基于人臉識(shí)別的社交關(guān)系檢索系統(tǒng)的設(shè)計(jì)與實(shí)現(xiàn)
本文選題:社交關(guān)系 + 關(guān)系檢索; 參考:《北京郵電大學(xué)》2013年碩士論文
【摘要】:人類(lèi)的社交關(guān)系是社會(huì)活動(dòng)的基本形式之一,互聯(lián)網(wǎng)技術(shù)的發(fā)展拉近了人與人之間距離,不管是線(xiàn)下還是線(xiàn)上,社交關(guān)系逐步成為人們維系感情聯(lián)系社會(huì)的一種方式。社交搜索作為下一代搜索引擎發(fā)展方向?qū)⒂欣谌藗兛焖俚墨@取各種形式的社交關(guān)系。傳統(tǒng)的基于關(guān)鍵字的搜索由于其固有的重名低效等缺點(diǎn)將不適用于社交關(guān)系搜索系統(tǒng),本課題創(chuàng)新性地將基于內(nèi)容的檢索技術(shù)運(yùn)用到社交關(guān)系檢索系統(tǒng),使用正面人臉圖像代替人名關(guān)鍵詞進(jìn)行檢索,是人臉識(shí)別領(lǐng)域的一個(gè)新型應(yīng)用實(shí)踐,為用戶(hù)提供了一種智能化社交關(guān)系檢索體驗(yàn)。 本課題主要研究并實(shí)現(xiàn)了基于人臉檢測(cè)與識(shí)別的社交關(guān)系檢索系統(tǒng)。該系統(tǒng)可以檢測(cè)用戶(hù)導(dǎo)入的圖像中的人臉和人物合照中的隱含的社交關(guān)系,并存儲(chǔ)這種關(guān)系,最后可以顯示待檢索的人臉的社交關(guān)系圖。本課題最終實(shí)現(xiàn)的系統(tǒng)是運(yùn)行在Android平臺(tái)的智能手機(jī)上的,用戶(hù)通過(guò)手機(jī)的拍照功能可以很方便的獲取人物照片導(dǎo)入本系統(tǒng),從而進(jìn)行相應(yīng)的識(shí)別與檢索操作。 本論文首先介紹了人臉檢測(cè)與識(shí)別的經(jīng)典算法,詳細(xì)闡述了基于Adaboost的人臉檢測(cè)和PCA的人臉識(shí)別算法,并通過(guò)實(shí)驗(yàn)證實(shí)了將其運(yùn)用于智能終端平臺(tái)上的效率和正確率的可行性。針對(duì)關(guān)系拓?fù)鋱D中兩個(gè)結(jié)點(diǎn)上人物之間的關(guān)系親密度值,本文除了考慮每?jī)蓚(gè)人物的合照數(shù)作為權(quán)值,還借鑒了詞的激活度公式,加入單個(gè)人物存在的圖像個(gè)數(shù)作為一個(gè)參數(shù)。接下來(lái)論文通過(guò)需求分析和設(shè)計(jì),實(shí)現(xiàn)了一個(gè)Android智能系統(tǒng)上的社交關(guān)系檢索系統(tǒng)。該系統(tǒng)不僅具有人臉檢測(cè)與識(shí)別、人臉庫(kù)和關(guān)系庫(kù)創(chuàng)建與更新和社交關(guān)系檢索等模塊,針對(duì)關(guān)系檢索的關(guān)系網(wǎng)狀圖還具有親密度檢索、關(guān)系查看和關(guān)系圖分享的功能。 最終系統(tǒng)測(cè)試結(jié)果表明,針對(duì)日常生活中人物照片,系統(tǒng)的人臉識(shí)別結(jié)果包括由相似度排序的n張人臉,識(shí)別的正確率隨n的增大而提升,當(dāng)n=1時(shí),識(shí)別的正確率較低,為47%左右,而當(dāng)n=6時(shí),識(shí)別的正確率可達(dá)97%左右。因此本系統(tǒng)在識(shí)別過(guò)程中都提供了6個(gè)結(jié)果,讓用戶(hù)通過(guò)手動(dòng)選擇的輔助手段,進(jìn)一步提高了識(shí)別準(zhǔn)確率。另一方面,綜合考慮了詞激活度理論的關(guān)系親密度值比只考慮兩兩人物之間的合照數(shù)更符合統(tǒng)計(jì)規(guī)律。
[Abstract]:The social relationship of human beings is one of the basic forms of social activities. The development of Internet technology has brought people closer to each other. Whether offline or online, social relations have gradually become a way for people to maintain emotional ties with society. As a next-generation search engine, social search will help people to quickly obtain various forms of social relations. The traditional keyword-based search will not be suitable for the social relationship search system because of its inherent shortcomings such as low efficiency of the duplicate name. This paper innovatively applies the content-based retrieval technology to the social relationship search system. It is a new application practice in the field of face recognition to use frontal face image instead of human name keyword for retrieval. It provides a kind of intelligent social relationship retrieval experience for users. This paper mainly studies and implements a social relationship retrieval system based on face detection and recognition. The system can detect the implied social relationship between the face and the person in the image imported by the user and store the relationship. Finally, the