6040/j.issn.1672-3961.2.2015.065

• 机器学习与数据挖掘 • 上一篇    下一篇

基于成分金字塔匹配的对象分类方法

朱杰1,2,王晶1,刘菲3,高冠东1,段庆1   

  1. 1. 中央司法警官学院信息管理系, 河北 保定 071000;2. 北京交通大学计算机与信息技术学院交通数据分析与挖掘北京市重点实验室, 北京 100044;3.中央司法警官学院现代教育技术中心, 河北 保定 071000
  • 收稿日期:2015-05-16 出版日期:2016-04-20 发布日期:2015-05-16
  • 作者简介:朱杰(1982— ),男,河北保定人,博士研究生,主要研究方向为机器学习,机器视觉. E-mail:arthurzhujie@gmail.com
  • 基金资助:
    国家自然科学基金资助项目(61033013,61370129,61375062,61300072,61105056,61402462);国家教育部博士点基金资助项目(20120009110006);中央高校基础科研业务经费北京市科委资助项目(Z131110002813118);河北省教育厅青年基金资助项目(QN2015099);2014年度全国司法行政系统理论研究规划课题资助项目(14GH2022);中国监狱工作协会监狱理论研究课题资助项目(2014YL41);河北省社会科学基金资助项目(HB15TQ013)

Object classification method based on component pyramid matching

ZHU Jie1,2, WANG Jing1, LIU Fei3, GAO Guandong1, DUAN Qing1   

  1. 1. Department of Information Management, The Central Institute for Correctional Police, Baoding 071000, Heibei, China;
    2. Beijing Key Lab of Traffic Data Analysis and Mining, School of Computer and Information Technology, Beijing Jiaotong University, Beijing 100044, China;
    3. Modern Educational Technology Center, The Central Institute for Correctional Police, Baoding 071000, Heibei, China
  • Received:2015-05-16 Online:2016-04-20 Published:2015-05-16

摘要: 提出基于成分金字塔匹配(component pyramid matching, CPM)的图像表示方法,将图像块按照颜色进行分层,在每一层中通过优化的方式选取几种颜色的图像块作为当前层次图像的前景成分,其余颜色的图形块作为图像的背景成分。前景成分对应对象的某些区域,能够为图像表示提供弱语义信息。然后,利用相似的颜色选择方法,对每一层背景成分进行再次划分,将其分为下一层前景成分和背景成分两部分。最后将这些成分所表示的直方图连接起来作为图像表示用于分类。试验采用Soccer、Flower17和Flower102 3个图像集进行测评,试验结果表明提出的算法能够得到比较好的分类结果。

关键词: 图像表示, 成分金字塔匹配, 颜色, 分类, 层次

Abstract: The image representation method based on component pyramid matching(CPM)was proposed, which separated the patches into different levels based on colors. In each level, some colors were selected by the optimal color selection method, then the patches with these selected colors were considered as the foreground components, and the rest of the patches with other colors were considered as the background components. Usually, the foreground components corresponded to some parts of the objects, which could supply weak semantic information for the image representation. Then, the background components were split into the foreground and background components in the next level based on the similar color selection method. The final representation of an image was obtained by concatenating the component histograms in each level. Classification results were presented on Soccer, Flower17 and Flower102 datasets, and the experiments showed that CMP could obtain satisfactory results in these datasets.

Key words: level, image representation, classification, component pyramid matching, color

中图分类号: 

