本文關(guān)鍵詞：基于多視圖鑒別特征學習的分類算法　出處：《中國礦業(yè)大學(北京)》2016年博士論文　論文類型：學位論文

  更多相關(guān)文章： 多視圖學習 鑒別特征 半監(jiān)督流形學習 字典學習 鑒別相關(guān)性

【摘要】：模式識別、機器學習等交叉學科需要從觀察到的數(shù)據(jù)中發(fā)現(xiàn)規(guī)律。最近的十幾年來,互聯(lián)網(wǎng)、通信等信息技術(shù)得到了革命性的發(fā)展,而信息技術(shù)的發(fā)展促使當今社會所產(chǎn)生的數(shù)據(jù)量極速增長,其中有很多數(shù)據(jù)能夠以多種不同的形式進行表示。比如,在互聯(lián)網(wǎng)中,每個Web網(wǎng)頁能夠表示為其所含文檔和指向它的超鏈接;人臉識別領(lǐng)域中,可以對同一人臉圖像樣本提取出不同形態(tài)的特征形式,如Gabor特征,HOG特征,LBP特征,PCA特征分別用來描述人臉的方向尺度特征,邊緣輪廓特征,局部像素灰度變化特征以及整體主要信息特征等。傳統(tǒng)的基于單視圖的分析算法,僅利用單一視圖內(nèi)的結(jié)構(gòu)特性,沒有利用視圖間的關(guān)聯(lián)、互補信息,多視圖學習方法則嘗試在不同的視圖之間提取出相互關(guān)聯(lián)、互補的特征,從而可以改善在數(shù)據(jù)集上的學習或分類效果。因此在最近的十幾年以來,多視圖特征學習在機器學習、數(shù)據(jù)挖掘和計算機視覺等領(lǐng)域受到了廣泛的關(guān)注。本文以研究多視圖數(shù)據(jù)的分類方法為主題,以提取數(shù)據(jù)中的鑒別特征為重點,從子空間鑒別特征提取、半監(jiān)督流行學習和鑒別字典學習三個方面入手,做了一些創(chuàng)新工作,其主要內(nèi)容包括:(1)以典型相關(guān)性分析(Correlation Canonical Analysis,CCA)為基礎(chǔ),分別對鑒別典型相關(guān)性分析(Discriminant Correlation Canonical Analysis,DCCA)、多視圖鑒別分析(Multi-view Discriminant Analysis,MvDA)、增強組合特征鑒別相關(guān)性分析(Combined-Feature-Discriminability Enhanced Canonical Correlation Analysis,CECCA)等算法進行研究分析,提出二重鑒別相關(guān)性分析(Dual Discriminant Correlation Analysis,DDCA)方法。DDCA算法設(shè)計的模型具有兩點優(yōu)勢:其一,能夠在每個視圖內(nèi)借助于Fisher鑒別分析(Fisher Discriminant Analysis,FDA)尋找投影向量以保證樣本的可分性;其二,能夠在視圖之間分析樣本的鑒別相關(guān)性,即尋找投影向量使得樣本之間的類內(nèi)相關(guān)性最大,類間相關(guān)性最小。DDCA是一種有監(jiān)督的特征提取方法,相比較于CCA能夠有效利用樣本的標簽信息;此外,傳統(tǒng)相關(guān)性分析方法由于自身模型的限制,僅適用于兩個視圖之間,而忽略了視圖內(nèi)部自身的信息,而DDCA在同一視圖內(nèi)部和不同視圖之間均能夠?qū)?shù)據(jù)進行分析,基于以上幾點,DDCA有助于改善分類效果。(2)在半監(jiān)督場景下,提取每個樣本的多個視圖特征有助于進一步挖掘樣本多方面的信息,目前已有學者和研究人員們提出了一些有效的半監(jiān)督多視圖學習方法。盡管現(xiàn)有的半監(jiān)督多視圖特征學習方法已經(jīng)取得了一定的效果,但是這些方法并不能很好的同時考慮到視圖內(nèi)和視圖間的鑒別信息,而且如何有效地提取無標記樣本的近鄰結(jié)構(gòu)信息,也具有較大的提升空間。本文提出了一種新的半監(jiān)督多視圖特征學習方法,即半監(jiān)督雙重視圖特征學習(Semi-supervised Dual-view Feature Learning,SDvFL),該方法可以讓有標記、相同視圖的異類樣本之間互相遠離,同時無標記、相同視圖的近鄰外樣本之間也要互相遠離;有標記、不同視圖的同類樣本互相靠近,同時無標記、不同視圖的近鄰內(nèi)樣本之間也要互相靠近。通過這種方式,SDvFL能夠有效地挖掘多視圖數(shù)據(jù)中的信息。(3)在(2)的基礎(chǔ)上,研究半監(jiān)督情形下不同視圖之間的相關(guān)性,為了挖掘不同視圖學習得到的投影矩陣之間的關(guān)聯(lián),引入了視圖一致性的概念,提出了半監(jiān)督雙重視圖一致性特征學習方法(Semi-supervised Dual-view Consistency Feature Learning,SDvCFL)。SDvCFL方法考慮多視圖中的樣本特征描述的是同一個對象不同方面的特性,那么不同視圖特征學習的投影矩陣之間應(yīng)該有一定的聯(lián)系,因此不同視圖的結(jié)構(gòu)信息都是類似的,可以考慮讓實際求解得到的不同視圖之間結(jié)構(gòu)信息的差異最小化,本文中稱之為“視圖一致性”,即通過視圖一致性來進一步約束原始樣本結(jié)構(gòu)信息的差異性。(4)稀疏表示及字典學習技術(shù)在模式識別領(lǐng)域已經(jīng)取得廣泛關(guān)注,本文在傳統(tǒng)單視圖字典學習的基礎(chǔ)上提出一種針對于多視圖數(shù)據(jù)的鑒別字典學習方法(Multi-view Discriminant Dictionary Learning,MDDL),MDDL模型能夠?qū)W習出結(jié)構(gòu)化的鑒別字典,該字典具有三點優(yōu)勢:其一,同類樣本能夠使用同類同視圖的字典進行逼近;其二,某一類樣本由不同類所有視圖的字典表示殘差較大;其三,引入重構(gòu)系數(shù)鑒別項進一步加強字典的鑒別能力。(5)在(4)的基礎(chǔ)上,進一步分析稀疏重構(gòu)系數(shù)的性質(zhì),在有監(jiān)督的情況下考慮重新定義系數(shù)鑒別項,新的鑒別項能夠使有標記、相同視圖的異類重構(gòu)系數(shù)之間互相遠離,同時無標記、相同視圖的近鄰外重構(gòu)系數(shù)之間也要互相遠離;有標記、不同視圖的同類重構(gòu)系數(shù)互相靠近,同時無標記、不同視圖的近鄰內(nèi)重構(gòu)系數(shù)之間也要互相靠近,基于此提出了近鄰多視圖鑒別字典學習方法(Neighbour Multi-view Discriminant Dictionary Learning,NMDDL)。NMDDL方法在保證字典近鄰關(guān)系的基礎(chǔ)上進一步提升字典的鑒別性,最終能夠有助于改善分類效果。
