基于卷积神经网络的彩色铅笔画算法

doi:10.13190/j.jbupt.2019-030

北京邮电大学学报 ›› 2020, Vol. 43 ›› Issue (1): 129-134.doi: 10.13190/j.jbupt.2019-030

基于卷积神经网络的彩色铅笔画算法

王小玉, 胡鑫豪, 韩昌林

哈尔滨理工大学计算机科学与技术学院, 哈尔滨 150080

收稿日期:2019-02-28 出版日期:2020-02-28 发布日期:2020-03-27
作者简介:王小玉(1971-),女,教授,E-mail:wangxiaoyu@hrbust.edu.cn.
基金资助:
国家自然科学基金项目（60572153，60972127）

Color Pencil Drawing Based on Convolutional Neural Network

WANG Xiao-yu, HU Xin-hao, HAN Chang-lin

School of Computer Science and Technology, Harbin University of Science and Technology, Harbin 150080, China

Received:2019-02-28 Online:2020-02-28 Published:2020-03-27
Supported by:

摘要/Abstract

摘要： 为了解决传统彩色铅笔画算法生成结果单一的问题，提出了一种基于卷积神经网络（CNN）生成彩色铅笔画的算法.采用分数阶微分获取原始图像轮廓信息，用卷积神经网络获取艺术家手绘铅笔画风格，利用直方图匹配获取与手绘铅笔画相似的色调，并使用L-BFGS优化算法来合成具有铅笔画效果的图像.该算法能够生成具有不同风格的彩色铅笔画图像.实验结果表明，该算法生成的图像保留了更多原始图像的细节信息，风格更加灵活多样.

关键词: 分数阶微分, 卷积神经网络, 直方图匹配, L-BFGS优化算法

Abstract: In order to optimize the single generation result of traditional color pencil drawing algorithms, a convolution neural network (CNN) based color pencil drawing generation method is presented. Fractional differentiation is employed to obtain original image contour information, CNN can obtain pencil drawing style, and histogram matching can obtain similar tones. Meanwhile, L-BFGS algorithm is used to synthesize pencil drawing image. This can generate color pencil drawing images of different styles. Experiments show that the images generated can retain more original image detail information, and feature with more flexible and diverse styles.

Key words: fractional differentiation, convolutional neural network, histogram matching, L-BFGS algorithm

中图分类号:

TP391

王小玉, 胡鑫豪, 韩昌林. 基于卷积神经网络的彩色铅笔画算法[J]. 北京邮电大学学报, 2020, 43(1): 129-134.

WANG Xiao-yu, HU Xin-hao, HAN Chang-lin. Color Pencil Drawing Based on Convolutional Neural Network[J]. Journal of Beijing University of Posts and Telecommunications, 2020, 43(1): 129-134.

参考文献

[1] Strassmann S. Hairy brushes[J]. Computer Graphics, 1986, 20(4):225-232.
[2] Sousa M C, Buchanan J W. Observational model of blenders and erasers in computer-generated pencil rendering[C]//Conference on Graphics Interface. Kingston:Morgan Kaufmann Publishers Inc, 1999:157-166.
[3] Mao Xiaoyang, Nagasaka Y, Imamiya A. Automatic generation of pencil drawing from 2D images using line integral convolution[C]//Proceedings of the 7th International Conference on Computer Aided Design and Computer Graphics. New York:IEEE Press, 2001:240-248.
[4] 吴友. 基于图像的彩色铅笔画快速生成算法研究[D]. 长沙:长沙理工大学, 2012.
[5] Lu Cewu, Xu Li, Jia Jiaya. Combining sketch and tone for pencil drawing production[C]//Proceedings of the Symposium on Non-Photorealistic Animation and Rendering. New York:ACM, 2012:65-73.
[6] 谢党恩, 张志立, 徐丹. 一种改进的二维彩色铅笔画自动绘制算法[J]. 计算机应用与软件, 2013, 30(8):28-31. Xie Dangen, Zhang Zhili, Xu Dan. An improved automatic rendering algorithm for two-dimensional color pencil drawings[J]. Computer Applications and Software, 2013, 30(8):28-31.
[7] 孙玉红, 张元科, 孟静. 基于纹理和草图的图像铅笔画绘制[J]. 计算机应用, 2016, 36(7):1976-1980. Sun Yuhong, Zhang Yuanke, Meng Jing. Image pencil drawing based on texture and sketch[J]. Computer Applications, 2016, 36(7):1976-1980.
[8] 潘龙, 纪庆革, 陈靖. 线积分卷积与双色调映射相结合的彩色素描模拟方法[J]. 中国图像图形学报, 2017, 22(7):875-885. Pan Long, Ji Qingge, Chen Jing. A color sketch simulation method combining line integral convolution with two-tone mapping[J]. Chinese Journal of Image and Graphics, 2017, 22(7):875-885.
[9] 王权, 胡越黎, 燕明, 等. 基于混合梯度最小化的铅笔画生成[J]. 上海大学学报(自然科学版), 2018, 24(2):168-175. Wang Quan, Hu Yueli, Yan Ming, et al. Pencil painting generation based on mixed gradient minimization[J]. Journal of Shanghai University (Natural Science Edition), 2018, 24(2):168-175.
[10] Yamamoto S, Mao Xiaoyang, Imamiya A. Enhanced LIC pencil filter[C]//International Conference on Computer Graphics, Imaging and Visualization. New York:IEEE Press, 2004:251-256.
[11] 冀中, 刘青, 聂林红, 等. 基于卷积神经网络的纹理分类方法研究[J]. 计算机科学与探索, 2016, 10(3):389-397. Ji Zhong, Liu Qing, Nie Linhong, et al. Texture classification method based on convolution neural network[J]. Computer Science and Exploration, 2016, 10(3):389-397.
[12] Xiao Tianjun, Zhang Jiaxing, Yang Kuiyuan, et al. Error-driven incremental learning in deep convolutional neural network for large-scale image classification[C]//Proceedings of the 22nd ACM International Conference on Multimedia. New York:ACM, 2014:177-186.
[13] Cai Xiuxia, Song Bin. Combining inconsistent textures using convolutional neural networks[J]. Journal of Visual Communication and Image Representation, 2016, 40:366-375.
[14] Yamins D, Hong H, Cadieu C, et al. Performance-optimized hierarchical models predict neural responses in higher visual cortex[J]. Proceedings of the National Academy of Sciences, 2014, 111(23):8619-8624.
[15] 李军成. 图像边缘检测的分数阶微分算子研究[J]. 计算机应用与软件, 2015, 32(12):206-209. Li Juncheng. Fractional differential operators for image edge detection[J]. Computer Applications and Software, 2015, 32(12):206-209.
[16] Zhu Ciyou, Byrd R H, Lu Peihuang, et al. Algorithm 778:L-BFGS-B:Fortran subroutines for large-scale bound-constrained optimization[J]. ACM Transactions on Mathematical Software, 1997, 23(4):550-560.

