Unsupervised learning of a finite mixture model based on the Dirichlet distribution and its application

被引：142
|
作者：
Bouguila, N [1 ]
Ziou, D
Vaillancourt, J
机构：
[1] Univ Sherbrooke, Dept Informat, Sherbrooke, PQ J1K 2R1, Canada
[2] Univ Quebec, Hull, PQ J8X 3X7, Canada
来源：
IEEE TRANSACTIONS ON IMAGE PROCESSING | 2004年 / 13卷 / 11期
关键词：
Dirichlet distribution; Fisher's scoring method; image summarizing; maximum likelihood; mixture modeling; natural gradient; Riemannian space;
D O I：
10.1109/TIP.2004.834664
中图分类号：
TP18 [人工智能理论];
学科分类号：
081104 ; 0812 ; 0835 ; 1405 ;
摘要：
This paper presents an unsupervised algorithm for learning a finite mixture model from multivariate data. This mixture model is based on the Dirichlet distribution, which offers high flexibility for modeling data. The proposed approach for estimating the parameters of a Dirichlet mixture is based on the maximum likelihood (NIL) and Fisher scoring methods. Experimental results are presented for the following applications: estimation of artificial histograms, summarization of image databases for efficient retrieval, and human skin color modeling and its application to skin detection in multimedia databases.
引用
收藏
页码：1533 / 1543
页数：11
相关论文
共 50 条
  • [1] A powreful finite mixture model based on the generalized Dirichlet distribution: Unsupervised learning and applications
    Bouguila, N
    Ziou, D
    [J]. PROCEEDINGS OF THE 17TH INTERNATIONAL CONFERENCE ON PATTERN RECOGNITION, VOL 1, 2004, : 280 - 283
  • [2] Unsupervised nested Dirichlet finite mixture model for clustering
    Fares Alkhawaja
    Nizar Bouguila
    [J]. Applied Intelligence, 2023, 53 : 25232 - 25258
  • [3] Unsupervised nested Dirichlet finite mixture model for clustering
    Alkhawaja, Fares
    Bouguila, Nizar
    [J]. APPLIED INTELLIGENCE, 2023, 53 (21) : 25232 - 25258
  • [4] Unsupervised Learning of Finite Mixtures using Scaled Dirichlet Distribution and its Application to Software Modules categorization
    Oboh, Eromonsele Samuel
    Bouguila, Nizar
    [J]. 2017 IEEE INTERNATIONAL CONFERENCE ON INDUSTRIAL TECHNOLOGY (ICIT), 2017, : 1085 - 1090
  • [5] Unsupervised Text Learning Based on Context Mixture Model with Dirichlet Prior
    Chen, Dongling
    Wang, Daling
    Yu, Ge
    [J]. ADVANCED WEB AND NETWORK TECHNOLOGIES, AND APPLICATIONS, 2008, 4977 : 172 - 181
  • [6] Unsupervised selection of a finite Dirichlet mixture model: An MML-based approach
    Bouguila, Nizar
    Ziou, Djemel
    [J]. IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING, 2006, 18 (08) : 993 - 1009
  • [7] Using unsupervised learning of a finite Dirichlet mixture model to improve pattern recognition applications
    Bouguila, N
    Ziou, D
    [J]. PATTERN RECOGNITION LETTERS, 2005, 26 (12) : 1916 - 1925
  • [8] Online Variational Learning for a Dirichlet Process Mixture of Dirichlet Distributions and Its Application
    Fan, Wentao
    Bouguila, Nizar
    [J]. 2012 11TH INTERNATIONAL CONFERENCE ON MACHINE LEARNING AND APPLICATIONS (ICMLA 2012), VOL 1, 2012, : 362 - 367
  • [9] Entropy-Based Variational Learning of Finite Generalized Inverted Dirichlet Mixture Model
    Ahmadzadeh, Mohammad Sadegh
    Manouchehri, Narges
    Ennajari, Hafsa
    Bouguila, Nizar
    Fan, Wentao
    [J]. INTELLIGENT INFORMATION AND DATABASE SYSTEMS, ACIIDS 2021, 2021, 12672 : 130 - 143
  • [10] Variational Bayesian Inference for Finite Inverted Dirichlet Mixture Model and Its Application to Object Detection
    Lai Yuping
    Ping Yuan
    He Wenda
    Wang Baocheng
    Wang Jingzhong
    Zhang Xiufeng
    [J]. CHINESE JOURNAL OF ELECTRONICS, 2018, 27 (03) : 603 - 610
12345