基于Web圖像的Kinship關系驗證研究
發(fā)布時間：2018-08-18 08:07
【摘要】：計算機視覺系統(tǒng)的最終目標是要獲得自適應能力、自學習能力、在各種解決方案中權衡的能力、對新的上下文情景和應用場合進行泛化的能力,以及和其它系統(tǒng)(包括人)進行溝通的能力。人臉作為計算機視覺領域中的一種重要研究對象,因其在圖像獲取過程中的便利性和廉價性,受到了模式識別和機器學習等相關領域科研人員的廣泛關注,經(jīng)過近三十年的發(fā)展,人臉識別系統(tǒng)已經(jīng)開始從實驗室進入商業(yè)領域。然而,在這一從實驗室到具體應用場景的轉(zhuǎn)移過程中,存在多種不同性質(zhì)的人臉識別問題,其中一些還非常困難,例如對從網(wǎng)頁中采集的人臉圖像進行親屬關系驗證的問題。基于人臉圖像進行親屬關系驗證面臨新的問題和挑戰(zhàn),這些問題主要來自于組圖像的表示和驗證器的設計兩個方面。其中組圖像表示方面的問題包括由成像環(huán)境、表情、遮擋、姿態(tài)和遺傳特性等造成的人臉外觀上的豐富變化。而驗證器的設計則面臨組圖像刻畫困難、目標類信息缺失和遺傳差異大等因素。正是由于這些挑戰(zhàn)存在,使得之前的人臉驗證算法難以直接被用于處理親屬關系驗證,急需研究新的解決方案來應對這些問題。本文重點研究了基于Web圖像的魯棒的親屬關系驗證問題。本文重點討論親屬關系驗證中涉及的三個核心問題,即親屬關系主體對象的表示學習,親屬關系驗證器的設計和在實際應用場合中的推廣。針對第一個核心問題,提出了一種基于軟投票的親屬關系人臉特征塊的選擇算法;針對第二個問題,探討了嵌入一定先驗信息的組親屬關系驗證模型;針對在實際應用場合中的推廣,提出了混合親屬關系驗證問題及其模型設計方法。具體地,本文的主要貢獻和創(chuàng)新點可以總結(jié)為如下幾點:(1)提出一種考慮組關系的親屬關系驗證問題并發(fā)布一個包含超過1000組家庭的親屬關系人臉數(shù)據(jù)集。親屬關系驗證學習可以被看作是向刻畫多個視覺對象之間互信息的邁進,然而已有的親屬關系驗證研究大多考慮的是對關系,即父—子,父—女,母—子和母—女關系,但在實際應用領域,親屬關系包括更加復雜的主體關系,而在所有人類社會關系中的核心基礎單元是父母—兒子和父母—女兒家庭關系,理解該親屬關系將促進人工智能對人類社會行為的理解,也是實現(xiàn)計算機視覺系統(tǒng)從對單一對象的刻畫到多個主體對象描述的飛躍,另外,相較于更復雜的親屬關系驗證,組親屬關系驗證更容易實現(xiàn),因為其涉及的范疇是可控的,且問題本身也更容易定義。(2)提出了一種基于軟投票的親屬關系人臉特征塊選擇方法。探討了基于有監(jiān)督方式的親屬關系表示學習,實現(xiàn)親屬關系特征提取的判別性和魯棒性。主要針對現(xiàn)有親屬關系表示學習僅使用家庭主體中的某個單一對象,而親屬關系主體之間又具有一定空間結(jié)構(gòu)關系問題,考慮挖掘主體對象之間的相關性并利用這些相關性探尋親屬主體間的判別信息。具體地,在給定圖像中每個位置上的所有單個特征完成相互之間的競爭后,再選擇一些圖像組,而這些組所包含的獲勝單特征的比例更高。該方法的主要優(yōu)點是相較于主流的人臉局部特征選擇算法更加靈活,因為其是在一種更加精細的級別進行特征選擇,因此可以獲得更高的性能。(3)提出了一種嵌入人類社會學知識的相對對稱的組親屬關系驗證模型�？紤]到現(xiàn)有親屬關系驗證必須要面對的問題,即小樣本問題,而借助額外判別信息又是解決小樣本問題的一個有力手段,受人類社會學研究成果的啟發(fā),將孩子和父母中某一方較為相似的先驗信息嵌入模型,提出一種相對對稱雙線性模型,在TSKinFace和KinFaceW親屬關系人臉數(shù)據(jù)集上驗證了算法的有效性。另外,當父母雙方信息均已知時,該方法還可用于解決對親屬關系驗證問題,相對于基于父母中一方進行判定的方法具有較好的推廣性,一定程度上彌補了待驗證人臉的身份信息,在TSKinFace數(shù)據(jù)集上驗證了算法的有效性。最后,所提方法可以被看作為一個框架,在該框架中可以通過有效地嵌入先驗信息的方式整合任何一種用于處理對親屬關系驗證的方法來應對組親屬關系驗證問題。(4)提出了一種混合親屬關系驗證問題及其模型設計方法。主要針對現(xiàn)有親屬關系驗證都是基于給定主體的性別種類分別進行研究而為實際應用帶來額外的性別標注工作量的問題,探討了親屬關系驗證模型在實際應用場景中的推廣,提出了混合對親屬關系驗證。具體的,受人類社會學研究成果的啟發(fā),即一些人臉外觀,如眼睛、頭發(fā)顏色、酒窩、皮膚等表現(xiàn)出極強的遺傳性,將不同親屬關系看作為不同但相互之間有相關性的任務,并使用多任務學習框架將每個任務模型分解為兩個部分,即一部分在所有任務間共享,另一部分則被每種任務獨享。這兩部分在一個聯(lián)合框架下同時學習,使得所提算法能利用到多個任務之間的共有信息。另外,該方法的優(yōu)點是,當每個任務僅有很少訓練樣本時,能通過在任務間遷移信息的手段互補判別性信息以達到提高算法泛化性的目的。進一步,為了使算法更加魯棒,提出了一個多視圖多任務的混合對親屬關系驗證模型,其中通過為不同的特征學習各自不同的權重融合多種特征以提高混合對親屬關系驗證的性能。
[Abstract]:The ultimate goal of computer vision systems is to acquire the ability of self-adaptation, self-learning, the ability to weigh among solutions, the ability to generalize new contexts and applications, and the ability to communicate with other systems (including people). Because of its convenience and low cost in the process of image acquisition, it has attracted extensive attention of researchers in the fields of pattern recognition and machine learning. After nearly 30 years of development, face recognition system has begun to enter the commercial field from the laboratory. However, in the process of the transition from the laboratory to the specific application scenario, there exists a lot of problems. There are many different kinds of face recognition problems, some of which are still very difficult, such as the problem of kinship verification of face images collected from web pages. The problems of group image representation include the rich changes of facial appearance caused by imaging environment, expression, occlusion, posture and genetic characteristics. The design of the validator is faced with the difficulties of group image description, target class information missing and genetic differences. This paper focuses on the robust relational validation problem based on Web images. This paper focuses on three core issues involved in relational validation, namely, representation learning of relational subject objects and