基于多层次特征表示的场景图像分类算法

doi:10.13229/j.cnki.jdxbgxb201706032

摘要/Abstract

摘要： 针对场景图像种类增多、场景复杂度增加和场景内容增大的趋势,本文提出了一种基于多层次特征表示的场景图像分类算法。首先采用Object Bank目标属性的高层特征表示方法,经分类器预测出该图像所属的场景主题;然后在同一场景主题内,采用基于底层特征的局部约束低秩编码方法提取图像特征;在低秩编码方法中加入局部约束正则化并采用F-范数替代核范数的优化方法,减少计算复杂度,实现对场景图像较为细致的理解。这种由高层特征和底层特征相结合的多层次特征表示方法,从对象特征的粗理解到底层细节特征的详细解析,充分利用了不同特征间层层递进和互补的关系,实验结果证明了本文算法的有效性。

关键词: 计算机应用, 目标属性, 低秩编码, 多层次特征, 场景图像分类

Abstract: With the increases in categories, complexity and content of scene images, a categorization algorithm based on multi-level features representation was proposed. First, object attributes based on high-level feature representation were available. Using simple classifiers, the topics of scene images were exported. Then in the same topic, the low-level feature in the image was extracted by the way of fast locality-constrained low rank coding. Meanwhile, in order to reduce the computational complexity, the method of adding local constraint regularization and replacing kernel norm with F-norm in the processing of low rank coding was adopted to achieve detailed understanding of scene images. Achieving scene classification from coarse understanding of object characteristics to detailed analysis of low-level feature, the method can make full use of the progressive and complementary relationship between different features. The experiment results show that better classification effect is obtained.

Key words: computer application, object bank, low rank coding, multi-level features, scene image categorization

中图分类号:

TP391.4

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.

FAN Min, HAN Qi, WANG Fen, SU Xiao-lan, XU Hao, WU Song-lin. Scene image categorization algorithm based on multi-level features representation[J]. 吉林大学学报(工学版), 2017, 47(6): 1909-1917.

