【摘要】：非真實(shí)感繪制(Non-Photorealistic Rendering,簡(jiǎn)稱(chēng)NPR)是計(jì)算機(jī)技術(shù)與繪畫(huà)藝術(shù)相結(jié)合的一個(gè)研究領(lǐng)域,其研究的主要是用計(jì)算機(jī)軟硬件手段模擬具有不同繪畫(huà)風(fēng)格的藝術(shù)流派,如鉛筆畫(huà)、水彩畫(huà)、油畫(huà)等。其研究成果可用于廣告宣傳、室內(nèi)裝修、影視制作、卡通畫(huà)制作等許多領(lǐng)域。 人臉肖像風(fēng)格化繪制是非真實(shí)感繪制研究中的一個(gè)分支,本文對(duì)肖像風(fēng)格化繪制研究的背景、意義及其中用到的一些關(guān)鍵技術(shù)展開(kāi)研究,并給出相應(yīng)的實(shí)驗(yàn)結(jié)果效果圖。 首先,論文選取丁紹光為代表的云南重彩畫(huà)作為研究對(duì)象,提出云南重彩畫(huà)風(fēng)格的人臉肖像生成算法,對(duì)人臉照片進(jìn)行重彩畫(huà)風(fēng)格的轉(zhuǎn)換。該算法作為基于照片的云南重彩畫(huà)風(fēng)格化繪制研究中的一個(gè)重要部分,其結(jié)果將會(huì)影響到整體風(fēng)格的繪制效果。云南重彩畫(huà)人臉肖像生成算法,探究并總結(jié)了云南重彩畫(huà)人臉繪制規(guī)律,采用移動(dòng)最小二乘法實(shí)現(xiàn)云南重彩畫(huà)風(fēng)格化轉(zhuǎn)換中五官特征的變形,采用基于流的高斯差分濾波器(Flow-based Difference-of-Gaussians,簡(jiǎn)稱(chēng)FDOG),進(jìn)行人臉肖像輪廓線的提取。此算法能夠有效地模擬云南重彩畫(huà)的人臉繪制特點(diǎn),并取得了較好的繪制效果。 其次,對(duì)卡通風(fēng)格的肖像繪制算法進(jìn)行了研究。針對(duì)卡通畫(huà)特點(diǎn),我們先對(duì)輸入圖像采用雙邊濾波進(jìn)行抽象化處理,使得高對(duì)比度區(qū)域的對(duì)比度更高,低對(duì)比度區(qū)域的對(duì)比度更低,簡(jiǎn)化了場(chǎng)景信息。然后,對(duì)抽象化圖像進(jìn)行量化處理以模擬卡通畫(huà)的著色風(fēng)格,并采用FDOG技術(shù)進(jìn)行邊緣輪廓線的提取以提高卡通畫(huà)的可視性；最后將量化后的圖像與提取出的邊緣圖進(jìn)行融合,即可得到色彩鮮艷、可視性較高、細(xì)節(jié)較少的卡通畫(huà)風(fēng)格的效果圖。 最后,針對(duì)圖像量化處理過(guò)程中量化區(qū)間之間出現(xiàn)的明顯過(guò)渡不連續(xù)問(wèn)題,論文中采用顏色軟量子化方法改進(jìn)量化效果。引入亮度梯度函數(shù),這樣,只有在亮度梯度大的地方,才會(huì)出現(xiàn)明顯的邊界,在梯度低的區(qū)域,邊界被延展到較大的區(qū)域中；最后可得到色彩鮮艷、量化區(qū)間過(guò)渡連續(xù)的量化效果圖。
[Abstract]:Non-Photorealistic Rendering, rendering (NPR for short) is a research field which combines computer technology with painting art. Its research mainly uses computer software and hardware to simulate art schools with different painting styles, such as pencil-drawing. Watercolor painting, oil painting, etc Its research results can be used in advertising, interior decoration, film and television production, cartoon production and many other fields. Facial portrait stylization is a branch of non-realistic rendering. In this paper, the background, significance and some key techniques of portrait stylization rendering are studied, and the corresponding experimental results are given. Firstly, the thesis chooses Yunnan heavy color painting represented by Ding Shaoguang as the research object, and puts forward a face portrait generation algorithm of Yunnan heavy color painting style. As an important part of the research on the stylized rendering of Yunnan heavy color paintings based on photos, the result of the algorithm will affect the rendering effect of the whole style. Yunnan heavy color painting face portrait generation algorithm, the study and summary of Yunnan heavy color painting face rendering law, using the moving least square method to realize the transformation of Yunnan heavy color painting style transformation of the features of the five features, A stream-based Gao Si differential filter (Flow-based Difference-of-Gaussians, for short FDOG),) is used to extract face profile. This algorithm can effectively simulate the features of Yunnan heavy color painting face rendering, and achieve a good result. Secondly, the image rendering algorithm of cartoon style is studied. According to the characteristics of cartoon, we first use bilateral filtering to abstract the input image, which makes the contrast of high contrast region higher and low contrast region lower, which simplifies the scene information. Then, the abstract image is quantitatively processed to simulate the coloring style of the cartoon, and the edge contour is extracted by using FDOG technology to improve the visibility of the cartoon. Finally, by merging the quantized image with the extracted edge image, we can get the cartoon drawing with bright color, high visibility and less detail. Finally, aiming at the obvious transition discontinuity between the quantization intervals in the image quantization process, the color soft quantization method is used to improve the quantization effect in this paper. The luminance gradient function is introduced so that only where the luminance gradient is large can the obvious boundary appear. In the region with low gradient the boundary is extended to the larger region. Finally, the quantization effect diagram with bright color and continuous transition of quantization interval can be obtained.
【學(xué)位授予單位】：云南大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2012
【分類(lèi)號(hào)】：TP391.41