[Abstract]:Pattern recognition, machine learning and other cross disciplinary rules need to find from the observed data. In recent years, the Internet, communications and information technology has revolutionized the development of the rapid development of information technology and the amount of data that generated in today's society the growth, there are a lot of data can be performed in many different forms said. For example, in the Internet, each Web page can be expressed as contained in the documents and hyperlinks pointing to it; in the face recognition, feature extraction can form different forms of the same sample face images, such as Gabor features, HOG features, LBP features, PCA features are used to describe the orientation of face scale feature, edge contour feature, local pixel gray change characteristic and the whole main feature of information. The traditional analysis algorithm based on single view, using only the structural characteristics within a single view, no The correlation between views, complementary information, multi view learning method to extract the correlation between different views, complementary characteristics, which can improve the data set on the learning or classification effect. So in recent years, multi view feature learning in machine learning, data mining and computer vision get extensive attention. The classification method of multi view data as the theme, to identify the feature extraction in the data as the focus, from the spatial feature extraction, semi supervised manifold learning and differential dictionary learning in three aspects, do some innovative work, the main contents include: (1) in a typical correlation analysis (Correlation Canonical, Analysis, CCA) based on canonical correlation analysis were identified (Discriminant Correlation Canonical Analysis, DCCA), Multi-v (differential analysis of multi view Iew Discriminant Analysis, MvDA), enhance the combined characteristics of differential correlation (Combined-Feature-Discriminability Enhanced Canonical Correlation Analysis CECCA) algorithm research and analysis, put forward analysis of double differential correlation (Dual Discriminant Correlation Analysis, DDCA) model.DDCA algorithm design has two advantages: first, to within each view by Fisher discriminant analysis (Fisher Discriminant Analysis, FDA) for projection vector to ensure sample separability; second, to analyze the correlation between the sample identification in the view, namely for projection vector so that the sample within class correlation maximum between class correlation, the minimum.DDCA is an extraction method of supervised feature, compared to CCA can effectively use the sample in addition, the traditional information label; correlation analysis method due to its limited model System applies only to between two views, while ignoring the views of internal information, and between DDCA within the same view and different views are able to analyze the data, based on the above points, DDCA helps to improve the classification results. (2) in the semi supervised setting, multiple view feature extraction each sample is helpful to mining the samples more information, at present, scholars and researchers have proposed some effective semi supervised multi view learning methods. Although the existing semi supervised multi view feature learning method has achieved certain effect, but at the same time, these methods are not good considering the identification information intra view and inter