Please wait a minute...
FITEE
Front. Inform. Technol. Electron. Eng.  2015, Vol. 16 Issue (10): 817-828    DOI: 10.1631/FITEE.1500070
    
超越隐主题包模型：针对场景类别识别的空间金字塔匹配
Fu-xiang Lu, Jun Huang
School of Information Science & Engineering, Lanzhou University, Lanzhou 730000, China; Shanghai Advanced Research Institute, Chinese Academy of Sciences, Shanghai 201210, China
Beyond bag of latent topics: spatial pyramid matching for scene category recognition
Fu-xiang Lu, Jun Huang
School of Information Science & Engineering, Lanzhou University, Lanzhou 730000, China; Shanghai Advanced Research Institute, Chinese Academy of Sciences, Shanghai 201210, China
 全文: PDF 
摘要： 目的：随着智能手机、数码相机的普及和互联网的高速发展，基于内容的场景类别识别对于图像数据库标注和检索具有重要意义。在场景类别数目比较多的情况下，本文基于概率隐语义分析（pLSA）和自适应提升（AdaBoost）算法，实现一种鲁棒的场景类别识别算法。
创新点：记录pLSA学习得到的主题的位置关系，提出金字塔主题直方图；在词包（bag-of-words）模型中采用不同的兴趣点提取算子和不同的局部区域描述符，实现异质金字塔单词直方图，显著提升场景识别准确率；提出一种两级多分类算法。
方法：利用期望最大化（EM）算法计算图像或图像块的pLSA主题分布，通过空间金字塔（SP）记录主题之间的大致位置关系；通过对兴趣点提取算子和区域描述符的比较研究，在词包模型中选用稠密兴趣点提取算子和六种区域描述符，从而得到六个金字塔主题直方图用来表示图像；为充分利用各异质金字塔主题直方图信息，先用AdaBoost选取分辨能力强的主题并计算测试图像的后验概率，再由prod-max融合规则确定测试图像的类别。
结论：对于特定的兴趣点提取算子和特定的区域描述符，金字塔主题直方图对所有基准图像库的场景识别率均高于标准pLSA主题直方图；融合各异质金字塔主题直方图显著提高了场景类别识别率。
关键词： 场景类别识别;  概率隐语义分析;  词包;  自适应提升    
Abstract: We propose a heterogeneous, mid-level feature based method for recognizing natural scene categories. The proposed feature introduces spatial information among the latent topics by means of spatial pyramid, while the latent topics are obtained by using probabilistic latent semantic analysis (pLSA) based on the bag-of-words representation. The proposed feature always performs better than standard pLSA because the performance of pLSA is adversely affected in many cases due to the loss of spatial information. By combining various interest point detectors and local region descriptors used in the bag-of-words model, the proposed feature can make further improvement for diverse scene category recognition tasks. We also propose a two-stage framework for multi-class classification. In the first stage, for each of possible detector/descriptor pairs, adaptive boosting classifiers are employed to select the most discriminative topics and further compute posterior probabilities of an unknown image from those selected topics. The second stage uses the prod-max rule to combine information coming from multiple sources and assigns the unknown image to the scene category with the highest ‘final’ posterior probability. Experimental results on three benchmark scene datasets show that the proposed method exceeds most state-of-the-art methods.
Key words: Scene category recognition    Probabilistic latent semantic analysis    Bag-of-words    Adaptive boosting
收稿日期: 2015-03-07 出版日期: 2015-10-08
CLC:  TP391.4  
服务　　
把本文推荐给朋友
加入引用管理器
E-mail Alert
RSS
作者相关文章　　
Fu-xiang Lu
Jun Huang

引用本文:

Fu-xiang Lu, Jun Huang. Beyond bag of latent topics: spatial pyramid matching for scene category recognition. Front. Inform. Technol. Electron. Eng., 2015, 16(10): 817-828.