【參考文獻(xiàn)】

中國(guó)期刊全文數(shù)據(jù)庫(kù) 前10條

1 錢(qián)小燕;肖亮;吳慧中;;一種流體藝術(shù)風(fēng)格的自適應(yīng)LIC繪制方法[J];計(jì)算機(jī)研究與發(fā)展;2007年09期

2 鄧維;魏迎梅;張友根;;利用圖像變形生成個(gè)性化人臉卡通[J];計(jì)算機(jī)工程與應(yīng)用;2011年24期

3 李龍生;周經(jīng)野;陳益強(qiáng);劉軍發(fā);陳振宇;;面向移動(dòng)的卡通人臉生成系統(tǒng)[J];計(jì)算機(jī)科學(xué);2007年01期

4 周仁琴;周經(jīng)野;陳益強(qiáng);劉軍發(fā);;基于特征發(fā)現(xiàn)的卡通人臉肖像生成[J];計(jì)算機(jī)輔助設(shè)計(jì)與圖形學(xué)學(xué)報(bào);2006年09期

5 閻芳;費(fèi)廣正;柳婷婷;馬文慧;石民勇;;漫畫(huà)風(fēng)格的人臉肖像生成算法[J];計(jì)算機(jī)輔助設(shè)計(jì)與圖形學(xué)學(xué)報(bào);2007年04期

6 華順剛;劉婷;;利用移動(dòng)最小二乘法實(shí)現(xiàn)圖像變形[J];計(jì)算機(jī)應(yīng)用;2009年01期

7 陳文娟;石民勇;孫慶杰;;人臉漫畫(huà)特征關(guān)系夸張及相像度優(yōu)化[J];計(jì)算機(jī)應(yīng)用;2009年S2期

8 萬(wàn)里紅;董蘭芳;沈育平;陳意云;;人物肖像畫(huà)及其卡通動(dòng)畫(huà)仿真系統(tǒng)的建立[J];計(jì)算機(jī)仿真;2007年05期

9 趙楊;徐丹;;運(yùn)用流體模擬的油畫(huà)生成方法[J];軟件學(xué)報(bào);2006年07期

10 普?qǐng)@媛;蘇迤;魏小敏;尉洪;錢(qián)文華;徐丹;;云南重彩畫(huà)白描圖繪制系統(tǒng)[J];計(jì)算機(jī)工程與設(shè)計(jì);2011年02期

中國(guó)碩士學(xué)位論文全文數(shù)據(jù)庫(kù) 前1條

1 覃日釗;線積分卷積與紋理合成在云南重彩畫(huà)風(fēng)格化繪制上的應(yīng)用[D];云南大學(xué);2011年

，

本文編號(hào)：2309133