  • TP301
[1] CSURKA G, DANCE CR, FAN LX, et al. Visual categorization with bags of keypoints[C] //Proceedings of the 8th European Conference on Computer Vision. Prague: IEEE, 2004:1-22.
[2] CAO Y, WANG C, LI Z, et al. Spatial-bag-of-features[C] //Proceedings of the 23th IEEE Computer Society Conference on Computer Vision and Pattern Recognition. San Francisco: IEEE, 2010:3352-3359.
[3] MORIOKA N, SATOH S. Building compact local pairwise codebook with joint feature space clustering[C] //Proceedings of the 11th European Conference on Computer Vision. Crete: IEEE, 2010:692-705.
[4] SIVIC J, RUSSELL B, EFROS A, et al. Discovering objects and their location in images[C] //Proceedings of the 10th International Conference on Computer Vision. Beijing:IEEE, 2005:370-377.
[5] GRAUMAN K, DARRELL T. The pyramid match kernel: Discriminative classification with sets of image features[C] //Proceedings of the 10th International Conference on Computer Vision. Beijing: IEEE, 2005:1458-1465.
[6] LAZEBNIK S, SCHMID C, PONCE J. Beyond bags of features: Spatial pyramid matching for recognizing natural scene categories[C] //Proceedings of the 19th IEEE Computer Society Conference on Computer Vision and Pattern Recognition. New York:IEEE, 2006:2169-2178.
[7] YANG J, YU K, GONG Y, et al. Linear spatial pyramid matching using sparse coding for image classification [C] //Proceedings of the 22th IEEE Computer Society Conference on Computer Vision and Pattern Recognition.Florida: IEEE, 2009:1794-1801.
[8] LI F, CARREIRA J, SMINCHISESCU C. Object recognition as ranking holistic figure-ground hypotheses[C] //Proceedings of the 23th IEEE Computer Society Conference on Computer Vision and Pattern Recognition. San Francisco: IEEE, 2010:1712-1719.
[9] CHEN Q, SONG Z, HUA Y, et al. Hierarchical matching with side information for image classification[C] //Proceedings of the 25th IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Rhode Island: IEEE, 2012:3426-3433.
[10] LI L J, SU H, LIM Y, et al. Object bank: an object-level image representation for high-level visual recognition[J].International Journal of Computer Vision, 2014, 107(1):20-39.
[11] FERNANDO B, FROMONT E, TUYTELAARS T. Mining mid-level features for image classification[J]. International Journal of Computer Vision, 2014, 108(3): 186-203.
[12] LIU J, ZHANG C, TIAN Q, et al. One step beyond bags of features: visual categorization using component[C] //Proceedings of the International Conference on Image Processing. Brussels: IEEE, 2011:2417-2420.
[13] LOWE D G. Object recognition from local scale-invariant features[C] //Proceedings of the 7th International Conference on Computer Vision. Kerkyra:IEEE, 1999: 1150-1157.
[14] VAN-DE-WEIJER J, SCHMID C, VERBEEK J, et al. Learning color names for real-world applications[J].IEEE Transactions on Image Processing, 2009, 18(7):1512-1523.
[15] VAN-DE-WEIJER J, SCHMID C. Coloring local feature extraction[C] //Proceedings of the 9th European Conference on Computer Vision. Graz: IEEE, 2006:334-348.
[16] SHAHBAZ-KHAN F, VAN-DE-WEIJER J, VANRELL M.Top-down color attention for object recognition[C] //Proceedings of the 12th International Conference on Computer Vision. Tokyo: IEEE, 2009:979-986.
[17] NILSBACK M E, ZISSEMAN A. A visual vocabulary for flower classification[C] //Proceedings of the 19th IEEE Computer Society Conference on Computer Vision and Pattern Recognition. New York: IEEE, 2006:1447-1454.
[18] NILSBACK M E, ZISSERMAN A. Automated flower classification over a large number of classes[C] //Proceedings of the 6th Indian Conference on Computer Vision, Graphics and Image Processing. Bhubaneswar: IEEE, 2008:722-729.