view, and how to effectively extract the local structure information of unlabeled samples, but also to be improved. This paper presents a new semi supervised multi view feature learning method, namely semi supervision Du dual view features (Semi-supervised Dual-view Feature Learning study, SDvFL), the method can make a mark, the same view of the heterogeneous sample away from each other, and no mark, also want to move away from each other between the same view neighbor samples; marked, not with the view of similar samples close to each other, and have no marks, close to each other between different views within the nearest neighbor sample. In this way, SDvFL can effectively mine the multi view data. (3) in (2) on the basis of the correlation between different views of the semi supervised case, in order to link between the projection matrix obtained by different mining view learning, introduces the concept of view consistency, this paper presents a semi supervised feature dual view consistency learning method (Semi-supervised Dual-view Consistency Feature Learning, SDvCFL).SDvCFL method considering multi view in Sample characteristics described are the same object characteristics in different aspects, there should be some relationship between the projection matrix so different views of learning, so the structure information of different views are similar, can consider the differences between different views make the actual obtained structure information minimization, this paper called "view consistency, difference through the view consistency to further constrain the original sample structure. (4) sparse representation and dictionary learning technology has been widely concerned in the field of pattern recognition, based on the traditional visual chart based on dictionary learning is proposed for a differential multi view data dictionary learning method (Multi-view Discriminant Dictionary Learning, MDDL), MDDL model can learn to identify the structured dictionary, the dictionary has three advantages: first, the same sample can use the same With the view of the dictionary is approaching; second, a class of samples by different views all dictionary representation of the residuals greatly; third, the reconstruction coefficient identification to further strengthen the ability to identify the dictionary. (5) in (4) on the basis of further analysis of the sparse coefficients, in the supervised case consider the re definition of coefficient identification, identification of new can be marked, the same view between heterogeneous coefficients away from each other, and no mark, also away from each other between the neighbor reconstruction coefficients of the same view; marked, similar reconstruction coefficients of different views towards each other, and no mark, to close to each other between different views within the nearest neighbor reconstruction coefficient based on the nearest neighbor multi view differential dictionary learning method is proposed (Neighbour Multi-view Discriminant Dictionary Learning, NMDDL.NMDDL) method in order to ensure close neighbor dictionary On the basis of the system, the differentiation of the dictionary can be further promoted, and the classification effect can be improved in the end.

