基于稀疏貪婪搜索的人臉畫像合成
發(fā)布時間：2018-08-19 20:03
【摘要】：人臉畫像合成是通過機器學習對照片和畫像之間的復雜映射關系建模進而利用該模型從照片合成畫像的過程。畫像合成對刑偵破案和數(shù)字娛樂具有重要的應用價值。例如,當案件發(fā)生后,由于環(huán)境或硬件條件的制約,警方無法獲取犯罪嫌疑人的影像資料。此時,畫家根據(jù)受害者或者目擊證人的描述繪制的素描畫像就成為犯罪嫌疑人照片的最優(yōu)替代。將警方數(shù)據(jù)庫中的身份證照片轉換成對應的素描畫像,再利用犯罪嫌疑人的素描畫進行檢索,從而縮小或鎖定犯罪嫌疑人的身份。另外,隨著社交媒體的發(fā)展,很多年輕人都希望自己的用戶頭像富有個性,因此各種風格的素描畫便成為他們熱衷的選擇之一。此外,人臉畫像合成還可作為其他計算機視覺任務的重要組成部分,比如人臉畫像老化等�，F(xiàn)有基于機器學習的人臉畫像合成方法可分成兩大類：模型驅動和數(shù)據(jù)驅動的方法。本論文致力于研究數(shù)據(jù)驅動的方法,針對現(xiàn)有數(shù)據(jù)驅動方法存在的一些不足,如對測試照片要求嚴格、需要依賴大量的訓練樣本等,進行方法的創(chuàng)新。本文的主要創(chuàng)新點可以概括為：1. 提出一種基于多照片-畫像對的人臉畫像合成方法。現(xiàn)有的數(shù)據(jù)驅動方法只考慮局部搜索策略,導致無法順利合成測試照片獨有的非人臉因素。此外,局部搜索要求測試照片和訓練集中的圖像對齊,限制了測試照片的要求。針對上述問題,提出一種基于多照片-畫像對的人臉畫像合成方法：第一步利用稀疏編碼算法將圖像塊像素特征變成稀疏表示特征,提高算法對干擾的魯棒性；第二步利用稀疏表示中每個稀疏系數(shù)的值以及稀疏系數(shù)編碼的次序這兩個信息對訓練圖像塊建立搜索樹,提高算法的搜索精度和速度；第三步利用測試照片的先驗信息,結合圖模型,通過貝葉斯推斷進行人臉畫像的合成。第一步和第二步簡稱稀疏貪婪搜索算法。實驗表明所提方法相較于已有的數(shù)據(jù)驅動方法能更好更快的合成非人臉因素,而且對于任意的測試照片都適用。2. 提出一種基于單照片-畫像對的人臉畫像合成方法�，F(xiàn)有數(shù)據(jù)驅動方法需要依賴大量的照片-畫像對作為訓練集。然而獲取大量照片-畫像對的代價很大,限制了已有方法的實際應用。此外,在某些極端情況下只有一個照片-畫像對可用。針對上述問題,提出一種基于單照片-畫像對的人臉畫像合成方法：第一步對訓練集中的單照片-畫像對建立高斯金字塔,不僅增加了訓練樣本而且考慮了人臉結構的尺度信息；第二步利用稀疏貪婪搜索算法得到測試照片的初始畫像,充分保持了基于多照片-畫像對的人臉畫像合成方法的優(yōu)點；第三步利用由測試照片和初始畫像以及已有的單照片-畫像對所構成的新訓練集,通過結合級聯(lián)回歸策略和圖模型進行最終的人臉畫像合成。實驗表明所提方法能取得與最新數(shù)據(jù)驅動方法可比擬的結果,而且同樣能合成非人臉因素且不限制測試照片的要求。3. 提出一種基于單目標畫像的人臉畫像合成方法�，F(xiàn)有數(shù)據(jù)驅動方法需要依賴照片-畫像對,不管是大量還是一對,都限制了合成任意風格畫像的能力。針對上述問題,提出一種基于單目標畫像的人臉畫像合成方法。第一步利用稀疏貪婪搜索算法合成測試照片的初始畫像；第二步利用多尺度特征尋找候選畫像塊；第三步利用基于多特征的最優(yōu)化模型精選候選畫像塊；第四步利用級聯(lián)回歸策略對初始畫像進行質量提升。實驗表明所提方法能取得與最新數(shù)據(jù)驅動方法可比擬的結果。而且在以實驗所列的風格目標畫像作為訓練集的情況下,所提方法對于任意給定的測試照片都能合成質量良好的對應風格畫像,這使算法更加有利于數(shù)字娛樂。4. 提出一種基于統(tǒng)一框架的人臉畫像合成方法�，F(xiàn)有數(shù)據(jù)驅動方法在候選圖像塊搜索時只利用了局部搜索策略而上述所提方法則只利用了全局搜索策略。此外,已有方法在最終畫像合成時大多利用了多個候選塊的線性組合,導致合成結果有些平滑。而已有的高頻重建策略都是模型驅動的方法,缺失畫像風格信息。針對上述問題,提出一種基于統(tǒng)一框架的人臉畫像合成方法：第一步將訓練集劃分為初始訓練集和高頻訓練集；第二步給定測試照片利用局部搜索策略和全局搜索策略在初始訓練集中進行候選圖像塊的搜索,充分利用局部位置信息和人臉全局相似性的信息,然后利用圖模型進行人臉初始畫像合成；第三步對給定的測試照片利用與初始畫像合成相同的策略進行人臉高頻畫像的合成。將初始畫像和高頻畫像相加得到最終的人臉畫像。實驗表明所提算法能同時合成非人臉部件和人臉部件,并且高頻細節(jié)更加豐富。綜上,本文本著訓練樣本從多到少、研究思路從偏到全的方式,提出以稀疏貪婪搜索作為基礎的四種人臉畫像合成方法,用于提升人臉畫像合成的實用性。理論分析和實驗結果表明了所提出方法相對于已有方法的優(yōu)越性。
[Abstract]:Face portrait synthesis is a process of synthesizing images from photographs by modeling the complex mapping relationship between photographs and images through machine learning. Portrait synthesis has important application value in criminal investigation and digital entertainment. For example, when a case occurs, the police can not obtain a crime because of environmental or hardware constraints. At this point, the painter's sketch based on the description of the victim or witness becomes the best alternative to the photograph of the criminal suspect. In addition, with the development of social media, many young people want their user portraits to be personalized, so sketching of various styles has become one of their favorite choices. In addition, face portrait synthesis can also be an important part of other computer vision tasks, such as face portrait aging. Machine-learning face portrait synthesis methods can be divided into two categories: model-driven and data-driven methods. This paper focuses on data-driven methods, aiming at the shortcomings of existing data-driven methods, such as strict requirements on test photos, relying on a large number of training samples, and so on, to innovate the methods. The main innovations can be summarized as follows: 1. A multi-photo-image pair based face image synthesis method is proposed. The existing data-driven methods only consider the local search strategy, which makes it impossible to successfully