An Hybrid Algorithm For Generating Synthetic Images From Text
Keywords:
GAN, CNN, RNN, BI-LSTMAbstract
A method called content-to-picture creation
aims to generate lifelike images that match text
descriptions. These visuals find use in tasks like photo
editing. Advanced neural networks like GANs have
shown promise in this field. Key considerations include
making the images look real and ensuring they match
the provided text accurately. Despite recent progress,
achieving both realism and content consistency remains
challenging. To tackle this, a new model called Bridge
GAN is introduced, which creates a bridge between text
and images. By combining Bridge GAN with a char
CNN – RNN model, the system produces images with
high content consistency, surpassing previous methods.
In these paper we used we have used FLICKER TEXT
and IMAGE dataset. Proposed model performs better
than state of art techniques.
Downloads
References
Frolov, S., Hinz, T., Raue, F., Hees, J., Dengel,
A.: Adversarial text-to-image synthesis: a
review. Neural Netw. 144, 187–209 (2021)
2. Dong, Y., Zhang, Y., Ma, L., Wang, Z., Luo, J.:
Unsupervised text-to-image synthesis. Pattern
Recognit. 110, 107573
(2021). https://doi.org/10.1016/j.patcog.2020.1
07573
3. Bankar, S.A., Ket, S.: An analysis of text-toimage
synthesis. In: Proceedings of the
International Conference on Smart Data
Intelligence (ICSMDI 2021) (2021)
4. Tan, Y.X., Lee, C.P., Neo, M., Lim, K.M.:
Text-to-image synthesis with self-supervised
learning. Pattern Recognit. Lett. 157, 119–126
(2022)
5. Hossain, M.Z., Sohel, F., Shiratuddin, M.F.,
Laga, H., Bennamoun, M.: Text to image
synthesis for improved image captioning. IEEE
Access 9, 64918–64928 (2021)
6. Zhang, Z., Xie, Y., Yang, L.: Photographic
text-to-image synthesis with a hierarchicallynested
adversarial network. In: Proceedings of
the IEEE Conference on Computer Vision and
Pattern Recognition, pp. 6199–6208 (2018)
7. Sun, J., Zhou, Y., Zhang, B.: ResFPA-GAN:
text-to-image synthesis with generative
adversarial network based on residual block
feature pyramid attention. In: 2019 IEEE
International Conference on Advanced
Robotics and its Social Impacts (ARSO), pp.
317–322. IEEE (2019)
8. Reed, S.E., Akata, Z., Mohan, S., Tenka, S.,
Schiele, B., Lee, H.: Learning what and where
to draw. Adv. Neural Inf. Process. Syst. 29,
217–225 (2018)
9. Mansimov, E., Parisotto, E., Ba, J.L.,
Salakhutdinov, R.: Generating images from
captions with attention. arXiv
preprint arXiv:1511.02793 (2015)
10. Odena, A., Olah, C., Shlens, J.: Conditional
image synthesis with auxiliary classifier GANs.
In: International Conference on Machine
Learning, pp. 2642–2651. PMLR (2017)
11. Zhang, H., et al.: StackGAN++: realistic image
synthesis with stacked generative adversarial
networks. IEEE Trans. Pattern Anal. Mach.
Intell. 41(8), 1947–1962 (2018)
12. Peng, Y., Qi, J.: Reinforced cross-media
correlation learning by context-aware
bidirectional translation. IEEE Trans. Circuits
Syst. Video Technol. 30(6), 1718–1731 (2019)
13. Gregor, K., Danihelka, I., Graves, A., Rezende,
D., Wierstra, D.: DRAW: a recurrent neural
network for image generation. In: International
Conference on Machine Learning, pp. 1462–
1471. PMLR (2015)
14. Dash, A., Gamboa, J.C.B., Ahmed, S., Liwicki,
M., Afzal, M.Z.: TAC-GAN-text conditioned
auxiliary classifier generative adversarial
network. arXiv
preprint arXiv:1703.06412 (2017)
15. Gajendran, S., Manjula, D., Sugumaran, V.:
Character level and word level embedding with
bidirectional LSTM–dynamic recurrent neural
network for biomedical named entity
recognition from literature. J. Biomed.
Inform. 112, 103609 (2020).