social relationship graph of the face to be retrieved can be displayed. The final implementation of the system is run on the Android platform of the smart phone, the user can easily get the photo of the person into the system through the camera function, so as to carry out the corresponding identification and retrieval operations. In this paper, the classical face detection and recognition algorithms are introduced, and the face detection and recognition algorithms based on Adaboost are described in detail, and the feasibility of applying them to the intelligent terminal platform is proved by experiments. Aiming at the relationship affinity value between two persons on two nodes in the relation topology graph, this paper not only considers the number of each two characters as the weight value, but also draws on the formula of the activation degree of words, and adds the number of images existing in a single character as a parameter. Then, through requirement analysis and design, a social relationship retrieval system based on Android intelligent system is implemented. The system not only has the modules of face detection and recognition, human face database and relationship database creation and update, and social relationship retrieval, but also has the functions of close density retrieval, relationship view and relationship graph sharing. Finally, the system test results show that the face recognition results of the system include n faces sorted by similarity degree, and the recognition accuracy increases with the increase of n, and when n = 1, the recognition accuracy is lower. When n = 6, the correct rate of recognition is about 97%. Therefore, the system provides six results in the process of recognition, which allows users to further improve the recognition accuracy through the manual selection of auxiliary means. On the other hand, the relational affinity value of word activation theory is more consistent with the statistical law than only considering the number of pictures between two characters.
【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】:2013
【分類(lèi)號(hào)】:TP391.41
【參考文獻(xiàn)】
相關(guān)期刊論文 前10條
1 孫寧;鄒采榮;趙力;;人臉檢測(cè)綜述[J];電路與系統(tǒng)學(xué)報(bào);2006年06期
2 周杰,盧春雨,張長(zhǎng)水,李衍達(dá);人臉自動(dòng)識(shí)別方法綜述[J];電子學(xué)報(bào);2000年04期
3 潘敏;凌惠;于朝陽(yáng);;國(guó)內(nèi)外BBS論壇發(fā)展及管理比較研究[J];思想理論教育導(dǎo)刊;2007年07期
4 祝秀萍;吳學(xué)毅;劉文峰;;人臉識(shí)別綜述與展望[J];計(jì)算機(jī)與信息技術(shù);2008年04期
5 梁路宏 ,艾海舟 ,徐光yP ,張鈸;人臉檢測(cè)研究綜述[J];計(jì)算機(jī)學(xué)報(bào);2002年05期
6 葉劍華;劉正光;;基于局部二值模式和級(jí)聯(lián)AdaBoost的多模態(tài)人臉識(shí)別[J];計(jì)算機(jī)應(yīng)用;2008年11期
7 王樂(lè)鵬;李春麗;王穎;;Foursquare模式及在中國(guó)的發(fā)展對(duì)策探討[J];科技信息;2010年23期
8 郝維;;社交搜索:下一代搜索引擎?[J];互聯(lián)網(wǎng)天地;2008年03期
9 馬勇,丁曉青;基于層次型支持向量機(jī)的人臉檢測(cè)[J];清華大學(xué)學(xué)報(bào)(自然科學(xué)版);2003年01期
10 盧春雨,張長(zhǎng)水,聞芳,閻平凡;基于區(qū)域特征的快速人臉檢測(cè)法[J];清華大學(xué)學(xué)報(bào)(自然科學(xué)版);1999年01期
,本文編號(hào):2032655
本文鏈接:http://www.sikaile.net/kejilunwen/sousuoyinqinglunwen/2032655.html