【摘要】：模糊是一種最常見的圖像退化之一。對(duì)于模糊的人臉,通常面臨著兩大任務(wù):模糊人臉識(shí)別和模糊人臉恢復(fù)。目前的大量工作都只針對(duì)其中某一個(gè)任務(wù),只有極少量的工作將兩個(gè)任務(wù)一起考慮。本文分析研究了模糊人臉識(shí)別和恢復(fù)之間的相輔相成關(guān)系。對(duì)于模糊人臉恢復(fù),提出了兩個(gè)新的基于模糊人臉識(shí)別結(jié)果的模型,分別解決了當(dāng)前最好的基于樣例人臉去模糊方法的兩個(gè)缺陷。模型1利用訓(xùn)練類內(nèi)差詞典的線性表示解決了人臉類內(nèi)差距問題,模型2利用梯度的L0.8先驗(yàn)替代L0先驗(yàn)解決了清晰的純?nèi)四槄^(qū)域先驗(yàn)約束問題。兩個(gè)模型級(jí)聯(lián)成兩步方案解決基于人臉識(shí)別的模糊人臉恢復(fù)問題。對(duì)于模糊人臉識(shí)別,綜合對(duì)比了模糊和去模糊方法,選擇利用模糊方法和LPQ特征做人臉識(shí)別解決基于模糊人臉恢復(fù)的模糊人臉識(shí)別問題。最后,將恢復(fù)與識(shí)別構(gòu)成一個(gè)良性循環(huán),提出了一個(gè)模糊人臉同步恢復(fù)與識(shí)別(Simultaneous Blurred Face Restoration and Recognition,SRR)算法,迭代完成模糊人臉恢復(fù)與識(shí)別。本文提出的SRR算法適用于復(fù)雜模糊核情況下的人臉去模糊問題,還適用于小樣本情況下的模糊人臉識(shí)別問題。在FERET數(shù)據(jù)庫上的實(shí)驗(yàn)表明,對(duì)于多種不同的模糊,SRR算法不僅大幅提高了模糊人臉識(shí)別的準(zhǔn)確率,還大大提升了模糊人臉恢復(fù)的質(zhì)量。
[Abstract]:Blur is one of the most common image degradation. For fuzzy faces, there are usually two tasks: fuzzy face recognition and fuzzy face restoration. Much of the current work is focused on only one of these tasks, with very little work considering the two tasks together. This paper analyzes and studies the complementary relationship between fuzzy face recognition and restoration. For fuzzy face restoration, two new models based on fuzzy face recognition results are proposed, respectively, to solve the two defects of the best face de-blurring method based on sample examples. Model 1 uses the linear representation of the training intra-class difference dictionary to solve the intra-class gap problem. Model 2 uses gradient L0.8 priori to replace L0 priori to solve a clear priori constraint problem in pure face regions. The two models are cascaded into two steps to solve the fuzzy face restoration problem based on face recognition. For fuzzy face recognition, fuzzy and de-fuzzy methods are compared synthetically, and fuzzy face recognition problem based on fuzzy face restoration is solved by using fuzzy method and LPQ feature as face recognition method. Finally, a fuzzy face synchronous recovery and recognition (Simultaneous Blurred Face Restoration and Recognition,SRR) algorithm is proposed, which is composed of a benign cycle of restoration and recognition, and the fuzzy face recovery and recognition is completed iteratively. The SRR algorithm proposed in this paper is suitable for the human face deblurring problem in the case of complex fuzzy kernel and for the fuzzy face recognition problem in the case of small samples. Experiments on FERET database show that SRR algorithm not only improves the accuracy of fuzzy face recognition, but also improves the quality of fuzzy face restoration.
【學(xué)位授予單位】：北京郵電大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2016
【分類號(hào)】：TP391.41

【相似文獻(xiàn)】

相關(guān)期刊論文 前10條

1 齊亞莉;李業(yè)麗;;模糊/去模糊攻擊的研究[J];北京印刷學(xué)院學(xué)報(bào);2005年04期

2 姚敏;去模糊機(jī)制及其一般形式[J];自動(dòng)化儀表;1997年12期

3 徐靜;石玉英;王肖玉;;全變分圖像去噪和去模糊問題的外插邊值條件(英文)[J];計(jì)算物理;2007年03期

4 馬麗紅,張宇;波動(dòng)方程去模糊的累積噪聲的CURVELET變換消除方法[J];信號(hào)處理;2005年05期

5 王國(guó)棟;潘振寬;劉存良;鄭世秀;;基于混合數(shù)據(jù)項(xiàng)的運(yùn)動(dòng)去模糊變分方法[J];儀器儀表學(xué)報(bào);2013年07期

6 唐夢(mèng);彭國(guó)華;鄭紅嬋;;基于正則化方法的圖像盲去模糊[J];計(jì)算機(jī)應(yīng)用研究;2014年02期

7 徐志浩;靳東明;李志堅(jiān);;基于電荷泵實(shí)現(xiàn)的模糊控制器去模糊電路設(shè)計(jì)[J];微電子學(xué);2005年06期

8 裴玉龍;仝衛(wèi)國(guó);李寶樹;;航拍絕緣子圖像的去模糊處理[J];電瓷避雷器;2010年05期

9 唐敏;彭國(guó)華;;基于非均勻模糊核的RL改進(jìn)算法[J];計(jì)算機(jī)工程與應(yīng)用;2013年21期

10 孫英皓;唐棣;;一種有效的交互式圖像局部?jī)?nèi)容放大方法[J];計(jì)算機(jī)工程與應(yīng)用;2012年12期

相關(guān)會(huì)議論文 前1條

1 張一鳴;劉亞t，

本文編號(hào)：2336673