Abstract
Text-to-image synthesis has advanced recently as a prospective area for improvement in computer vision applications. The image synthesis model follows significant neural network architectures such as Generative Adversarial Networks (GANs). The flourishing text-to-image generation approaches can nominally reflect the meaning of the text in generated images. Still, they need the prospect of providing the necessary details and eloquent object features. Intelligent systems are trained in text-to-image synthesis applications for various languages. However, their contribution to regional languages is yet to be explored. Autoencoders prompt the synthesis of images, but they result in blurriness, which results in clear output and essential features of the picture. Based on textual descriptions, The GAN model is capable of producing realistic images of a high quality that can be used in various applications, like fashion design, photo editing, computer-aided design, and educational platforms. The proposed method uses two-stage processing to create a language model using a BERT model called TAM-BERT and an existing MuRIL BERT, followed by image synthesis using a GAN. The work was conducted using the Oxford-102 dataset, and the model's efficiency was evaluated using the F1-Score measure.
- [1] . 2018. Synthesizing images of humans in unseen poses. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 8340–8348.Google Scholar
Cross Ref
- [2] . 2016. Generative adversarial text to image synthesis. In Proceedings of the International Conference on Machine Learning. PMLR, 1060–1069.Google Scholar
- [3] . 2020. Semantically consistent text to fashion image synthesis with an enhanced attentional generative adversarial network. Pattern Recogn. Lett. 135 (2020), 22–29.Google Scholar
Cross Ref
- [4] . 2018. Cross-view image synthesis using conditional GANs. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 3501–3510.Google Scholar
Cross Ref
- [5] . 2004. Building language models for Tamil speech recognition system. In Proceedings of the Asian Applied Computing Conference. Springer, Berlin, 161–168.Google Scholar
Cross Ref
- [6] . 2012. Language models for online handwritten Tamil word recognition. In Proceeding of the Workshop on Document Analysis and Recognition. 42–48.Google Scholar
Digital Library
- [7] . 2015. Bigram language models and reevaluation strategy for improved recognition of online handwritten Tamil words. ACM Trans. Asian Low-Res. Lang. Info. Process. 14, 2 (2015), 1–28.Google Scholar
Digital Library
- [8] . 2020. Generative adversarial networks. Commun. ACM 63, 11 (2020), 139–144.Google Scholar
Digital Library
- [9] . 2015. Unsupervised representation learning with deep convolutional generative adversarial networks. Retrieved from https://arXiv:1511.06434.Google Scholar
- [10] . 2018. RDCGAN: Unsupervised representation learning with regularized deep convolutional generative adversarial networks. In Proceedings of the 9th Conference on Artificial Intelligence and Robotics and 2nd Asia-Pacific International Symposium. IEEE. 31–38.Google Scholar
Cross Ref
- [11] . 2020. CookGAN: Causality-based text-to-image synthesis. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 5519–5527.Google Scholar
Cross Ref
- [12] . 2019. Dm-gan: Dynamic memory generative adversarial networks for text-to-image synthesis. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 5802–5810.Google Scholar
Cross Ref
- [13] . 2020. KT-GAN: Knowledge-transfer generative adversarial network for text-to-image synthesis. IEEE Trans. Image Process. 30 (2020), 1275–1290.Google Scholar
Digital Library
- [14] . 2019. Semantic object accuracy for generative text-to-image synthesis. Retrieved from https://arXiv:1910.13321.Google Scholar
- [15] . 2020. Face completion using generative adversarial network. In Advanced Computing Technologies and Applications. Springer, 523–531.Google Scholar
Cross Ref
- [16] . 2011. HMM-based lexicon-driven and lexicon-free word recognition for online handwritten Indic scripts. IEEE Trans. Pattern Anal. Mach. Intell. 34, 4 (2011), 670–682.Google Scholar
Digital Library
- [17] . 2021. ThamizhiMorph: A morphological parser for the Tamil language. Mach. Transl. 35, 1 (2021), 37–70.Google Scholar
Digital Library
- [18] . 2019. Piripori: Morphological analyser for Tamil. In Proceedings of the International Conference on Artificial Intelligence, Smart Grid And Smart City Applications. Springer, Cham, 801–809.Google Scholar
- [19] . 2020. Topic categorization of Tamil News Articles using PreTrained Word2Vec Embeddings with Convolutional Neural Network. In Proceedings of the International Conference on Computational Intelligence for Smart Power System and Sustainable Energy (CISPSSE’20). IEEE, 1–4.Google Scholar
Cross Ref
- [20] . 2019. Sentiment analysis in Tamil texts: A study on machine learning techniques and feature representation. In Proceedings of the 14th Conference on Industrial and Information Systems (ICIIS’19). IEEE, 320–325.Google Scholar
Cross Ref
- [21] . 2021. Learning syllables using Conv-LSTM model for Swahili word representation and part-of-speech Tagging. Trans. Asian Low-Res. Lang. Info. Process. 20, 4 (2021), 1–25.Google Scholar
Digital Library
- [22] . 2022. The survey: Text generation models in deep learning. Journal of King Saud University-Computer and Information Sciences 34, 6 (2022), 2515--2528.Google Scholar
- [23] . 2019. Scibert: A pre-trained language model for scientific text. Retrieved from https://arXiv:1903.10676.Google Scholar
- [24] . 2018. Neural vector spaces for unsupervised information retrieval. ACM Trans. Info. Syst. 36, 4 (2018), 1–25.Google Scholar
Digital Library
- [25] . 2018. Generating handwritten chinese characters using cyclegan. In Proceedings of the IEEE Winter Conference on Applications of Computer Vision (WACV’18). IEEE, 199–207.Google Scholar
Cross Ref
- [26] . 2021. Text to image synthesis for improved image captioning. IEEE Access 9 (2021), 64918–64928.Google Scholar
Cross Ref
- [27] . 2020. End-to-end text-to-image synthesis with spatial constraints. ACM Trans. Intell. Syst. Technol. 11, 4,
Article 47 (Aug. 2020), 19 pages. Google ScholarDigital Library
- [28] . 2021. Text to image synthesis using multi-generator text conditioned generative adversarial networks. Multimedia Tools Appl. 80, 5 (Feb 2021), 7789–7803. Google Scholar
Digital Library
- [29] , and Talukdar. 2021. MuRIL: Multilingual representations for Indian languages. Retrieved from https://arxiv.org/abs/2103.10730.Google Scholar
Index Terms
TAM GAN: Tamil Text to Naturalistic Image Synthesis Using Conventional Deep Adversarial Networks
Recommendations
Perceptual adversarial non-residual learning for blind image denoising
AbstractImage denoising is tricky work required in various image processing and computer vision challenges. This paper proposes and implements a perceptual adversarial non-residual blind denoising training architecture based on non-residual adversarial ...
GAN review: Models and medical image fusion applications
Highlights- Summarizing various models of GAN.
- Discussing the advantages and applications ...
AbstractGenerative Adversarial Network (GAN) is a research hotspot in deep generative models, which has been widely used in the field of medical image fusion. This paper summarizes GAN models from the following four aspects: firstly, the basic ...
Graphical abstractDisplay Omitted
Secure deep neural networks using adversarial image generation and training with Noise-GAN
Highlights- Generating adversarial samples for evasion attacks are proposed using Noise-Generative Adversarial Networks.
AbstractRecent advances in artificial intelligence have increased the importance of security issues. Nowadays, deep neural networks (DNNs) are used in many critical applications such as pilot drones and self-driving cars. So, the DNN's ...






Comments