A Novel Distribution of Local Invariant Features for Classification of Scene and Object Categories

被引：0
作者：
Guo, LiJun [1 ]
Zhao, JieYu [2 ]
Zhang, Rong [2 ]
机构：
[1] Chinese Acad Sci, Grad Univ, Inst Comp Technol, Beijing 100864, Peoples R China
[2] Ningbo Univ Fac Informat Sci & Engn, Ningbo, Zhejiang, Peoples R China
来源：
INTELLIGENT INFORMATION PROCESSING V | 2010年 / 340卷
关键词：
Image classification; distribution representation; probability signature; kernel method;
D O I：
10.1007/978-3-642-16327-2_37
中图分类号：
TP18 [人工智能理论];
学科分类号：
081104 ; 0812 ; 0835 ; 1405 ;
摘要：
A new image representation based on distribution of local invariant features to be used in a discriminative approach to image categorization is presented. The representation which is called Probability Signature (PS) is combined with character of two distribution models Probability Density Function and standard signatures. The PS representation retains high discriminative power of PDF model, and is suited for measuring dissimilarity of images with Earth Mover's Distance (EMD), which allows for partial matches of compared distributions. It is evaluated on whole-image classification tasks from the scene and category image datasets. The comparative experiments show that the proposed algorithm has inspiring performance.
引用
收藏
页码：308 / +
页数：2
相关论文
共 13 条
  • [1] Support vector machines for histogram-based image classification
    Chapelle, O
    Haffner, P
    Vapnik, VN
    [J]. IEEE TRANSACTIONS ON NEURAL NETWORKS, 1999, 10 (05): : 1055 - 1064
  • [2] Csurka G., 2004, WORKSH STAT LEARN CO, V1, P1, DOI DOI 10.1234/12345678
  • [3] Farquhar J., 2005, 118141 LAVA, P141
  • [4] Gionis A, 1999, PROCEEDINGS OF THE TWENTY-FIFTH INTERNATIONAL CONFERENCE ON VERY LARGE DATA BASES, P518
  • [5] Grauman K, 2005, PROC CVPR IEEE, P627
  • [6] Hillier F.S., 1990, INTRO MATH PROGRAMMI
  • [7] Ke Y, 2004, PROC CVPR IEEE, P506
  • [8] Distinctive image features from scale-invariant keypoints
    Lowe, DG
    [J]. INTERNATIONAL JOURNAL OF COMPUTER VISION, 2004, 60 (02) : 91 - 110
  • [9] A performance evaluation of local descriptors
    Mikolajczyk, K
    Schmid, C
    [J]. IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2005, 27 (10) : 1615 - 1630
  • [10] Moreno P.J., 2004, NEURAL INFORM PROCES, P430
12