【學位授予單位】：中國礦業(yè)大學(北京)
【學位級別】：博士
【學位授予年份】：2016
【分類號】：TP391.41

【相似文獻】

相關(guān)期刊論文 前10條

1 薛暉;陳松燦;劉潔;黃繼建;;基于跨視圖約束的多視圖分類方法[J];模式識別與人工智能;2014年02期

2 朱浩,尹澤勇,劉建武,陳高陽;跨企業(yè)工程更改的多視圖建模體系研究[J];工程設(shè)計學報;2004年04期

3 陳平;孫立鐫;梁宗學;;特征轉(zhuǎn)換在多視圖維護中的應(yīng)用[J];哈爾濱理工大學學報;2006年02期

4 曲云堯;;多視圖環(huán)境[J];山東礦業(yè)學院學報;1993年02期

5 劉明周;何曉軍;程曉梅;蔣增強;安叔華;;機電項目管理中的多視圖及其映射方法研究[J];機械工程師;2006年09期

6 唐國興;胡建;郭魂;廖文和;;基于知識引導的多視圖產(chǎn)品設(shè)計檢索技術(shù)研究[J];計算機集成制造系統(tǒng);2007年07期

7 石艷玲;單文檔多視圖的多種實現(xiàn)方式[J];計算機應(yīng)用研究;1999年10期

8 武丹;王琰;祁燕;;基于DXF文件的工程圖中多視圖的視圖分離方法[J];沈陽理工大學學報;2007年06期

9 舒振;劉俊先;易先清;羅雪山;;基于多視圖的復雜信息系統(tǒng)需求開發(fā)方法研究[J];計算機工程與設(shè)計;2010年07期

10 張巖;何曉波;管濤;;基于多視圖幾何的位置與遮擋一致性恢復方法研究[J];工程圖學學報;2011年01期

相關(guān)會議論文 前3條

1 張秀芬;裴承慧;胡志勇;;在OpenGL中實現(xiàn)多視圖表示[A];第十四屆全國圖學教育研討會暨第六屆制圖CAI課件演示交流會論文集（下冊）[C];2004年

2 趙旭;劉克;吳威;;多視圖三維重建技術(shù)和不確定問題[A];第八屆中國不確定系統(tǒng)年會論文集[C];2010年

3 張巖;楊冬青;唐世渭;;Web倉儲中的多視圖一致性維護[A];第十九屆全國數(shù)據(jù)庫學術(shù)會議論文集（研究報告篇）[C];2002年

相關(guān)博士學位論文 前9條

1 楊琬琪;多視圖特征選擇與降維方法及其應(yīng)用研究[D];南京大學;2015年

2 李晉;基于多視圖鑒別特征學習的分類算法[D];中國礦業(yè)大學(北京);2016年

3 錢強;復雜場景下的多視圖學習方法研究[D];南京航空航天大學;2013年

4 田文;多視圖圖像的快速三維場景重建[D];華中科技大學;2010年

5 徐帆;無組織多視圖圖像的自動化三維場景重建[D];華中科技大學;2007年

6 周旭東;基于不同多視圖數(shù)據(jù)場景的典型相關(guān)分析研究和應(yīng)用[D];南京航空航天大學;2013年

7 段春梅;基于多視圖的三維模型重建方法研究[D];山東大學;2009年

8 陳斌;異常檢測方法及其關(guān)鍵技術(shù)研究[D];南京航空航天大學;2013年

9 李靜;基于多視圖的三維景物重建技術(shù)研究[D];廣東工業(yè)大學;2013年

相關(guān)碩士學位論文 前10條

1 周艷杰;基于多視圖的交互式機械建模[D];鄭州大學;2015年

2 洪鑫;基于多視圖哈希的圖書推薦系統(tǒng)的研究與實現(xiàn)[D];浙江大學;2015年

3 龍躍;基于產(chǎn)品BOM的多視圖應(yīng)用及實現(xiàn)[D];電子科技大學;2014年

4 王世佳;RF數(shù)據(jù)記錄系統(tǒng)的重放軟件設(shè)計[D];電子科技大學;2014年

5 王家亮;基于片元多視圖重建在未標定序列圖像重建上的應(yīng)用[D];東北大學;2014年

6 陶萌;基于語義元的產(chǎn)品信息多視圖語義研究[D];浙江工業(yè)大學;2015年

7 賈超;基于多視圖的瓦當三維模型重建的研究與實現(xiàn)[D];西北大學;2015年

8 吳珊珊;基于多視圖稀疏嵌入分析的識別算法研究[D];南京郵電大學;2015年

9 高珊;基于距離度量學習和多視圖學習的服裝主觀風格識別方法[D];浙江大學;2016年

10 金登科;基于多視圖錨點圖哈希技術(shù)的推薦算法研究[D];浙江大學;2016年

，

本文編號：1377641