参考文献

[1] Forsyth D A, Ponce J. Computer Vision: a modern approach[M]. New Jersey: Pearson Educacion Inc., 2002.
[2] Xiao J X, Hays J, Ehinger K A, et al. Sundatabase: large-scale scene recognition from abbeyto zoo[C]//IEEE Conference on Computer Vision and Pattern Reco-gnition (CVPR), San Francisco, California, USA, 2010:3485-3492.
[3] 李学龙,史建华,董永生,等. 场景图像分类技术综述[J].中国科学:信息科学,2015,45(7):827-848.
Li Xue-long, Shi Jian-hua, Dong Yong-sheng, et al. Summarize of scene image classification technology[J].Science China Information Sciences, 2015, 45(7):827-848.
[4] Lowe D G. Distinctive image features from scaleinvariantkeypoints[J]. International Journal of Computer Vision, 2004, 60(2):91-110.
[5] Oliva A, Torralba A. Modeling the shape of the scene: a holistic representation of the spatial envelope[J].International Journal of Computer Vision, 2001, 42(3): 145-175.
[6] Dalal N, Triggs B. Histograms of oriented gradientsfor human detection[C]//IEEE Conference on Computer Vision and Pattern Recognition(CVPR), San Diego, CA, USA, 2005, 1(12):886-893.
[7] 刘萍萍,赵宏伟,耿庆田,等.基于局部特征和视皮层识别机制的图像分类[J]. 吉林大学学报:工学版, 2011, 41 (5): 1401-1406.
Liu Ping-ping,Zhao Hong-wei,Geng Qing-tian, et al.Image classification method based on local feature and visual cortex recognition mechanism[J]. Journal of Jilin University (Engineering and Technology Edition), 2011, 41(5):1401-1406.
[8] Yang J, Yu K, Gong Y, et al. Linear spatial pyramidmatching using sparse coding for image classification[C]//Computer Society Conference on Computer Vision and Pattern Recognition(CVPR), Miami, FL, 2009: 1794-1801.
[9] Wang J, Yang J, Yu K, et al. Locality-constrained lin-ear coding for image classification[C]//Computer Society Conference on Computer Vision and Pattern Rec-ognition (CVPR),San Francisco, California, USA, 2010, 119(5):3360-3367.
[10] Xi Peng, Rui Yan, Bo Zhao, et al. Fast low rank representation based spatial pyramid matching for image classification[J]. Knowledge Based Systems, 2015, 90(C):14-22.
[11] Datta R, Joshi D, Li J. Image retrieval: ideas, influences, and trends of the new age[J].ACM, Computing Surveys, 2008, 40(2): 1-60.
[12] 陈涛, 邓辉舫, 刘靖. 基于密度聚类和多示例学习的图像分类方法[J]. 吉林大学学报:工学版, 2014, 44 (4):1126-1134.
Chen Tao,Deng Hui-fang,Liu Jing. Image categorization method using density clustering on region features and mutiinstance learning[J]. Journal of Jilin University (Engineering and Technology Edition), 2014, 44 (4):1126-1134.
[13] Li L J, Su H, Xing E P, et al. Object bank: a highlevel image representation for scene classification & s-emanticfeature sparsification[J]. Advances in Neural Information Proceedings Systems, Vancouver, 2010, 26 (6):719-729.
[14] Li Li-jia, Su Hao, Lim Yong-whan , et al. Objects as attributes for scene classification[J]. Trends and Topics in Computer Vision, 2010, 6553: 57-69.
[15] Juneja M, Vedialdi A, Jawahar C V, et al. Blocks thatshout: distinctive part for scene classification[C]//IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Portland, OR USA, 2013, 9(4):923-930.
[16] Sadeghi F, Tappen M F. Latent pyramidal regions for recognizing scenes[C]//European Conference on Computer Vision (ECCV), Firenze, Italy, 2012, 7576(1): 228-241.
[17] Yu Jun, Tao Da-cheng, Rui Yong, et al. Pairwise constrains based multiview features fusion for scene classification[J]. Pattern Recognition, 2013, 46(2):483-396.
[18] Luo Y, Tao D, Xu C, et al. Multiview vector-valued manifold regularization for multilabel image classification[J].IEEE Transactions on Neural Networks and Learning Systems, 2013, 24(5):709-722.
[19] Fan Min, Wang Fen, et al. Fast locality-constrained low-rank coding for image classification[C]//The Chinese Automation Congress (CAC), Wuhan, China, 2015:644-650.
[20] Felzenszwalb P, McAllester D, Ramanan D. A discriminatively trained, multiscale, deformable part model[C]//IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Anchorage, Alaska, USA, 2008:1-8.
[21] Felzenszwalb P, Girshick R B, McAllester D, et al. Object detection with discriminatively trained part-bas-ed models[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2010, 32(9): 1627-1645.
[22] Andrews S, Tsochantaridis I, Hofmann T. Support vector machines for multiple-instance learning[J]. Advances in Neural Information Processing Systems, Vancouver, 2002, 15(2): 561-568.
[23] Grauman K, Darrell T. Pyramid match kernels: Disc-riminative classification with sets of image features[C]//IEEE International Conference on Computer Vision (ICCV), Beijing, China, 2006:1458-1465.
[24] Lazebnik S, Schmid C, Ponce J. Beyond bags of features: spatial pyramid matching for recognizingnatur-al scene categories[C]//IEEE Conference on Computer Vision and Pattern Recognition(CVPR), New York, NY, USA, 2006: 2169-2178.
[25] Candes E, Recht B. Exact matrix completion via convex optimization[J]. Foundations of Computational Mathematics, 2008, 9: 712-717.
[26] Lin Z, Ganesh A, Wright J, et al. Fast convex optimization algorithms for exact recovery of a corrupted lowrank matrix[J].Journal of the Marine Biological Association of the UK, 2009, 56(3):707-722.
[27] Zhang H, Yi Z, Peng X. fLRR: fast low-rank repre-sentation using Frobenius-norm[J]. Electronics Letters, 2014, 50 (13):936-938.
[28] Yu K, Zhang T, Gong Y. Nonlinear learning using lo-calcoordinate coding[C]//Proc of NIPS, 2009:2223-2231.
[29] Yang Lei, Re Yan-yunn,Zhang Wen-qiang,et al. 3D depth image analysis for indoor fall detection of elderly people[J].Digital Communications & Networks, 2016, 2(1):24-33.
[30] Xu H, Hua K, Wang H. Adaptive FEC coding and cooperative relayed wireless image transmission[J]. Digital Communications & Networks, 2015, 1(3):213-221.
[31] Li L J,Li Fei-fei. What, where and who? classifyi-ng events by scene and object recognition[C]//IEEE International Conference on Computer Vision (ICCV), Rio de Janeiro,Brazil, 2007:1-8.
[32] Li Fei-fei, Perona P. A Bayesian hierarchical model for learning natural scene categories[C]//IEEE Confer-ence on Computer Vision and Pattern Recognition (CVPR), San Diego, CA,USA, 2005:524-531.