relational validator. Aiming at the first core problem, this paper proposes an algorithm for selecting the feature blocks of relatives based on soft voting; for the second problem, a group relatives validation model embedding certain prior information is discussed; for the promotion in practical application, a hybrid relatives algorithm is proposed. Specifically, the main contributions and innovations of this paper can be summarized as follows: (1) A relational validation problem considering group relationships is proposed and a relational face dataset containing more than 1000 families is published. Mutual information advances between visual objects, however, most of the existing kinship validation studies have considered pairwise relationships, i.e. father-son, father-daughter, mother-son and mother-daughter relationships. In practical applications, kinship includes more complex subject relationships, and the core unit of all human social relationships is parent-son. Understanding a parent-daughter family relationship will facilitate AI's understanding of human social behavior, as well as a leap in computer vision systems from depicting a single object to describing multiple subject objects. In addition, group kinship validation is easier to implement than more complex kinship validation because of its involvement. (2) A method of feature block selection based on soft voting is proposed for relational facial feature extraction. The method is based on supervised relational representation learning to realize the discriminability and robustness of relational feature extraction. A single object in a family subject, and the relatives have a certain spatial structure relationship between them. Considering mining the relativity between the subject objects and exploring the discriminant information between the relatives, all the individual features in each position in a given image compete with each other. The main advantage of this method is that it is more flexible than the mainstream face feature selection algorithm, because it is a more fine level of feature selection, so it can obtain higher performance. (3) A new embedded human face feature selection algorithm is proposed. Relatively symmetrical group relational validation model of sociological knowledge. Considering the existing problems in relational validation, that is, the small sample problem, and the use of additional discriminant information is a powerful means to solve the small sample problem, inspired by the results of anthropological sociology, children and one of the parents are more similar. A priori information embedding model is proposed, and a relative symmetric bilinear model is proposed to verify the validity of the proposed algorithm on TSKinFace and KinFaceW relational face datasets. In addition, when both parents'information is known, this method can also be used to solve the problem of relational validation. Finally, the proposed method can be regarded as a framework in which any method used to process relational validation can be integrated by effectively embedding prior information. (4) Propose a hybrid kinship validation problem and its model design method. Mainly aim at the problem that the existing kinship validation is based on the gender type of given subject and brings extra gender labeling workload for practical application, and discuss the kinship validation model. A hybrid approach is proposed to validate kinship in practical scenarios. Specifically, inspired by anthropological research, some facial features, such as eyes, hair color, dimples, and skin, exhibit strong inheritance. Different kinship relationships are viewed as different but related tasks and are used widely. Task learning framework decomposes each task model into two parts, one shared by all tasks and the other shared by each task. The two parts learn simultaneously in a joint framework, enabling the proposed algorithm to take advantage of the common information between multiple tasks. Furthermore, in order to make the algorithm more robust, a multi-view and multi-task hybrid pairwise kinship verification model is proposed, in which different weights are fused by learning for different features. Features to enhance the performance of hybrid validation for kinship.