synthesize the non-face factors unique to the test photos. In addition, the local search requires the alignment of the test photos and the training set, which limits the test. In order to solve the above problems, this paper proposes a face image synthesis method based on multi-photo-image pairs. The first step is to use sparse coding algorithm to transform the pixel features of image blocks into sparse representation features to improve the robustness of the algorithm to interference. The second step is to use the value of each sparse coefficient in sparse representation and sparse coefficient coding. The order of the two information sets up a search tree for the training image blocks to improve the search accuracy and speed of the algorithm. The third step uses the prior information of the test photos and combines with the graph model to synthesize the face image by Bayesian inference. Data-driven methods can synthesize non-face factors better and faster, and can be applied to any test photograph. 2. A face image synthesis method based on single photo-image pairs is proposed. In addition, in some extreme cases there is only one photo-portrait pair available. To solve the above problem, a face portrait synthesis method based on single photo-portrait pair is proposed. The first step is to build a Gaussian pyramid for the single photo-portrait pair in the training set, which not only increases the training sample but also considers the human being. In the second step, the sparse greedy search algorithm is used to obtain the initial portrait of the test photos, which fully maintains the advantages of the multi-photo-image pair based face portrait synthesis method. In the third step, the new training set composed of the test photos, the initial portrait and the existing single-photo-image pairs is utilized, and the combination level is adopted. Experiments show that the proposed method can achieve comparable results with the latest data-driven methods, and can also synthesize non-face factors without restricting the requirements of the test photos. 3. A face image synthesis method based on single-object portrait is proposed. In order to solve the above problem, a method of face portrait synthesis based on single-object portrait is proposed. First, the initial portrait of the test picture is synthesized by sparse greedy search algorithm; second, the multi-scale feature is used to find the condition. In the third step, the candidate blocks are selected by the Multi-feature-based optimization model, and in the fourth step, the quality of the initial portrait is improved by cascade regression strategy. In the case of any given test image, the proposed method can synthesize good quality corresponding style portraits, which makes the algorithm more conducive to digital entertainment. 4. A unified framework based face portrait synthesis method is proposed. In addition, most of the existing methods utilize the linear combination of multiple candidate blocks in the final portrait synthesis, resulting in smoother results. However, the existing high-frequency reconstruction strategies are model-driven and lack of portrait style information. The first step is to divide the training set into the initial training set and the high frequency training set; the second step is to search the candidate image blocks in the initial training set by using local search strategy and global search strategy for a given test photo, making full use of the information of local location information and global face similarity, and then using the graph model to advance. In the third step, we use the same strategy as the original portrait synthesis to synthesize the high-frequency portrait of the human face for a given test picture. The final portrait is obtained by adding the initial portrait and the high-frequency portrait. In summary, this paper proposes four face image synthesis methods based on sparse greedy search to improve the practicability of face image synthesis. Theoretical analysis and experimental results show that the proposed method is superior to the existing methods.