[19] FERNANDO B, FROMONT E, MUSELET D, et al. Discriminative feature fusion for image classification[C] //Proceedings of the 25th IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Rhode Island: IEEE, 2012:3434-3441.
[20] GEHLER P, NOWOZIN S. On feature combination for multiclass object classification[C] //Proceedings of the 12th International Conference on Computer Vision. Tokyo:IEEE, 221-228.
[21] YUAN X T, YAN S. Visual classification with multi-task joint sparse representation[C] //Proceedings of the 23th IEEE Computer Society Conference on Computer Vision and Pattern Recognition. San Francisco: IEEE, 2010:3493-3500.
[22] YAN F, MIKOLAJCZYK K, BARNARD M, et al. Lp norm multiple kernel fisher discriminant analysis for object and image categorisation[C] //Proceedings of the 23th IEEE Computer Society Conference on Computer Vision and Pattern Recognition. San Francisco: IEEE, 2010:3626-3632.
[23] KANAN C, COTTRELL G. Robust classification of objects, faces, and flowers using natural image statistics [C] //Proceedings of the 23th IEEE Computer Society Conference on Computer Vision and Pattern Recognition. San Francisco: IEEE, 2010:2472-2479.
[24] CHAI Y, LEMPITSKY V, ZISSERMAN A. BiCoS: A Bi-level Co-Segmentation Method for Image Classification[C] //Proceedings of the 13th International Conference on Computer Vision. Barcelona: IEEE, 2011:2579-2586.
[25] CHAI Y, RAHTU E, RAHTU E, et al. Tricos: A tri-level class-discriminative co-segmentation method for image classification[C] //Proceedings of the 12th European Conference on Computer Vision. Firenze: IEEE, 2012:794-807.
[1] 张璞,刘畅,王永. 基于特征融合和集成学习的建议语句分类模型[J]. 山东大学学报 (工学版), 2018, 48(5): 47-54.
[2] 叶明全,高凌云,万春圆. 基于人工蜂群和SVM的基因表达数据分类[J]. 山东大学学报(工学版), 2018, 48(3): 10-16.
[3] 王换,周忠眉. 一种基于聚类的过抽样算法[J]. 山东大学学报(工学版), 2018, 48(3): 134-139.
[4] 曹雅,邓赵红,王士同. 基于单调约束的径向基函数神经网络模型[J]. 山东大学学报(工学版), 2018, 48(3): 127-133.
[5] 龙柏,曾宪宇,李徵,刘淇. 电商商品嵌入表示分类方法[J]. 山东大学学报(工学版), 2018, 48(3): 17-24.
[6] 谢志峰,吴佳萍,马利庄. 基于卷积神经网络的中文财经新闻分类方法[J]. 山东大学学报(工学版), 2018, 48(3): 34-39.
[7] 王婷婷,翟俊海,张明阳,郝璞. 基于HBase和SimHash的大数据K-近邻算法[J]. 山东大学学报(工学版), 2018, 48(3): 54-59.
[8] 陈嘉杰,王金凤. 基于蚁群算法求解Choquet模糊积分模型[J]. 山东大学学报(工学版), 2018, 48(3): 81-87.
[9] 王磊,邓晓刚,曹玉苹,田学民. 基于MLFDA的化工过程故障模式分类方法[J]. 山东大学学报(工学版), 2017, 47(5): 179-186.
[10] 李素姝,王士同,李滔. 基于LS-SVM与模糊补准则的特征选择方法[J]. 山东大学学报(工学版), 2017, 47(3): 34-42.
[11] 何其佳,刘振丙,徐涛,蒋淑洁. 基于LBP和极限学习机的脑部MR图像分类[J]. 山东大学学报(工学版), 2017, 47(2): 86-93.
[12] 郭超,杨燕,江永全,宋祎. 基于多视图分类集成的高铁工况识别[J]. 山东大学学报(工学版), 2017, 47(1): 7-14.
[13] 陈泽华,尚晓慧,柴晶. 基于混合Hausdorff距离的多示例学习近邻分类器[J]. 山东大学学报(工学版), 2016, 46(6): 15-22.
[14] 王斌,常发亮,刘春生. 基于多特征融合的交通标志分类[J]. 山东大学学报(工学版), 2016, 46(4): 34-40.
[15] 郭志波, 董健, 庞成. 多技术融合的Mean-Shift目标跟踪算法[J]. 山东大学学报(工学版), 2015, 45(2): 10-16.
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
[1] 李辉平, 赵国群, 张雷, 贺连芳. 超高强度钢板热冲压及模内淬火工艺的发展现状[J]. 山东大学学报(工学版), 2010, 40(3): 69 -74 .
[2] 李士进,王声特,黄乐平. 基于正反向异质性的遥感图像变化检测[J]. 山东大学学报(工学版), 2018, 48(3): 1 -9 .
[3] 高厚磊 田佳 杜强 武志刚 刘淑敏. 能源开发新技术——分布式发电[J]. 山东大学学报(工学版), 2009, 39(5): 106 -110 .
[4] 庞志俭 张长桥. 甲基丙烯酸十二酯基二元共聚制备缔合减阻剂的合成与性能研究[J]. 山东大学学报(工学版), 2009, 39(5): 128 -132 .
[5] 王学平,王登杰,孙英明,董磊 . 免棱镜全站仪在桥梁检测中的应用[J]. 山东大学学报(工学版), 2007, 37(3): 105 -108 .
[6] 陈朋 胡文容 裴海燕. 一株反硝化细菌LZ-14的筛选及其脱氮特性[J]. 山东大学学报(工学版), 2009, 39(5): 133 -138 .
[7] 张宏博,苗海涛,宋修广. 长期交通荷载作用下粉砂土累积变形本构模型构建及数值积分格式[J]. 山东大学学报(工学版), 2010, 40(2): 59 -65 .
[8] 周绍伟. 随机Markov跳跃系统有限时间稳定性[J]. 山东大学学报(工学版), 2016, 46(2): 78 -84 .
[9] 赵继增. 青岛胶州湾海底隧道涌水断层全断面帷幕注浆技术研究[J]. 山东大学学报(工学版), 2009, 39(6): 116 -120 .
[10] 赵冠琳,邹增大,王新洪,杜宝帅 . 激光熔覆原位自生TiC-VC复合增强铁基合金层的研究[J]. 山东大学学报(工学版), 2008, 38(2): 6 -9 .