A text image generation model based on deep learning

Article type: Research Article

Authors: Wang, Jing^{a; b; *}

Affiliations: [a] School of Humanities and Arts, Hunan International Economics University, Changsha, China | [b] STAMFORD INTERNATIONAL UNIVERSITY, Bangkok, Thailand

Correspondence: [*] Corresponding author. Jing Wang. E-mail: [email protected].

Abstract: The traditional text-image confrontation model utilizes a convolutional network in the discriminator to extract image features, yet this fails to involve the spatial relationship between underlying objects, resulting in a poor-quality generated image. To remedy this, a capsule network is proposed to improve the model. The convolutional network in the discriminator is replaced with a capsule network, thereby improving the robustness of the images. Through experiments on the Oxford-102 and CUB datasets, it has been found that the new model can effectively improve the quality of generated text-image. The FID value of the generated flower image decreased by 14.49%, and the FID value of the generated bird image decreased by 9.64%. Additionally, the Inception Score of images generated on the Oxford-102 and CUB datasets increased by 22.60% and 26.28%, respectively, indicating that the improved model generated richer and more meaningful image features.

Keywords: Generating images, capsule network, generation adversarial network, convolutional network, robustness

DOI: 10.3233/JIFS-223741

Journal: Journal of Intelligent & Fuzzy Systems, vol. 45, no. 3, pp. 4979-4989, 2023