發(fā)布時間：2018-03-04 18:38

  本文選題：三維人臉重建　切入點：深度信息恢復(fù)　出處：《山東大學》2017年碩士論文　論文類型：學位論文

【摘要】：伴隨經(jīng)濟日漸繁榮和科學技術(shù)日新月異,人類在物質(zhì)需求和精神層面都有了更高的追求。在游戲動漫、影視劇作、醫(yī)療美容、視頻通訊和信息安全等眾多方面,不再滿足于二維世界帶來的視覺感官體驗,3D電影、電視,游戲動漫等應(yīng)運而生。其中,三維人臉建模由于直觀的顯示效果和廣泛的應(yīng)用場景,成為目前科學研究領(lǐng)域和實際工程項目中的一個關(guān)注熱點。相對于傳統(tǒng)的基于三視圖、多視圖以及視頻流的三維人臉重建,基于單張照片對人臉進行重建需要的用戶輸入量最少,因此是目前研究的重點。然而由于人臉面部構(gòu)造極為復(fù)雜,并且不同人臉之間的差異巨大,只通過單張人臉照片很難直接獲取人臉的深度數(shù)據(jù),其實際執(zhí)行操作更具挑戰(zhàn)性。因此,本課題的開展極具研究價值和實用價值。本文圍繞基于單張照片的重塑三維人臉模型進行了如下兩項工作:一是提出了一種基于特征融合的面部特征點深度恢復(fù)算法。首先,對人臉數(shù)據(jù)庫采取預(yù)處理工作,獲取三維模型對應(yīng)的二維面部圖像;其次通過顯式形狀回歸的方法獲取面部特征點位置信息;之后,提取面部幾何特征,依據(jù)所獲得的關(guān)鍵點對人臉進行Delaunay三角剖分,劃分人臉特征區(qū)域,通過比對待恢復(fù)人臉與數(shù)據(jù)庫人臉特征區(qū)域的幾何特征距離相似度,完成基于幾何特征的深度信息恢復(fù);接著,提取局部紋理特征,以關(guān)鍵點劃分局部紋理區(qū)域,并進行區(qū)域局部二值模式算子直方圖統(tǒng)計,通過衡量待恢復(fù)人臉與數(shù)據(jù)庫人臉的直方圖距離相似度,完成基于局部紋理特征的深度恢復(fù);最后,運用最小二乘法進行特征融合,提高特征點的恢復(fù)準確度。本文提出的基于特征融合的人臉特征點深度恢復(fù)算法,所使用的特征易于提取并且算法復(fù)雜度低,實驗結(jié)果表明恢復(fù)的面部特征點深度信息較為精確。二是提出了兩種三維人臉模型的紋理映射算法。基于約束細化Delaunay三角剖分的紋理映射方法是通過關(guān)鍵點計算二維圖像和三維模型之間的投影關(guān)系,對關(guān)鍵點構(gòu)建的特征區(qū)域進行撒點插值,進行進一步約束細化的Delaunay三角剖分,依據(jù)不同區(qū)域的映射關(guān)系,完成三維人臉的建立以及對應(yīng)紋理的貼附�；趶较蚧逯档募y理映射方法是通過已知特征點信息對徑向基網(wǎng)絡(luò)進行擬合訓練,形成特定人臉對應(yīng)的徑向基網(wǎng)絡(luò),然后對非特征點經(jīng)構(gòu)建完成的網(wǎng)絡(luò)實現(xiàn)插值映射,重建特定的人臉模型。相較于傳統(tǒng)的方法,本文提出的方法不需要進行大量的人機交互操作,在使用少量數(shù)據(jù)的基礎(chǔ)上重建出了較為真實的人臉模型,適合應(yīng)用在實際工程中。
[Abstract]:With the increasing prosperity of economy and the rapid development of science and technology, human beings have a higher pursuit in both material and spiritual aspects. In many aspects, such as game animation, film and television plays, medical beauty, video communication and information security, etc. No longer satisfied with the visual sensory experience brought by the two-dimensional world, 3D film, television, game animation and so on. Among them, 3D face modeling, due to the visual display effect and extensive application scene, Compared with the traditional 3D face reconstruction based on three-view, multi-view and video stream, it has become a hot topic in the field of scientific research and practical engineering. Face reconstruction based on single photo requires the least input from users, so it is the focus of current research. However, due to the complexity of facial structure and the huge differences between different faces, It is difficult to get the depth data of a face directly by using only a single face photograph, so it is more challenging to perform the operation in practice. This thesis is of great research value and practical value. This paper focuses on the reconstruction of 3D face model based on single photo as follows: first, a facial feature point depth restoration algorithm based on feature fusion is proposed. The face database is preprocessed to obtain 2D facial image corresponding to 3D model. Secondly, the location information of facial feature points is obtained by explicit shape regression. After that, facial geometric features are extracted. According to the key points obtained, the face is triangulated by Delaunay, and the facial feature regions are divided. The depth information restoration based on geometric features is completed by comparing the similarity of geometric features between face and database facial features. Then, the local texture features are extracted, the local texture regions are divided by the key points, and the histogram statistics of the local binary pattern operators are carried out to measure the histogram distance similarity between the face to be recovered and the face in the database. The depth restoration based on local texture features is completed. Finally, the least square method is used for feature fusion to improve the accuracy of feature point restoration. A facial feature point depth restoration algorithm based on feature fusion is proposed in this paper. The features used are easy to extract and have low algorithm complexity. The experimental results show that the depth information of facial feature points restored is more accurate. Secondly, two texture mapping algorithms for 3D face models are proposed. The texture mapping method based on constrained thinning Delaunay triangulation is calculated through key points. The projection relationship between 2D images and 3D models, The characteristic regions constructed by key points are interpolated by scatter points, and further constrained Delaunay triangulation is carried out. According to the mapping relationship of different regions, The method of texture mapping based on radial basis function interpolation (RBF) is to fit and train radial basis function network (RBF) through the information of known feature points to form radial basis function network (RBF) corresponding to a particular face. Then the network constructed by non-feature points is interpolated to reconstruct a specific face model. Compared with the traditional method, the method proposed in this paper does not require a lot of man-machine interaction operations. A real face model is reconstructed on the basis of a small amount of data, which is suitable for practical engineering.
【學位授予單位】：山東大學
【學位級別】：碩士
【學位授予年份】：2017
【分類號】：TP391.41

