基于Sobel滤波器的图像风格转换算法

doi:10.19678/j.issn.1000-3428.0059961

摘要/Abstract

摘要： 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。

关键词: 图像风格转换, 边缘检测, Sobel滤波器, 卷积神经网络, 均方误差

Abstract: Iteration-based image style transformation does not consider the structure of content image, resulting in a distortion of lines in the generated image.To solve the problem, an algorithm based on edge detection is proposed to constrain the information during image reorganization.The Sobel filter is used to extract edge information on the same convolutional layer of the content image and the generated image.The loss function selects the mean square error, and the weighted algebraic sum of edge loss, content loss and style loss is taken as the total loss of the neural network.The experimental results show that the proposed algorithm can effectively reduce the distortion of image lines and the image noise, and improves the quality of generated images.

Key words: image style transformation, edge detection, Sobel filter, Convolutional Neural Network(CNN), mean square error

中图分类号:

TN958.34

陈志鹏, 郑文秀, 黄琼丹. 基于Sobel滤波器的图像风格转换算法[J]. 计算机工程, 2021, 47(12): 274-277,284.

CHEN Zhipeng, ZHENG Wenxiu, HUANG Qiongdan. Image Style Transformation Algorithm Based on Sobel Filter[J]. Computer Engineering, 2021, 47(12): 274-277,284.

https://www.ecice06.com/CN/Y2021/V47/I12/274

图/表 4

参考文献

[1] 张景祥.王士同.邓赵红.等.融合异构特征的子空间迁移学习算法[J].自动化学报, 2014, 40(2):236-246. ZHANG J X, WANG S T, DENG Z H, et al.A subspace transfer learning algorithm integrating heterogeneous features[J].Acta Automatica Sinica, 2014, 40(2):236-246.(in Chinese)
[2] PORTILLA J, SIMONCELLI E P.A parametric texture model based on joint statistics of complex wavelet coefficients[J].International Journal of Computer Vision, 2000, 40:49-70.
[3] SEMMO A, LIMBERGER D, KYPRIANIDIS J E, et al.Image stylization by oil paint filtering using color palettes[C]//Proceedings of International Symposium on Computational Aesthetics in Graphics, Visualization, and Imaging.New York, USA:ACM Press, 2015:149-158.
[4] SHIH Y C, PARIS S, BARNES C, et al.Style transfer for headshot portraits[J].ACM Transactions on Graphics, 2014, 33(4):1-14.
[5] LI X T, LIU S F, KAUTZ J, et al.Learning linear transformations for fast arbitrary style transfer[EB/OL].[2020-10-07].http://export.arxiv.org/abs/1808.04537.
[6] CHEN D D, YUAN L, LIAO J, et al.StyleBank:an explicit representation for neural image style transfer[C]//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.Washington D.C., USA:IEEE Press, 2017:2770-2779.
[7] GATYS L A, ECKER A S, BETHGE M.A neural algorithm of artistic style[J].Journal of Vision, 2016, 16:326-345.
[8] GATYS L A, ECKER A S, BETHGE M.Image style transfer using convolutional neural networks[C]//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.Washington D.C., USA:IEEE Press, 2016:2414-2423.
[9] 郑茗化, 白本督, 范九伦, 等.基于局部均方差的神经网络图像风格转换[J].现代电子技术, 2019, 42(14):144-147, 151. ZHENG M H, BAI B D, FAN J L, et al.Neural network image style conversion based on local mean square error[J].Modern Electronic Technology, 2019, 42(14):144-147, 151(in Chinese)
[10] RISSER E, WILMOT P, BARNES C.Stable and controllable neural texture synthesis and style transfer using histogram losses[EB/OL].[2020-10-09].https://arxiv.org/abs/1701.08893.
[11] LI C, WAND M.Combining markov randomfields and convolution neural networks for image synthesis[C]//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.Washington D.C., USA:IEEE Press, 2016:1-10.
[12] BERGER G, MEMISEVIC R.Incorporating long range consistency in CNN-based texture generation[EB/OL].[2020-10-08].http://arxiv.org/pdf/1606.01286.
[13] 孙冬梅, 张飞飞, 毛启容.标签引导的生成对抗网络人脸表情识别域适应方法[J].计算机工程, 2020, 46(5):267-273, 281. SUN D M, ZHANG F F, MAO Q R.Label-guided domain adaptation method in generative adversarial network for facial expression recognition[J].Computer Engineering, 2020, 46(5):267-273, 281.(in Chinese)
[14] GOODFELLOW I J, POUGET-ABADIE J, MIRZA M, et al.Generative adversarial nets[C]//Proceedings of the 28th International Conference on Neural Information Processing Systems.Cambridge, USA:MIT Press, 2014:2672-2680.
[15] HUANG X, BELONGIE S.Arbitrary style transfer in real-time with adaptive instance normalization[C]//Proceedings of IEEE International Conference on Computer Vision and Pattern Recognition.Washington D.C., USA:IEEE Press, 2017:1510-1519.
[16] 张航, 曹瞻.基于局部均值与方差的图像中值滤波方法[J].中南大学学报(自然科学版), 2013, 44(2):381-384. ZHANG H, CAO Z.Image median filter method based on local mean and variance[J].Journal of Central South University(Science and Technology), 2013, 44(2):381-384.(in Chinese)
[17] LIU X W, LIU Z, ZHOU X F, et al.Saliency-guided image style transfer[C]//Proceedings of International Conference on Multimedia & Expo Workshops.Washington D.C., USA:IEEE Press, 2019:66-71.
[18] ZHU T, LIU S G.Detail-preserving arbitrary stylle transfer[C]//Proceedings of IEEE International Conference on Multimedia and Expo.Washington D.C., USA:IEEE Press, 2020:1-6.
[19] 谢志峰, 叶冠桦, 闫淑萁, 等.基于生成对抗网络的HDR图像风格迁移技术[J].上海大学学报(自然科学版), 2018, 24(4):524-534. XIE Z F, YE G H, YAN S Q, et al.HDR image style transfer technology based on generative confrontation network[J].Journal of Shanghai University (Natural Science Edition), 2018, 24(4):524-534.(in Chinese)
[20] SIMONYAN K, ZISSERMAN A.Very deep convolutional networks for large-scale image recognition[EB/OL].[2020-10-11].https://arxiv.org/pdf/1409.1556.pdf.
[21] 高飞, 黄启宏, 程卫东, 等.Sobel边缘检测算子的改进研究[J].数字技术与应用, 2016, 1:143-145. GAO F, HUANG Q H, CHENG W D.et al.Research on improvement of edge detection operator[J].Digital Technology and Application, 2016, 1:1-10.(in Chinese)
[22] 虎玲, 常霞, 纪峰.图像边缘检测方法研究新进展[J].现代电子技术, 2018, 41(23):32-37. HU L, CHANG X, JI F.New progress in research on image edge detection[J].Modern Electronics Technique, 2018, 41(23):32-37.(in Chinese)
[23] 苗英杰, 崔琛, 等.基于BFGS拟牛顿法的观测矩阵优化算法[J].电子信息对抗技术, 2019, 34(6):32-37, 55. MIAO Y J, CUI C, et al.Observation matrix optimization algorithm based on BFGS quasi-Newton method[J].Electronic Information Warfare Technology, 2019, 34(6):32-37, 55.(in Chinese)

选择文件类型/文献管理软件名称

选择包含的内容