一种基于卡通画的线条画提取方法

给出了一种从卡通画中提取线条画的新方法。方法由三部分组成:线条提取、线条绘制和风格变换。给出了基于形态学方法细化图像,把结果中离散像素点深度优先遍历生成笔划路径集合,用不同细节来控制线条绘制,达到不同程度的抽象效果。给出了生成具有夸张风格的线条画的方法,实验结果显示用文中方法能从图像中抽象出生动的线条画。     

一种基于卡通画的线条画提取方法

给出了一种从卡通画中提取线条画的新方法.方法由三部分组成:线条提取、线条绘制和风格变换.给出了基于形态学方法细化图像,把结果中离散像素点深度优先遍历生成笔划路径集合,用不同细节来控制线条绘制,达到不同程度的抽象效果.给出了生成具有夸张风格的线条画的方法,实验结果显示用文中方法能从图像中抽象出生动的线条画.     

自适应的线条画绘制

目的 基于参考图像的线条画生成是非真实感绘制最为常见的应用之一。尽可能模拟艺术家的创作风格生成疏密得当、具有层次感的线条画是这类工作的主要目标和挑战。本文提出一个自适应线画图绘制算法。方法 首先,将场景图像分割成若干个区域,分别计算每个区域亮度的方差以及每个像素到边界的最小距离,将每个区域的方差和面积的比值作为该区域的复杂度。然后,计算能反映其显著视觉特征的边缘切向流场。最后,使用基于流的各向异性高斯差分滤波生成线条画。在构造边缘切向流时,每个位置的切向量由其邻域的切向量加权而得到。文中增加了一个新的系数项,对于邻域的任意一个位置,如果它和参考位置在区域分类中属同一个类别。则该位置的权值更大。基于流的高斯差分自适应滤波过程中,高斯差分滤波的尺度参数和复杂度以及到区域边界距离有关。细节越丰富,离边界越近,尺度参数取值越小,这样得到的边缘比较细,同时可以防止将相邻小细线条连接成粗线条。然后,将高斯差分滤波结果沿着流线方向进行高斯滤波,对于细节丰富的区域,边缘比较多,尺度参数取值比较小,所连接边缘比较短,可以减少错误边缘可能。结果 对生物、树林、建筑、山河等具有代表性的图像,采用本文算法进行自动实时进行线条绘制,实验结果表明,采用本文算法所生成的线条随着区域场景的复杂程度呈现不同粗细和浓淡的变化,具有一定的层次感。因而本文算法能生成视觉特征鲜明、风格化效果突出的线条画,且能处理各种复杂场景的图像。结论 本文自适应参数的线条画生成算法,其算法参数调节以及算法效果优于固定参数的算法,本文算法在处理日常生活中各类主题场景的图像时均能取得良好效果。     

基于语义分割的简洁线条肖像画生成方法

针对目前主流的线条提取算法对于区域对比度不明显的边缘的检测能力较弱,且对于所有区域采用无差别、统一化的处理策略,所生成的线条画往往较复杂,非常不利于机器人机械臂绘图的问题,本文提出了一种基于语义分割的简洁线条肖像画生成方法(concise line portrait generation based on semantic segmentation, CLPG-SS)。首先,对人脸图像进行语义分割,将人脸划分为不同的区域,基于不同区域提取边缘轮廓与五官细节线条,进行边缘切向流优化,从而加强方向信息;在此基础上,利用线条图来生成调和图像,并利用优化后的边缘切向流、人脸语义分割结果以及调和图像,针对不同的分割区域调整线条提取方法的参数,实现对细节无关区域的线条过滤和细节重点区域的线条加强,生成简洁线条肖像画。实验结果表明:本文提出的CLPG-SS方法能够有效提取人脸主轮廓线条,并针对不同区域实现了对细节线条的针对性调节,提高了机器人机械臂的绘制效率。     

基于特征流的抽象线条画绘制

为了将照片图像转换为具有一定艺术美感的线条画图像,文中设计了3种基于特征流的各向异性滤波器:FGsD滤波器、FGaD滤波器和FLSM滤波器.这些滤波器的主要任务是提取图像的边缘信息,并将其显示为光滑连续的风格化线条.前两种滤波器是在分析数字图像中基于一阶微分和二阶微分边缘检测算法的性能后,将高斯一阶导滤波结果和高斯差分滤波结果进行适当的混合作为边缘检测的微分响应,然后对混合的微分响应值进行柔和阈值化处理提取边缘点.第3种滤波器是专门针对图像中的线型边结构提出的,通过计算局部亮度相似度质量来判断该像素是否属于边缘点.如果将FGsD滤波结果和FLSM滤波结果进行叠加,还可以得到明暗对比度增强的抽象线条画效果.与已有的线条画绘制算法相比,采用文中算法所生成的线条画视觉特征更鲜明、风格化效果更突出、艺术表现力更强烈.     