【學位授予單位】：西安電子科技大學
【學位級別】：博士
【學位授予年份】：2016
【分類號】：TP391.41
本文編號：2192694
[Abstract]:Face portrait synthesis is a process of synthesizing images from photographs by modeling the complex mapping relationship between photographs and images through machine learning. Portrait synthesis has important application value in criminal investigation and digital entertainment. For example, when a case occurs, the police can not obtain a crime because of environmental or hardware constraints. At this point, the painter's sketch based on the description of the victim or witness becomes the best alternative to the photograph of the criminal suspect. In addition, with the development of social media, many young people want their user portraits to be personalized, so sketching of various styles has become one of their favorite choices. In addition, face portrait synthesis can also be an important part of other computer vision tasks, such as face portrait aging. Machine-learning face portrait synthesis methods can be divided into two categories: model-driven and data-driven methods. This paper focuses on data-driven methods, aiming at the shortcomings of existing data-driven methods, such as strict requirements on test photos, relying on a large number of training samples, and so on, to innovate the methods. The main innovations can be summarized as follows: 1. A multi-photo-image pair based face image synthesis method is proposed. The existing data-driven methods only consider the local search strategy, which makes it impossible to successfully synthesize the non-face factors unique to the test photos. In addition, the local search requires the alignment of the test photos and the training set, which limits the test. In order to solve the above problems, this paper proposes a face image synthesis method based on multi-photo-image pairs. The first step is to use sparse coding algorithm to transform the pixel features of image blocks into sparse representation features to improve the robustness of the algorithm to interference. The second step is to use the value of each sparse coefficient in sparse representation and sparse coefficient coding. The order of the two information sets up a search tree for the training image blocks to improve the search accuracy and speed of the algorithm. The third step uses the prior information of the test photos and combines with the graph model to synthesize the face image by Bayesian inference. Data-driven methods can synthesize non-face factors better and faster, and can be applied to any test photograph. 2. A face image synthesis method based on single photo-image pairs is proposed. In addition, in some extreme cases there is only one photo-portrait pair available. To solve the above problem, a face portrait synthesis method based on single photo-portrait pair is proposed. The first step is to build a Gaussian pyramid for the single photo-portrait pair in the training set, which not only increases the training sample but also considers the human being. In the second step, the sparse greedy search algorithm is used to obtain the initial portrait of the test photos, which fully maintains the advantages of the multi-photo-image pair based face portrait synthesis method. In the third step, the new training set composed of the test photos, the initial portrait and the existing single-photo-image pairs is utilized, and the combination level is adopted. Experiments show that the proposed method can achieve comparable results with the latest data-driven methods, and can also synthesize non-face factors without restricting the requirements of the test photos. 