【參考文獻】

相關(guān)期刊論文 前9條

1 詹曙;常樂樂;梁植程;閆婷;方琪;;SICP配準的三維人臉建模[J];光電工程;2016年03期

2 鹿樂;鞠園;蔡亮;黃杰;馮燦;;基于特征分塊的快速三維人臉重建[J];火力與指揮控制;2014年S1期

3 張余敬;常丹華;劉宇;張昆;孫志華;;基于Gabor小波變換的人臉表情識別技術(shù)研究[J];計算機測量與控制;2010年04期

4 尹寶才;孫艷豐;王成章;蓋峗;;BJUT-3D三維人臉數(shù)據(jù)庫及其處理技術(shù)[J];計算機研究與發(fā)展;2009年06期

5 王成章;尹寶才;孫艷豐;胡永利;;改進的基于形變模型的三維人臉建模方法[J];自動化學報;2007年03期

6 尹寶才,胡永利,程世銓,谷春亮;基于形變模型的人臉建模及其應(yīng)用綜述[J];北京工業(yè)大學學報;2003年03期

7 梅麗,鮑虎軍,鄭文庭,彭群生;基于實拍圖像的人臉真實感重建[J];計算機學報;2000年09期

8 晏潔,高文;基于一般人臉模型修改的特定人臉合成技術(shù)[J];計算機輔助設(shè)計與圖形學學報;1999年05期

9 晏潔,高文,尹寶才;具有真實感的三維虛擬特定人臉生成方法[J];計算機學報;1999年02期

相關(guān)博士學位論文 前1條

1 龔勛;基于單張二維圖片的三維人臉建模[D];西南交通大學;2008年

相關(guān)碩士學位論文 前1條

1 王剛;基于雙目立體視覺的人臉三維模型重建研究[D];吉林大學;2014年

，

本文編號：1566841