基于Sobel滤波器的图像风格转换算法

基于迭代的图像风格转换在图像重组时未考虑内容图像的结构,导致生成的图像存在线条扭曲.为约束图像重组时的信息,提出一种基于边缘检测的图像风格转换算法.通过Sobel滤波器在内容图像和生成图像相同的卷积层上提取边缘信息,同时以均方误差作为损失函数.在此基础上,将边缘损失、内容损失和风格损失的加权代数和作为神经网络的总损失.实验结果表明,该算法能够有效抑制图像的线条扭曲,减少图像噪声,生成更高质量的图像.     

基于照片的可编辑光照效果卡通人脸生成算法

提出一种基于照片的可编辑光照效果卡通人脸图像生成算法。算法首先提取输入人脸照片的边缘轮廓,生成线条画;其次对输入照片进行本征分解,分离出光照图像和材质图像;然后对光照图像进行光照编辑,如量化、非线性增强等;对材质图像进行抽象化处理,并融合线条画得到卡通图像;最后将编辑过的光照图像添加到卡通图像上生成含有光照效果的人脸卡通图像。实验结果表明:该算法生成的人脸卡通图像效果逼真,并且可对光照进行编辑。     

基于Sobel滤波器的图像风格转换算法

基于迭代的图像风格转换在图像重组时未考虑内容图像的结构,导致生成的图像存在线条扭曲.为约束图像重组时的信息,提出一种基于边缘检测的图像风格转换算法.通过Sobel滤波器在内容图像和生成图像相同的卷积层上提取边缘信息,同时以均方误差作为损失函数.在此基础上,将边缘损失、内容损失和风格损失的加权代数和作为神经网络的总损失.实验结果表明,该算法能够有效抑制图像的线条扭曲,减少图像噪声,生成更高质量的图像.     

一种全自动铅笔画生成方法研究

铅笔画是一种发展迅速并受人喜爱的绘图风格,通常由画师手工绘制,但受画手绘画功底限制很大,且用时很长,因此无法满足目前大量平面设计的需求,而利用图像处理技术,可以将自然图像方便、快速地转化为铅笔画。为此,提出一种全自动的铅笔画生成算法,融合自然图像中可变局部边缘模式提取的梯度信息和色调值生成的色调信息,获得包含重要笔画特征的线条画和色度画,并将二者有效融合,生成素描或彩色铅笔画。实验结果显示,该方法不仅能够生成视觉感逼真、信息丰富的铅笔画,同时对噪声、强纹理信息和光照变化不敏感。     

图像抽象化的实时增强型绘制

现有的图像抽象化绘制算法主要采用基于图像分割或边缘保持的平滑滤波技术,导致所生成的抽象化图像经常存在明暗对比度较低、画质昏暗模糊、画面色彩表现力不强等问题,为此提出一种增强对比度的图像抽象化绘制算法.首先利用结构张量平滑技术生成光滑连续、显著特征保持的特征流场,然后基于该流场对图像进行沿边缘切向流方向的自适应平滑和沿梯度方向的对比度增强处理,最后使用改进的基于流场的双边滤波或者Kuwahara滤波算法实现图像抽象化的实时绘制.实验结果表明,该算法可显著改善已有抽象化方法的绘制质量,抽象化图像的边界特征明显增强,画质更清晰、层次感更分明.     

Style enhanced line drawings based on multi-feature

Line drawing is a means of superior visual communication, which is made up of lines. Artists usually show their unique styles while creating a line drawing. However, traditional methods can not effectively simulate this free-hand style of artists. Though the data-driven method can generate abundant styles, it is complex and time-consuming. To this end, a new style enhanced line drawing method was proposed. First, lines in images were extracted based on edge detection and edge tracking methods. Then, the global drawing features were simulated, including length measurement, overlap measurement and offset measurement. Finally, the local drawing features that contain width measurement, sharpness measurement and depth measurement were simulated. The results showed that our method can generate stylized line drawings that are more similar to free-hand drawings of artists than the state-of-the-art methods.

     

Animated 3D Line Drawings with Temporal Coherence

Producing traditional animation is a laborious task where the key drawings are first drawn by artists and thereafter inbetween drawings are created, whether it is by hand or computer‐assisted. Auto‐inbetweening of these 2D key drawings by computer is a non‐trivial task as 3D depths are missing. An alternate approach is to generate all the drawings by extracting lines directly from animated 3D models frame by frame, concatenating and rendering them together into an animation. However, animation quality generated using this straightforward method bears two problems. Firstly, the animation contains unsatisfactory visual artifacts such as line flickering and popping. This is especially pronounced when the lines are extracted using high‐order derivatives, such as ridges and valleys, from 3D models represented in triangle meshes. Secondly, there is a lack of temporal continuity as each drawing is generated without taking its neighboring drawings into consideration. In this paper, we propose an improved approach over the straightforward method by transferring extracted 3D line drawings of each frame into individual 3D lines and processing them along the time domain. Our objective is to minimize the visual artifacts and incorporate temporal relationship of individual lines throughout the entire animation sequence. This is achieved by creating correspondent trajectory of each line from each frame and applying global optimization on each trajectory. To realize this target, we present a fully automatic novel approach, which consists of (1) a line matching algorithm, (2) an optimizing algorithm, taking into account both the variations of numbers and lengths of 3D lines in each frame, and (3) a robust tracing method for transferring collections of line segments extracted from the 3D models into individual lines. We evaluate our approach on several animated model sequences to demonstrate its effectiveness in producing line drawing animations with temporal coherence.     