基于卷积神经网络的彩色铅笔画算法

Color Pencil Drawing Based on Convolutional Neural Network

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

本文评价

[1]	余佳润王亚峰. 一种低信噪比下基于深度学习的DoA估计方法[J]. 北京邮电大学学报, 2022, 45(6): 119-125.
[2]	叶康张淑军郭淇李辉崔雪红. 基于CM-Transformer的连续手语识别[J]. 北京邮电大学学报, 2022, 45(5): 49-53,78.
[3]	武兴坤, 罗涛, 刘爱军, 杨明, 张文静. 面向主动脉缩窄辅助诊断的神经网络模型设计[J]. 北京邮电大学学报, 2022, 45(4): 1-6.
[4]	武兴坤罗涛刘爱军杨明张文静李剑峰李文秀. 面向主动脉缩窄辅助诊断的神经网络模型设计[J]. 北京邮电大学学报, 2022, 45(4): 1-6.
[5]	许同乐, 孟良, 孔晓佳, 苏元浩, 孙砚飞. 基于EEMD的ICNN故障诊断方法[J]. 北京邮电大学学报, 2022, 45(2): 110-116.
[6]	李晓辉, 王先文, 樊韬, 刘佳文, 万宏杰. 基于卷积神经网络的高性能5G下行同步算法[J]. 北京邮电大学学报, 2022, 45(2): 117-123.
[7]	王靖, 姜竹青, 门爱东, 郭晓强, 王智康. 阶梯式图像去噪方法[J]. 北京邮电大学学报, 2022, 45(1): 52-57.
[8]	刘永利, 朱亚孟, 晁浩. 多策略MRFO算法的卷积神经网络超参数优化[J]. 北京邮电大学学报, 2021, 44(6): 83-88,95.
[9]	普运伟, 郭江, 刘涛涛, 吴海潇. 基于多学习单元卷积神经网络的雷达辐射源信号识别[J]. 北京邮电大学学报, 2021, 44(6): 74-82.
[10]	王艺霏, 莫爽, 吴文睿, 范少华, 肖丁. 基于内外卷积网络的网络入侵检测[J]. 北京邮电大学学报, 2021, 44(5): 94-100.
[11]	刘国桢, 陈鸿龙. 卷积记忆图协同过滤[J]. 北京邮电大学学报, 2021, 44(3): 21-26.
[12]	彭鹏, 李卓, 梁纪峰, 马天祥, 刘开华. 支持泛洪攻击检测的命名数据网PIT[J]. 北京邮电大学学报, 2021, 44(2): 61-67.
[13]	曹毅, 黄子龙, 盛永健, 刘晨, 费鸿博. D-2-DenseNet噪音鲁棒的城市音频分类模型[J]. 北京邮电大学学报, 2021, 44(1): 86-91.
[14]	蒲悦逸, 王文涵, 朱强, 陈朋朋. 基于CNN-ResNet-LSTM模型的城市短时交通流量预测算法[J]. 北京邮电大学学报, 2020, 43(5): 9-14.
[15]	谢晓燕, 赵欢, 蒋林. 基于视频数据特性的动态手势识别[J]. 北京邮电大学学报, 2020, 43(5): 91-97.