Overcomplete ICA-based manmade scene classification

被引:0
|
作者
Boutell, M [1 ]
Luo, JB [1 ]
机构
[1] Univ Rochester, Dept Comp Sci, Rochester, NY 14627 USA
关键词
D O I
10.1109/ICME.2005.1521358
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Principal Component Analysis (PCA) has been widely used to extract features for pattern recognition problems such as object recognition. Oliva and Torralba used "spatial envelope" properties derived from PCA to classify images as manmade or natural. While our implementation closely matched theirs in accuracy on a similar (Corel) dataset, we found that consumer photos, which are far less constrained in content and imaging conditions., present a greater challenge for the algorithm (as is typical in image understanding). We present an alternative approach to more robust naturalness classification, using overcomplete Independent Components Analysis (ICA) directly on the Fourier-transformed image to derive sparse representations as more effective features for classification. We demonstrated that our ICA-based features are Superior to the PCA-based features on a large set of consumer photographs.
引用
收藏
页码:53 / 56
页数:4
相关论文
共 50 条
  • [1] Natural scene classification using overcomplete ICA
    Luo, JB
    Boutell, M
    [J]. PATTERN RECOGNITION, 2005, 38 (10) : 1507 - 1519
  • [2] Reliability in ICA-based text classification
    Sevillano, X
    Alías, F
    Socoró, JC
    [J]. INDEPENDENT COMPONENT ANALYSIS AND BLIND SIGNAL SEPARATION, 2004, 3195 : 1213 - 1220
  • [3] ICA-based classification of sea ice SAR images
    Karvonen, J
    Simila, M
    [J]. REMOTE SENSING IN TRANSITION, 2004, : 211 - 217
  • [4] An ICA-based method for stress classification from voice samples
    Palacios, Daniel
    Rodellar, Victoria
    Lazaro, Carlos
    Gomez, Andres
    Gomez, Pedro
    [J]. NEURAL COMPUTING & APPLICATIONS, 2020, 32 (24): : 17887 - 17897
  • [5] An ICA-based method for stress classification from voice samples
    Daniel Palacios
    Victoria Rodellar
    Carlos Lázaro
    Andrés Gómez
    Pedro Gómez
    [J]. Neural Computing and Applications, 2020, 32 : 17887 - 17897
  • [6] ICA-based neural network approach to classification of hyperspectral image
    Feng Yan
    He Mingyi
    Song Jianghong
    Wei Jiang
    [J]. PROCEEDINGS OF 2006 INTERNATIONAL CONFERENCE ON ARTIFICIAL INTELLIGENCE: 50 YEARS' ACHIEVEMENTS, FUTURE DIRECTIONS AND SOCIAL IMPACTS, 2006, : 835 - 839
  • [7] ICA-Based EEG Feature Analysis and Classification of Learning Styles
    Alhasan, Khawla
    Aliyu, Suleiman
    Chen, Liming
    Chen, Feng
    [J]. IEEE 17TH INT CONF ON DEPENDABLE, AUTONOM AND SECURE COMP / IEEE 17TH INT CONF ON PERVAS INTELLIGENCE AND COMP / IEEE 5TH INT CONF ON CLOUD AND BIG DATA COMP / IEEE 4TH CYBER SCIENCE AND TECHNOLOGY CONGRESS (DASC/PICOM/CBDCOM/CYBERSCITECH), 2019, : 271 - 276
  • [8] A New Approach to Improving ICA-Based Models for the Classification of Microarray Data
    Liu, Kun-Hong
    Li, Bo
    Zhang, Jun
    Du, Ji-Xiang
    [J]. ADVANCES IN NEURAL NETWORKS - ISNN 2009, PT 3, PROCEEDINGS, 2009, 5553 : 983 - +
  • [9] ICA-Based Automatic Classification of PET Images from ADNI Database
    Yang Wenlu
    He Fangyu
    Chen Xinyun
    Huang Xudong
    [J]. NEURAL INFORMATION PROCESSING, PT I, 2011, 7062 : 265 - +
  • [10] ICA-based multi-colour space texture classification system
    Chindaro, S.
    Sirlantzis, K.
    Fairhurst, M. C.
    [J]. ELECTRONICS LETTERS, 2006, 42 (21) : 1208 - 1210