【學位授予單位】：南京航空航天大學
【學位級別】：博士
【學位授予年份】：2016
【分類號】：TP391.41
本文編號：2188873
[Abstract]:The ultimate goal of computer vision systems is to acquire the ability of self-adaptation, self-learning, the ability to weigh among solutions, the ability to generalize new contexts and applications, and the ability to communicate with other systems (including people). Because of its convenience and low cost in the process of image acquisition, it has attracted extensive attention of researchers in the fields of pattern recognition and machine learning. After nearly 30 years of development, face recognition system has begun to enter the commercial field from the laboratory. However, in the process of the transition from the laboratory to the specific application scenario, there exists a lot of problems. There are many different kinds of face recognition problems, some of which are still very difficult, such as the problem of kinship verification of face images collected from web pages. The problems of group image representation include the rich changes of facial appearance caused by imaging environment, expression, occlusion, posture and genetic characteristics. The design of the validator is faced with the difficulties of group image description, target class information missing and genetic differences. This paper focuses on the robust relational validation problem based on Web images. This paper focuses on three core issues involved in relational validation, namely, representation learning of relational subject objects and relational validator. Aiming at the first core problem, this paper proposes an algorithm for selecting the feature blocks of relatives based on soft voting; for the second problem, a group relatives validation model embedding certain prior information is discussed; for the promotion in practical application, a hybrid relatives algorithm is proposed. Specifically, the main contributions and innovations of this paper can be summarized as follows: (1) A relational validation problem considering group relationships is proposed and a relational face dataset containing more than 1000 families is published. Mutual information advances between visual objects, however, most of the existing kinship validation studies have considered pairwise relationships, i.e. father-son, father-daughter, mother-son and mother-daughter relationships. In practical applications, kinship includes more complex subject relationships, and the core unit of all human social relationships is parent-son. Understanding a parent-daughter family relationship will facilitate AI's understanding of human social behavior, as well as a leap in computer vision systems from depicting a single object to describing multiple subject objects. In addition, group kinship validation is easier to implement than more complex kinship validation because of its involvement. (2) A method of feature block selection based on soft voting is proposed for relational facial feature extraction. The method is based on supervised relational representation learning to realize the discriminability and robustness of relational feature extraction. A single object in a family subject, and the relatives