Image Colorization Algorithm Based on Deep Learning

Author:

Wang Na,Chen Guo-Dong,Tian Ying

Abstract

As we know, image colorization is widely used in computer graphics and has become a research hotspot in the field of image processing. Current image colorization technology has the phenomenon of single coloring effect and unreal color, which is too complicated to be implemented and struggled to gain popularity. In this paper, a new method based on a convolution neural network is proposed to study the reasonable coloring of human images and ensures the realism of the coloring effect and the diversity of coloring at the same time. First, this paper selects about 5000 pictures of people and plants from the Imagenet dataset and makes a small dataset containing only people and backgrounds. Secondly, in order to obtain the image segmentation results, this paper improves the U-net network and carries out three times of down sampling and three times of up-sampling. Finally, we add the expanded convolution, and use the sigmoid activation function to replace the ReLU (The Rectified Linear Unit) activation function and put the BN (Batch Normalization) before the activation function. Experimental results show that our proposed image colorization algorithm based on the deep learning scheme can reduce the training time of the network and achieve higher quality segmentation results.

Funder

Fujian Provincial Science and Technology Department

Publisher

MDPI AG

Subject

Physics and Astronomy (miscellaneous),General Mathematics,Chemistry (miscellaneous),Computer Science (miscellaneous)

Reference45 articles.

1. Gupta, R.K., Chia, Y.S., Rajan, D., Ng, E.S., and Huang, Z.Y. Image colorization using similar images. Proceedings of the 20th ACM International Conference on Multimedia.

2. Long, J., Feng, X., Zhu, X., Zhang, J., and Gou, G. Efficient Superpixel-Guided Interactive Image Segmentation Based on Graph Theory. Symmetry, 2018. 10.

3. StyLit: Illumination-Guided Example-Based Stylization of 3D Renderings;Fier;ACM Trans. Graph.,2016

4. Interactive toon shading using mesh smoothing;Al-Rousan;Int. J. Intell. Syst. Technol. Appl.,2016

5. Contour-Aware 3D Reconstruction of Side-View Sketches;Ramos;Comput. Graph.,2018

Cited by 4 articles. 订阅此论文施引文献 订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献

1. Automated Image Colorization using Machine Learning Algorithms;2024 International Conference on Inventive Computation Technologies (ICICT);2024-04-24

2. A Study of Advancements in Deep Learning-Based Image Colorization Techniques;2023 5th International Conference on Advances in Computing, Communication Control and Networking (ICAC3N);2023-12-15

3. SPDGAN: a generative adversarial network based on SPD manifold learning for automatic image colorization;Neural Computing and Applications;2023-09-09

4. Reviving Black and White Images: Enhancing Colorization with Generative Adversarial Networks (GANs);2023 14th International Conference on Computing Communication and Networking Technologies (ICCCNT);2023-07-06

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3