基于生成对抗网络的图标形状生成
Icon Shape Generation Based on Generative Adversarial Network
DOI: 10.12677/CSA.2020.103047, PDF,  被引量    科研立项经费支持
作者: 赵 璁*, 陈平华：广东工业大学，广东 广州
关键词: 生成对抗网络；深度学习；图标；图像生成；Generative Adversarial Network； Deep Learning； Icon； Image Generation
摘要: 针对实际中的图标设计流程过于漫长和复杂的问题，参考实际图标设计流程提出了基于生成对抗网络模型的图标生成模型。首先，将用户所给出的需求转化为条件特征与噪声数据一起传入生成器中生成图标，接着将生成的图标与真实的图标一起输入鉴别器中，鉴别器鉴别图标的真假以及图标是否满足需求特征，最后二者经过迭代训练达到平衡，能够生成以假乱真的且符合需求的图标。实验表明，这种模型能够快速地生成多样的图标，且生成的图标能够满足指定的需求。
Abstract: Aiming at the problem that the icon design process is very long and complicated in the real world, with the reference of actual icon design process, an icon generation model based on the generative adversarial network model is proposed based on the actual icon design process. First, the requirements given by the user are converted into conditional features and passed into the generator to generate icons together with the noise data, and then the generated icons and the real icons are the input of the discriminator. The discriminator evaluates the icon is real or not and the icon meets the required features. Finally, the generator and discriminator come to a balanced state through the iterative training. The experiment shows that the model can quickly generate a variety of icons and the icons can meet the requirements given by user.
文章引用：赵璁, 陈平华. 基于生成对抗网络的图标形状生成[J]. 计算机科学与应用, 2020, 10(3): 456-463. https://doi.org/10.12677/CSA.2020.103047

参考文献

[1] Doersch, C. (2016) Tutorial on Variational Autoencoders. arXiv preprint arXiv:1606.05908
[2] Goodfellow, I., Pouget-Abadie, J., Mirza, M., et al. (2014) Generative Adversarial Nets. Advances in Neural Information Processing Systems, 2014, 2672-2680.
[3] Jin, Y.H., et al. (2017) Towards the Automatic Anime Characters Creation with Generative Adversarial Networks. arXiv preprint arXiv:1708.05509
[4] 许哲豪, 陈玮. 基于生成对抗网络的图片风格迁移[J]. 软件导刊, 2018, 17(6): 207-209+212+228.
[5] Nash, M.J.F., et al. (1950) Equilibrium Points in n-Person Games. Proceedings of the National Academy of Sciences, 36, 48-49. [Google Scholar] [CrossRef] [PubMed]
[6] Gulrajani, I., Ahmed, F., Arjovsky, M., et al. (2017) Improved Training of Wasserstein GANs. .
[7] Radford, A., Metz, L. and Chintala, S. (2015) Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks. arXiv preprint arXiv:1511.06434
[8] Mirza, M. and Osindero, S. (2014) Conditional Generative Adversarial Nets. arXiv preprint arXiv:1411.1784
[9] Odena, A., Chris-topher, O. and Jonathon, S. (2016) Conditional Image Synthesis with Auxiliary Classifier Gans. arXiv preprint arXiv:1610.09585
[10] Wu, H., Zheng, S., Zhang, J., et al. (2017) GP-GAN: Towards Realistic High-Resolution Im-age Blending. .
[11] Ioffe, S. and Szegedy, C. (2015) Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift. arXiv preprint arXiv:1502.03167
[12] Abadi, M., Barham, P., Chen, J., et al. (2016) Tensorflow: A System for Large-Scale Machine Learning. 12th Symposium on Operating Systems Design and Imple-mentation, 2016, 265-283.
[13] Kingma, D.P. and Ba, J. (2014) Adam: A Method for Stochastic Optimization. arXiv preprint arXiv:1412.6980