A new unsupervised image segmentation algorithm based on deterministic annealing EM

被引：0
|
作者：
Zhong, JQ [1 ]
Wang, RS [1 ]
机构：
[1] Natl Univ Def Technol, ATR, Natl Lab, Changsha 410073, Peoples R China
来源：
2003 IEEE INTERNATIONAL CONFERENCE ON ROBOTICS, INTELLIGENT SYSTEMS AND SIGNAL PROCESSING, VOLS 1 AND 2, PROCEEDINGS | 2003年
关键词：
D O I：
暂无
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 unsupervised image segmentation algorithm based on deterministic annealing EM (DAEM) is proposed in this paper The method is based on maximum likelihood (ML) estimation. Image is considered as a mixture of multi-variant normal densities and the number of densities is assumed to know. In order to obtain the parameters of densities, deterministic annealing EM algorithm is introduced. In DAEM algorithm, the EM process is reformulated as the problem of minimizing the thermodynamic free energy by, using a statistical mechanics analogy. Thus, The DAEM algorithm can overcome the local maximize problem of general EM algorithm. The proposed method is successfully applied to image segmentation experiments.
引用
收藏
页码：600 / 604
页数：5
相关论文
共 50 条
  • [41] Unsupervised image segmentation based on a new fuzzy HMC model
    Carincotte, C
    Derrode, S
    Sicot, G
    Boucher, JM
    2004 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING, VOL V, PROCEEDINGS: DESIGN AND IMPLEMENTATION OF SIGNAL PROCESSING SYSTEMS INDUSTRY TECHNOLOGY TRACKS MACHINE LEARNING FOR SIGNAL PROCESSING MULTIMEDIA SIGNAL PROCESSING SIGNAL PROCESSING FOR EDUCATION, 2004, : 693 - 696
  • [42] Application of deterministic annealing EM algorithm to MAP/PH parameter estimation
    Okamura, Hiroyuki
    Kishikawa, Hidenari
    Dohi, Tadashi
    TELECOMMUNICATION SYSTEMS, 2013, 54 (01) : 79 - 90
  • [43] Application of deterministic annealing EM algorithm to MAP/PH parameter estimation
    Hiroyuki Okamura
    Hidenari Kishikawa
    Tadashi Dohi
    Telecommunication Systems, 2013, 54 : 79 - 90
  • [44] Deterministic annealing EM algorithm in acoustic Modeling for speaker and speech recognition
    Itaya, Y
    Zen, HG
    Nankaku, Y
    Miyajima, C
    Tokuda, K
    Kitamura, T
    IEICE TRANSACTIONS ON INFORMATION AND SYSTEMS, 2005, E88D (03): : 425 - 431
  • [45] Unsupervised Ground Truth Generation for Automated Brain EM Image Segmentation
    Roy, Srijita
    Panda, Aditi
    Naskar, Ruchira
    2019 6TH INTERNATIONAL CONFERENCE ON SIGNAL PROCESSING AND INTEGRATED NETWORKS (SPIN), 2019, : 66 - 71
  • [46] A new Deterministic Annealing for image contextual classification
    Chitroub, S
    Houacine, A
    Allaoua, A
    Aroua, MD
    Sansal, B
    2000 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING, PROCEEDINGS, VOLS I-VI, 2000, : 2243 - 2246
  • [47] An image segmentation algorithm based on the simulated annealing and improved snake model
    Tang, Liqun
    Wang, Kejun
    Feng, Guangsheng
    Li, Yonghua
    2007 IEEE INTERNATIONAL CONFERENCE ON MECHATRONICS AND AUTOMATION, VOLS I-V, CONFERENCE PROCEEDINGS, 2007, : 3876 - 3881
  • [48] Simulated annealing based maximum likelihood clustering algorithm for image segmentation
    State Key Lab. of CAD and CG, Zhejiang Univ., Hangzhou 310027, China
    Ruan Jian Xue Bao/Journal of Software, 2001, 12 (02): : 212 - 218
  • [49] Image segmentation based on fuzzy maximum entropy and simulated annealing algorithm
    Liu, HK
    Li, J
    Wu, J
    DCABES 2004, Proceedings, Vols, 1 and 2, 2004, : 846 - 849
  • [50] A new deterministic annealing algorithm for maximum clique
    Jagota, A
    Pelillo, M
    Rangarajan, A
    IJCNN 2000: PROCEEDINGS OF THE IEEE-INNS-ENNS INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS, VOL VI, 2000, : 505 - 508
12345