基于颜色量化的肖像漫画生成方法研究  

Research on the Method of Portrait Cartoon Generation Based on Color Quantization

作　　者：韩燕丽[1] 杨慧炯[1] 

机构地区：[1]太原工业学院,山西太原030008

出　　处：《软件工程师》2015年第11期20-21,共2页Software Engineer

摘　　要：目前创意文化已经受到国家和地方政府的关注和大力发展,而人脸漫画也受到了众多爱好者的支持。本文在研究非真实感绘制的基础上,提出了一种基于颜色量化的肖像漫画生成算法。该算法首先通过双边滤波对输入图像进行降噪处理,进而提高图像质量;其次对降噪图像进行颜色量化处理,生成图像的色块效果;然后使用Canny边缘检测算子,提取降噪图像的边缘;最后将色块效果图像与边缘图像进行融合,最终生成肖像漫画效果。实验结果表明,对于给定的输入图像,能够有效地生成具有艺术效果的漫画肖像画。At present,creative culture has been concerned and developed by the national and local governments,and face cartoon has been supported by many fans.This paper presents a new method of generating portrait cartoon based on color quantization by studying non realistic rendering.Firstly,the image is processed by the bilateral filtering to improve the image quality.Secondly,the image＇s color is equably quantizated to produce the effect of color lump.Then,the Canny edge detection operator is used to detect the image＇s edge.Finally,portrait cartoon is generated by integrating the color lump image and the edge image together.Experimental results show that for a given input image,it can effectively generate a portrait cartoon with artistic style.

关 键 词：非真实感绘制 双边滤波 颜色量化 边缘检测 图像融合 

分 类 号：TP391.9[自动化与计算机技术—计算机应用技术]