have a certain spatial structure relationship between them. Considering mining the relativity between the subject objects and exploring the discriminant information between the relatives, all the individual features in each position in a given image compete with each other. The main advantage of this method is that it is more flexible than the mainstream face feature selection algorithm, because it is a more fine level of feature selection, so it can obtain higher performance. (3) A new embedded human face feature selection algorithm is proposed. Relatively symmetrical group relational validation model of sociological knowledge. Considering the existing problems in relational validation, that is, the small sample problem, and the use of additional discriminant information is a powerful means to solve the small sample problem, inspired by the results of anthropological sociology, children and one of the parents are more similar. A priori information embedding model is proposed, and a relative symmetric bilinear model is proposed to verify the validity of the proposed algorithm on TSKinFace and KinFaceW relational face datasets. In addition, when both parents'information is known, this method can also be used to solve the problem of relational validation. Finally, the proposed method can be regarded as a framework in which any method used to process relational validation can be integrated by effectively embedding prior information. (4) Propose a hybrid kinship validation problem and its model design method. Mainly aim at the problem that the existing kinship validation is based on the gender type of given subject and brings extra gender labeling workload for practical application, and discuss the kinship validation model. A hybrid approach is proposed to validate kinship in practical scenarios. Specifically, inspired by anthropological research, some facial features, such as eyes, hair color, dimples, and skin, exhibit strong inheritance. Different kinship relationships are viewed as different but related tasks and are used widely. Task learning framework decomposes each task model into two parts, one shared by all tasks and the other shared by each task. The two parts learn simultaneously in a joint framework, enabling the proposed algorithm to take advantage of the common information between multiple tasks. Furthermore, in order to make the algorithm more robust, a multi-view and multi-task hybrid pairwise kinship verification model is proposed, in which different weights are fused by learning for different features. Features to enhance the performance of hybrid validation for kinship.
【學位授予單位】：南京航空航天大學
【學位級別】：博士
【學位授予年份】：2016
【分類號】：TP391.41
【相似文獻】
相關期刊論文 前2條
1 郭瑞強;閆紹惠;趙書良;申玉鳳;;親屬關系網(wǎng)絡的關系追溯算法[J];計算機應用;2014年07期
2 程美寶;;網(wǎng)上織網(wǎng):當代親屬關系的建構(gòu)[J];學術研究;2008年09期
相關重要報紙文章 前7條
1 華中師范大學政治學研究院 吳理財;鄉(xiāng)村社會個體化的一種反應[N];社會科學報;2014年
2 早報見習記者 陳竹沁;“王曉玲與兩股東非親屬關系”[N];東方早報;2014年
3 特約記者 云也退;人的身份應該是復雜多變的[N];第一財經(jīng)日報;2014年
4 本報記者 杜昌營;親屬關系證明等事項可網(wǎng)上申辦[N];人民公安報;2014年
5 東方;香港接納內(nèi)地移民擬實行新計分制度[N];法制日報;2002年
6 ;未成年人監(jiān)護應有說法[N];中國婦女報;2000年
7 李 華 馮劍曉;“醫(yī)學上認為不能結(jié)婚的疾病”應該明確[N];人民法院報;2004年
相關博士學位論文 前2條
1 秦曉倩;基于Web圖像的Kinship關系驗證研究[D];南京航空航天大學;2016年
2 王利芬;延續(xù)、疏遠和理性化[D];華中科技大學;2015年
相關碩士學位論文 前10條
1 李應芝;彝族擬親屬關系研究[D];西南大學;2012年
2 黃巖;農(nóng)村擬親屬關系研究[D];濟南大學;2012年
3 譚建榮;親屬關系影響定罪量刑研究[D];西南政法大學;2013年
4 滿昌朋;個體化、親屬關系與老年人精神贍養(yǎng)研究[D];西南交通大學;2015年
5 童欣弘;已婚子女與父母的互動傾向研究[D];杭州師范大學;2016年
6 張浩;基于親屬關系網(wǎng)絡的圖模式匹配方法研究[D];河北師范大學;2016年
7 張霞;基于親屬關系網(wǎng)絡的子圖查詢方法研究[D];河北師范大學;2017年
8 李虎;壯族擬親屬關系的研究[D];廈門大學;2008年
9 嚴子文;親屬雇傭中的糾紛與沖[D];吉林大學;2013年
10 閆紹惠;親屬關系網(wǎng)絡的結(jié)構(gòu)分析及關系追溯算法研究[D];河北師范大學;2014年
，本文編號：2188873
本文鏈接：http://www.sikaile.net/shoufeilunwen/xxkjbs/2188873.html
最近更新
教材專著