Line drawing via saliency map and ETF

Line drawing is a means of superior visual communication which can effectively convey useful information to viewers. Artists usually draw what they see rather than what exists, which means the most attractive object is emphasized while the rest are inhibited. Moreover, artists draw the whole object with coherent lines instead of fractured lines, which also contribute to the outstanding visual effect. From these perspectives, generating line drawings with saliency and coherence remains a great challenge. Existing line drawing generation methods ignore these important properties and cannot generate coherent lines in some cases since they do not take into account how artists draw a picture. To this end, a novel saliency-aware line drawing method was proposed to better grasp the viewer’s attention on an image. First, a saliency enhanced line extraction method combining saliency map and edge tangent flow was proposed to ensure the saliency and coherence of lines, especially in salient but low contrast areas. Then, the salient information was highlighted while irrelevant details were eliminated by inhibiting lines in less salient areas to enhance the saliency of the line drawing. Finally, the transparency of lines was adjusted to further emphasize important information. Various results showed that our method can generate line drawings with better visual saliency and coherence than the state-of-the-art methods.     

基于趋势优先跟踪方向的直线矢量化算法

直线是工程图纸中最常使用的图元,并且工程图中常出现的圆、圆弧、曲线都可以用直线段来生成,因此,对直线的矢量化是工程图识别中一个非常重要的研究方向。针对工程图的特点,提出了一种基于趋势优先跟踪方向的直线矢量化算法,在细化后的单像素宽度图形上,根据直线的斜率趋势确定优先跟踪方向,较好地解决了在交叉点处长直线断裂的问题。同时结合跟踪过程中使用的边跟踪边检测方法,可以有效抑制短小直线段过多地产生,实现小斜率直线和大斜率直线的整体识别。     

工程扫描图象的直线整体识别算法

利用工程图纸的整体形状特性，提出了对扫描图象的直线整体识别算法，该算法对图象线条轮廓上的关键点进行了精确记录，并对它们进行了分析和处理。该算法不必单独处理线的交叉问题，但交叉点处的效果明显。它的基本思想是：首先检测原图象线宽，然后依据原图象线条的不同线宽，把原图象转化为一些由梯形块组成的条块图，并对不同的条块图分别进行整体识别     

Efficient and robust 3D line drawings using difference-of-Gaussian

Line drawings are widely used for sketches, animations, and technical illustrations because they are effective and easy to draw. The existing computer-generated lines, such as suggestive contours, apparent ridges, and demarcating curves, adopt the two-pass framework: in the first pass, certain geometric features or properties are extracted or computed in the object space; then in the second pass, the line drawings are rendered by iterating each polygonal face or edge. It is known these approaches are very sensitive to the mesh quality, and usually require appropriate preprocessing operations (e.g. smoothing, remeshing, etc.) to the input meshes. This paper presents a simple yet robust approach to generate view-dependent line drawings for 3D models. Inspired by the image edge detector, we compute the difference-of-Gaussian of illumination on the 3D model. With moderate assumption, we show all the expensive computations can be done in the pre-computing stage. Our method naturally integrates object- and image-spaces in that we compute the geometric features in the object space and then adopt a simple fragment shader to render the lines in the image space. As a result, our algorithm is more efficient than the existing object-space approaches, since the lines are generated in a single pass without iterating the mesh edges/faces. Furthermore, our method is more flexible and robust than the existing algorithms in that it does not require the preprocessing on the input 3D models. Finally, the difference-of-Gaussian operator can be extended to the anisotropic setting guided by local geometric features. The promising experimental results on a wide range of real-world models demonstrate the effectiveness and robustness of our method.     

基于连贯性的地形等高线提取方法研究

该文提出了基于地形等高线国贯性的的等高线自动识别方法,等高线连贯性和线的连贯性,点的辖 贯性是指同一条等高线上的任何一点都具有相同的标高;线的连贯性是指相邻两条等高线的高度值之差是一个常量,文中所提出的方法首先利用地识别功能得到部分显式标注的等高线的高度值,然后利用等高线的连续建立等高线之间的邻接关系,并递推计算出其余等高线的高度值,该文最后提出了几个实例用以说明该方法的有效性。