相关文章 15

[1]	刘富,宗宇轩,康冰,张益萌,林彩霞,赵宏伟. 基于优化纹理特征的手背静脉识别系统[J]. 吉林大学学报(工学版), 2018, 48(6): 1844-1850.
[2]	王利民,刘洋,孙铭会,李美慧. 基于Markov blanket的无约束型K阶贝叶斯集成分类模型[J]. 吉林大学学报(工学版), 2018, 48(6): 1851-1858.
[3]	金顺福,王宝帅,郝闪闪,贾晓光,霍占强. 基于备用虚拟机同步休眠的云数据中心节能策略及性能[J]. 吉林大学学报(工学版), 2018, 48(6): 1859-1866.
[4]	赵东,孙明玉,朱金龙,于繁华,刘光洁,陈慧灵. 结合粒子群和单纯形的改进飞蛾优化算法[J]. 吉林大学学报(工学版), 2018, 48(6): 1867-1872.
[5]	刘恩泽,吴文福. 基于机器视觉的农作物表面多特征决策融合病变判断算法[J]. 吉林大学学报(工学版), 2018, 48(6): 1873-1878.
[6]	欧阳丹彤, 范琪. 子句级别语境感知的开放信息抽取方法[J]. 吉林大学学报(工学版), 2018, 48(5): 1563-1570.
[7]	刘富, 兰旭腾, 侯涛, 康冰, 刘云, 林彩霞. 基于优化k-mer频率的宏基因组聚类方法[J]. 吉林大学学报(工学版), 2018, 48(5): 1593-1599.
[8]	桂春, 黄旺星. 基于改进的标签传播算法的网络聚类方法[J]. 吉林大学学报(工学版), 2018, 48(5): 1600-1605.
[9]	刘元宁, 刘帅, 朱晓冬, 陈一浩, 郑少阁, 沈椿壮. 基于高斯拉普拉斯算子与自适应优化伽柏滤波的虹膜识别[J]. 吉林大学学报(工学版), 2018, 48(5): 1606-1613.
[10]	车翔玖, 王利, 郭晓新. 基于多尺度特征融合的边界检测算法[J]. 吉林大学学报(工学版), 2018, 48(5): 1621-1628.
[11]	赵宏伟, 刘宇琦, 董立岩, 王玉, 刘陪. 智能交通混合动态路径优化算法[J]. 吉林大学学报(工学版), 2018, 48(4): 1214-1223.
[12]	黄辉, 冯西安, 魏燕, 许驰, 陈慧灵. 基于增强核极限学习机的专业选择智能系统[J]. 吉林大学学报(工学版), 2018, 48(4): 1224-1230.
[13]	傅文博, 张杰, 陈永乐. 物联网环境下抵抗路由欺骗攻击的网络拓扑发现算法[J]. 吉林大学学报(工学版), 2018, 48(4): 1231-1236.
[14]	曹洁, 苏哲, 李晓旭. 基于Corr-LDA模型的图像标注方法[J]. 吉林大学学报(工学版), 2018, 48(4): 1237-1243.
[15]	侯永宏, 王利伟, 邢家明. 基于HTTP的动态自适应流媒体传输算法[J]. 吉林大学学报(工学版), 2018, 48(4): 1244-1253.

Metrics

Viewed

Full text

Abstract

Cited

Shared

Discussed