English  |  正體中文  |  简体中文  |  Items with full text/Total items : 54372/62179 (87%)
Visitors : 8545467      Online Users : 103
RC Version 6.0 © Powered By DSPACE, MIT. Enhanced by NTHU Library IR team.
Scope Tips:
  • please add "double quotation mark" for query phrases to get precise results
  • please goto advance search for comprehansive author search
  • Adv. Search
    HomeLoginUploadHelpAboutAdminister Goto mobile version
    National Tsing Hua University Institutional Repository > 理學院 > 數學系 > 博碩士論文  >  合成式視覺與推論:應用吉式抽樣於脈絡敏感的擾動建構


    Please use this identifier to cite or link to this item: http://nthur.lib.nthu.edu.tw/dspace/handle/987654321/86592


    Title: 合成式視覺與推論:應用吉式抽樣於脈絡敏感的擾動建構
    Authors: 李冠俊
    Lee, Kuan-Chun
    Description: GH02101021610
    碩士
    數學系
    Date: 2014
    Keywords: 貝氏影像分析;脈絡敏感;擾動方法;吉式抽樣;合成性
    Bayesian image analysis;context-sensitive;perturbation Method;Gibbs sampler;compositionality
    Abstract: 本文將會討論一貝氏影像分析的生成模型。模型部分,我們考慮兩點:根據「合成性(compositioanlity)」的想法,建構一個關於影像解釋並具有脈絡訊息的先驗分布以及建構給定特定解釋下,影像像素的機率分布。我們也會介紹一個馬可夫鏈蒙地卡羅的推論算法---吉式抽樣。最後,我們將應用此模型與吉式方法進行五官樣態估計的實驗。
    In this thesis, we discuss a generative model for Bayesian image analysis. In this model, we focus on building a prior of pares of an image with context information based on compositionality and a conditional model of image pixels given a particular interpretation.
    Also, a MCMC inference algorithm, Gibbs sampler, is introduced. Finally,
    Gibbs sampler and our model will be applied to a facial pose estimation experiment.
    URI: http://nthur.lib.nthu.edu.tw/dspace/handle/987654321/86592
    Source: http://thesis.nthu.edu.tw/cgi-bin/gs/hugsweb.cgi?o=dnthucdr&i=sGH02101021610.id
    Appears in Collections:[數學系] 博碩士論文

    Files in This Item:

    File SizeFormat
    GH02101021610.pdf208KbAdobe PDF124View/Open


    在NTHUR中所有的資料項目都受到原著作權保護,僅提供學術研究及教育使用,敬請尊重著作權人之權益。若須利用於商業或營利,請先取得著作權人授權。
    若發現本網站收錄之內容有侵害著作權人權益之情事,請權利人通知本網站管理者(smluo@lib.nthu.edu.tw),管理者將立即採取移除該內容等補救措施。

    SFX Query

    與系統管理員聯絡

    DSpace Software Copyright © 2002-2004  MIT &  Hewlett-Packard  /   Enhanced by   NTU Library IR team Copyright ©   - Feedback