SealGAN: Research on the Seal Elimination Based on Generative Adversarial Network

被引：0
作者：
Li X.-L. [1 ]
Zou C.-M. [1 ]
Yang G.-T. [1 ]
Liu H. [1 ]
机构：
[1] School of Control and Computer Engineering, North China Electric Power University, Beijing
来源：
Zidonghua Xuebao/Acta Automatica Sinica | 2021年 / 47卷 / 11期
关键词：
CycleGAN; Evaluation index; Generative adversarial networks; Seal elimination; SealGAN;
D O I：
10.16383/j.aas.c190459
中图分类号：
学科分类号：
摘要：
Invoice is an important part of the financial system. With the development of computer vision and artificial intelligence technologies, various automatic invoice identification systems have been developed. However, the seals on the invoice often affect the identification success rate. In this paper, the SealGAN network structure is proposed, which can automatically eliminate the seal of invoice. SealGAN network is an improvement based on generative adversarial network CycleGAN. The two discriminant networks are replaced with two independent classifiers in the SealGAN, which reduces the classification requirement of each classifier, and the learning performance of classifiers can be improved. In addition, it combines the ResNet and UNet structures to construct a downsampling-refining-upsampling generation network, which can generate clearer images of invoice. And the network comprehensive evaluation index, including style evaluation and content evaluation, is proposed to evaluate the performance of network. Experimental results demonstrate that the SealGAN network can not only eliminate the seal automatically, but also retain the invoice content under the seal clearly, and the network performance evaluation index is higher than that of the CycleGAN-ResNet and CycleGAN-Unet. Copyright © 2021 Acta Automatica Sinica. All rights reserved.
引用
收藏
页码：2614 / 2622
页数：8
相关论文
共 24 条
  • [1] Hu Ze-Feng, Zhang Xue-Xi, Li Zhao-Xian, Batch Invoice Recognition System Based on Convolutional Neural Network (CNN), Industrial Control Computer, 32, pp. 104-105, (2019)
  • [2] Ou -Yang Huan, Fan Da-Zhao, Li Dong-Zi, Invoice seal identification based on multi-feature fusion decision, Computer Engineering and Design, 39, pp. 2842-2847, (2018)
  • [3] Chung W H, Wu M E, Ueng Y L, Su Y H., Seal imprint verification via feature analysis and classifications, Future Generation Computer Systems, 101, pp. 458-466, (2019)
  • [4] Xie R N, Mao W H, Shi G Z., Electronic invoice authenticity verifying scheme based on signature recognition, Proceedings of International Conference on Advanced Algorithms and Control Engineering (ICAACE), pp. 1-8, (2019)
  • [5] Ji Jing-Jing, Lou Zhen, Filtering of color seal on bank notes based on re-segmentation, Modern Electronics Technique, 37, 22, pp. 5-9, (2014)
  • [6] Cui Wen-Cheng, Ren Lei, Liu Yang, Chao Hong, Invoice Number recognition algorithm based on numerical structure characteristics, Journal of Dat Acquisition and Processing, 32, 1, pp. 119-125, (2017)
  • [7] Goodfellow I J, Pouget-Abadie J, Mirza M, Xu B, WardeFarley D, Ozair S, Et al., Generative adversarial nets, Proceedings of the 27th International Conference on Neural Information Processing Systems, pp. 2672-2680, (2014)
  • [8] Rezende D J, Mohamed S, Wierstra D., Stochastic back-propagation and approximate inference in deep generative models, Proceedings of International Conference on Machine Learning (ICML), (2014)
  • [9] Hinton G E, Osindero S, Teh Y W., A fast learning algorithm for deep belief nets. Neural Computation, Beijing, China, 18, 7, pp. 1527-1554, (2006)
  • [10] Wang Kun-Feng, Gou Chao, Duan Yan-Jie, Lin Yi-Lun, Zheng Xin-Hu, Wang Fei-Yue, Generative adversarial networks: the state of the art and beyond, Acta Automatica Sinica, 43, 3, pp. 321-333, (2017)
123