An Image Style Transfer Algorithm Based on Multi-dimension Histograms Matching

doi:10.3969/j.issn.1006-2475.2019.02.003

Abstract

Abstract: Based on the classical image style transfer algorithm using histogram matching, a new image style transfer algorithm has been proposed, which uses multi-dimension histograms matching. Firstly, different dimension histograms are generated. Then, the histogram matching is performed between the original and target images. As a result, the images after style transfer using different dimension histograms are obtained. Finally, the image having the same style with the target image is produced by fusing the images obtained in the histogram matching step. Experimental results show that the proposed algorithm can ensure that the original and target images obtain the best similarity in global scale. Meanwhile, the proposed algorithm can also make the generated image save the most details from the original image. Namely, the generated image has the similarity between the original and target images as much as possible and the local details from the original image are saved as many as possible simultaneously.

Key words: multi-dimension, histogram matching, style transfer

CLC Number:

TP391.41

LI Yu-ni, WANG Peng, XIAO Jian-li. An Image Style Transfer Algorithm Based on Multi-dimension Histograms Matching[J]. Computer and Modernization, doi: 10.3969/j.issn.1006-2475.2019.02.003.

References

［1］钱小燕,肖亮,吴慧中. 快速风格迁移［J］. 计算机工程, 2006,32(21):15-17.
［2］窦亚玲,周武彬,季人煌. 基于卷积神经网络的图像风格迁移技术［J］. 现代计算机(专业版), 2018(30):47-51.
［3］丁晓龙. 基于深度学习的图像风格迁移技术的前沿进展［J］. 电子制作, 2018(18):86-87.
［4］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.
［5］陈淑環,韦玉科,徐乐,等. 基于深度学习的图像风格迁移研究综述［J/OL］. (2018-07-23). http://www.arocmag.com/article/02-2019-08-063.html.
［6］ JOHNSON J, ALAHI A, LI F F. Perceptual losses for real-time style transfer and super-resolution［C］// Proceedings of the 2016 European Conference on Computer Vision. Springer, 2016:694-711.
［7］张俊杰,丁淑艳,李伦波. 基于类Haar特征和颜色特征的NAO机器人识别［J］. 计算机与现代化, 2017(2):30-35.
［8］刘子君,张杰斌,周欣欣,等. 基于颜色特征的自然保护区图像筛选系统［J］. 计算机与现代化, 2016(2):32-37.
［9］ LIU P Z, GUO J M, CHAMNONGTHAI K, et al. Fusion of color histogram and LBP-based features for texture image retrieval and classification［J］. Information Sciences, 2017,390:95-111.
［10］NIU Y Z, ZHANG H F, GUO W Z, et al. Image quality assessment for color correction based on color contrast similarity and color value difference［J］. IEEE Transactions on Circuits and Systems for Video Technology, 2018,28(4):849-862.
［11］王刚. 基于角度径向变换的旋转不变纹理分类［J］. 计算机与现代化, 2015(6):46-50.
［12］田配云,郑碧波,陈伟清. 基于彩色局部角度二值模式的纹理分类研究［J］. 计算机与现代化, 2013(4):86-89.
［13］马欢,楚恒,王汝言. 纹理与几何特征在道路提取中的应用［J］. 计算机与现代化, 2012(7):96-99.
［14］BANERJEE P, BHUNIA A K, BHATTACHARYYA A, et al. Local neighborhood intensity pattern: A new texture feature descriptor for image retrieval［J］. Expert Systems with Applications, 2018,113:100-115.
［15］宋志超. 基于多特征的图像表观迁移技术研究［D］. 天津:天津大学, 2017.
［16］GAO T, ZHAO X M, CHEN T, et al. Face description based on adaptive local weighted Gabor comprehensive histogram feature［J］. Multimedia Tools and Applications, 2017,76(10):12893-12916.
［17］XIAO J L, XIANG W S, LIU Y C. Vehicle logo recognition by weighted multi-class support vector machine ensembles based on sharpness histogram features［J］. IET Image Processing, 2015,9(7):527-534.
［18］熊伟. 基于颜色直方图匹配的色彩传输［J］. 计算机应用与软件, 2007,24(9):147-148.
［19］WEI M, XIAO J L. Vehicle logo recognition using multi-level fusion model［C］// Proceedings of the 9th International Conference on Graphic and Image Processing (ICGIP 2017). 2017, doi: 10.1117/12.2303590.
［20］肖建力. 智能交通中的多核支持向量机与分类器集成方法研究［D］. 上海:上海交通大学, 2013.
［21］苏莘珺,何星慰. 基于纹理相似度的颜色迁移［J］. 包装学报, 2016,8(1):59-62.
［22］GATYS L A, ECKER A S, BETHGE M. Image style transfer using convolutional neural networks［C］// Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition. 2016:2414-2423.
［23］GONZALEZ R C, WOODS R E. Digital Image Processing［M］. Addison-Wesley, 2010.
［24］阮秋琦. 数字图像处理基础［M］. 北京:清华大学出版社, 2009.

[1]	CHEN Ming-yao, XU Kun, LI Xiao-xuan. A Hand Gesture Segmentation Method Based on Style Transfer [J]. Computer and Modernization, 2021, 0(05): 20-25.
[2]	LI Xin-hua, WANG Yong, YAN Jia-jing, HOU Wen-gang. A Multi-source and Multi-dimensional Government Data Sharing Analysis System for Macroeconomic Analysis [J]. Computer and Modernization, 2020, 0(09): 25-31.
[3]	LI Dan-yu, CHEN Yi-hua. Application of Multi-layer Multi-dimensional Association #br# Rule Mining Algorithm in Recommendation System [J]. Computer and Modernization, 2019, 0(06): 44-.
[4]	ZHANG Jun-jie1, DING Shu-yan2, LI Lun-bo1. NAO Robot Player Recognition Based on Haar-like Features and Color Features [J]. Computer and Modernization, 2017, 0(2): 30-35.
[5]	WANG Zhi-qiang, LE Jia-jin, CHEN De-hua. Multi-dimensional Time Series Correlation Analysis Based on Hyperthyroidism Clinical Parameters [J]. Computer and Modernization, 2016, 0(4): 12-15.
[6]	ZHENG Sheng-jun1， GUO Long-hua2， LI Jian-hua2, WANG Hong-kai3, LIU Yun4. Multi-dimensional Monitoring System for Website Security Based on Cloud Platform [J]. Computer and Modernization, 2016, 0(1): 39-45.
[7]	DAI Hong, YU Ning, CHANG Zi-guan. A Multi-dimension Constellation Snapshot Spatio-temporal #br# Data Model Based on Historical Events [J]. Computer and Modernization, 2014, 0(1): 176-181.
[8]	QI Li-na. Application of Data Granularity in Warehouse for E-commerce Website [J]. Computer and Modernization, 2013, 218(10): 91-93.
[9]	LIU Lin . Multi-dimensional Analysis of Library Loans of College Staff Based on Data Warehouse [J]. Computer and Modernization, 2010, 1(11): 124-126.