链接本文:

http://www.zjujournals.com/xueshu/fitee/CN/10.1631/FITEE.1500070    或    http://www.zjujournals.com/xueshu/fitee/CN/Y2015/V16/I10/817

[1] Rong-Feng Zhang , Ting Deng , Gui-Hong Wang , Jing-Lun Shi , Quan-Sheng Guan . 基于可靠特征点分配算法的鲁棒性跟踪框架[J]. Frontiers of Information Technology & Electronic Engineering, 2017, 18(4): 545-558.
[2] Yuan-ping Nie, Yi Han, Jiu-ming Huang, Bo Jiao, Ai-ping Li. 基于注意机制编码解码模型的答案选择方法[J]. Frontiers of Information Technology & Electronic Engineering, 2017, 18(4): 535-544.
[3] Yue-ting Zhuang, Fei Wu, Chun Chen, Yun-he Pan. 挑战与希望：AI2.0时代从大数据到知识[J]. Frontiers of Information Technology & Electronic Engineering, 2017, 18(1): 3-14.
[4] Le-kui Zhou, Si-liang Tang, Jun Xiao, Fei Wu, Yue-ting Zhuang. 基于众包标签数据深度学习的命名实体消歧算法[J]. Frontiers of Information Technology & Electronic Engineering, 2017, 18(1): 97-106.
[5] M. F. Kazemi, M. A. Pourmina, A. H. Mazinan. 图像水印框架的层级-方向分解分析[J]. Front. Inform. Technol. Electron. Eng., 2016, 17(11): 1199-1217.
[6] Guang-hui Song, Xiao-gang Jin, Gen-lang Chen, Yan Nie. 基于两级层次特征学习的图像分类方法[J]. Front. Inform. Technol. Electron. Eng., 2016, 17(9): 897-906.
[7] Jia-yin Song, Wen-long Song, Jian-ping Huang, Liang-kuan Zhu. 基于边界分析的森林冠层半球图像中心点定位与分割[J]. Front. Inform. Technol. Electron. Eng., 2016, 17(8): 741-749.
[8] Gao-li Sang, Hu Chen, Ge Huang, Qi-jun Zhao. 基于稠密多变量标签的“连续”头部姿态估计方法[J]. Front. Inform. Technol. Electron. Eng., 2016, 17(6): 516-526.
[9] Chu-hua Huang, Dong-ming Lu, Chang-yu Diao. 基于多尺度轮廓插值生成准密集时变点云模型序列[J]. Front. Inform. Technol. Electron. Eng., 2016, 17(5): 422-434.
[10] Xi-chuan Zhou, Fang Tang, Qin Li, Sheng-dong Hu, Guo-jun Li, Yun-jian Jia, Xin-ke Li, Yu-jie Feng. 基于多维尺度拉普拉斯分析方法的全球流感疫情监测[J]. Front. Inform. Technol. Electron. Eng., 2016, 17(5): 413-421.
[11] Xiao-hu Ma, Meng Yang, Zhao Zhang. 局部不相关的局部判别嵌入人脸识别算法[J]. Front. Inform. Technol. Electron. Eng., 2016, 17(3): 212-223.
[12] Yu Liu, Bo Zhu. 带有几何形变的变形图像配准[J]. Front. Inform. Technol. Electron. Eng., 2015, 16(10): 829-837.
[13] Zheng-wei Huang, Wen-tao Xue, Qi-rong Mao. 基于无监督特征学习的语音情感识别方法[J]. Front. Inform. Technol. Electron. Eng., 2015, 16(5): 358-366.
[14] Xun Liu, Yin Zhang, San-yuan Zhang, Ying Wang, Zhong-yan Liang, Xiu-zi Ye. 基于高清监控图像的工程车辆检测算法[J]. Front. Inform. Technol. Electron. Eng., 2015, 16(5): 346-357.
[15] Xiao-fang Huang, Shou-qian Sun, Ke-jun Zhang, Tian-ning Xu, Jian-feng Wu, Bin Zhu. 一种皮影人物建模及动画生成方法[J]. Front. Inform. Technol. Electron. Eng., 2015, 16(5): 367-379.