3. A face image synthesis method based on single-object portrait is proposed. In order to solve the above problem, a method of face portrait synthesis based on single-object portrait is proposed. First, the initial portrait of the test picture is synthesized by sparse greedy search algorithm; second, the multi-scale feature is used to find the condition. In the third step, the candidate blocks are selected by the Multi-feature-based optimization model, and in the fourth step, the quality of the initial portrait is improved by cascade regression strategy. In the case of any given test image, the proposed method can synthesize good quality corresponding style portraits, which makes the algorithm more conducive to digital entertainment. 4. A unified framework based face portrait synthesis method is proposed. In addition, most of the existing methods utilize the linear combination of multiple candidate blocks in the final portrait synthesis, resulting in smoother results. However, the existing high-frequency reconstruction strategies are model-driven and lack of portrait style information. The first step is to divide the training set into the initial training set and the high frequency training set; the second step is to search the candidate image blocks in the initial training set by using local search strategy and global search strategy for a given test photo, making full use of the information of local location information and global face similarity, and then using the graph model to advance. In the third step, we use the same strategy as the original portrait synthesis to synthesize the high-frequency portrait of the human face for a given test picture. The final portrait is obtained by adding the initial portrait and the high-frequency portrait. In summary, this paper proposes four face image synthesis methods based on sparse greedy search to improve the practicability of face image synthesis. Theoretical analysis and experimental results show that the proposed method is superior to the existing methods.
【學位授予單位】：西安電子科技大學
【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10條
1 朱林;王士同;;人臉合成圖像檢測方法研究[J];計算機工程與應用;2007年13期
2 張培;吳亞鋒;;基于局部指向性的反向合成圖像對齊算法[J];西北工業(yè)大學學報;2007年04期
3 陳波;朱秋煜;;基于光照方向的人像合成圖像的檢測[J];計算機仿真;2009年03期
4 王偉;曾鳳;章國安;段新濤;;合成圖像被動取證技術研究進展[J];南通大學學報(自然科學版);2013年03期
5 錢霖,葉燕,臧崢寧;一種合成圖像的數(shù)字處理方法[J];蘇州大學學報(自然科學);2002年02期
6 ;視角[J];科技傳播;2014年06期
7 劉元生;;通道合成圖像原理[J];影像技術;2009年06期
8 侯志青;劉東州;康艷霜;劉立芳;唐志英;;Matlab6.0在拍合成中的輔助教學應用[J];保定師范專科學校學報;2006年04期
9 周維;汪增福;;用于高真實感口型合成的唇區(qū)肌肉模型[J];中國圖象圖形學報;2008年11期
10 閻積惠;康慧;陳懷亮;田曉東;;甘肅北山TM合成圖像的波段組合模式與解譯[J];遙感信息;1989年01期
相關會議論文 前2條
1 曹奇志;;提高多光譜合成圖像質量的一種新方法[A];中國光學學會2011年學術大會摘要集[C];2011年
2 毛慧蕓;龐家昊;金連文;杜明輝;;一種美麗人臉的計算機合成方法[A];第十五屆全國圖象圖形學學術會議論文集[C];2010年
相關博士學位論文 前1條
1 張聲傳;基于稀疏貪婪搜索的人臉畫像合成[D];西安電子科技大學;2016年
相關碩士學位論文 前5條
1 張培;反向合成圖像對齊算法的研究及改進[D];西北工業(yè)大學;2007年
2 左龍;基于主動表觀模型的多姿態(tài)人臉合成研究與應用[D];西安電子科技大學;2015年
3 郭超薇;數(shù)字接景真實感合成技術應用研究[D];北京工業(yè)大學;2013年
4 張嗣;造相[D];中央美術學院;2014年
5 田燦燦;半自動感興趣區(qū)檢測算法在腎小球濾過率定量分析中的研究[D];上海交通大學;2013年
，本文編號：2192694
本文鏈接：http://www.wukwdryxk.cn/shoufeilunwen/xxkjbs/2192694.html
最近更新
教材專著
