Abstract
Nowadays generating high-quality image from text description is one of most challenging problem in computer vision. Generating images from text description has a wide range of applications, like computer-aided design. In this chapter, a new model called Knowledge Transfer Generative Adversarial Networks (KT GAN) is proposed for an exact synthesis of given image. To enhance the quality of generated image, an Alternate Attention Transfer Mechanism (AATM) and Semantic Distillation Mechanism (SDM) are introduced to help the generator better to traverse cross-domain area that exists between text and image. There are two main goals for using AATM: first, to make images more visually appealing by highlighting relevant words and second, to make images more visually appealing by highlighting essential sub-regions of an image. Use an image encoder that has been taught in image-image for training the text encoder for image-image. Improved text characteristics and photos of higher quality is possible with this method. The suggested KT GAN outperforms the traditional approach significantly and provides convincing results over a wide range of assessment measures after precise testing on two public datasets.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Pradhan AK, Swain S, Rout JK (2022) Role of machine learning and cloud-driven platform in IoT-based smart farming. In: Machine learning and internet of things for societal issues. Springer, Singapore, pp 43–54
Christian L et al (2017) Photo realistic single image super-resolution using a GAN. In: CVPR
Kumar S, Ansari MD, Gunjan VK, Solanki VK (2020) On classification of BMD images using machine learning (ANN) algorithm. In: ICDSMLA 2019. Springer, Singapore, pp 1590–1599
Mani MR, Srikanth T, Satyanarayana C (2022) An integrated approach for medical image classification using potential shape signature and neural network. In: Machine learning and internet of things for societal issues. Springer, Singapore, pp 109–115
Shaik AS, Karsh RK, Suresh M, Gunjan VK (2022) LWT-DCT based image hashing for tampering localization via blind geometric correction. In: ICDSMLA 2020. Springer, Singapore, pp 1651–1663
Reed S et al (2016) Generative adversarial text to image synthesis. In: ICML
Gunjan VK, Shaik F, Venkatesh C, Amarnath M (2017) Artifacts correction in MRI images. In: Computational methods in molecular imaging technologies. Springer, Singapore, pp 9–28
Zhang H et al (2017) StackGAN: text to photo-realistic image synthesis with stacked generative adversarial networks. In: IEEE/ICCV, Oct. 2017, pp 5907–5915
Prasad PS, Bethel GNB, Singh N, Gunjan VK, Basir S, Miah S (2022) Blockchain-based privacy access control mechanism and collaborative analysis for medical images. Sec Commun Netw
Bowen L et al (2019) Controllable text to image generation. In: NeurIPS, pp 2065–2075
Gunjan VK, Shaik F, Venkatesh C, Amarnath M (2017) Visual quality improvement of CT image reconstruction with quantitative measures. In: Computational methods in molecular imaging technologies. Springer, Singapore, pp 45–73
Bhardwaj T, Mittal R, Upadhyay H, Lagos L (2022) Applications of swarm intelligent and deep learning algorithms for image-based cancer recognition. In: Garg L, Basterrech S, Banerjee C, Sharma TK (eds) Artificial intelligence in healthcare. Advanced technologies and societal change. Springer, Singapore. https://doi.org/10.1007/978-981-16-6265-2_9
Merugu S, Kumar A, Ghinea G (2023) Hardware, component, description. In: Track and trace management system for dementia and intellectual disabilities. Springer, Singapore, pp 31–48
Sinha P, Shaob M (2021) Detection of lung cancer in CT scans via deep learning and Cuckoo search optimization and IOT. Peer Rev Bimonthly Int J 11(5):11–19. Helix-The Scientific Explorer
Merugu S, Kumar A, Ghinea G (2023) Geriatric mobility assistive system. In: Track and trace management system for dementia and intellectual disabilities. Springer, Singapore, pp 85–93
Rane CV, Patil SR (2020) Data embeddable texture synthesis with fast data extraction. Peer Rev Bimonthly Int J 10(04):83–89. Helix-The Scientific Explorer
Kinge S (2019) A multi-class fisher linear discriminant approach for the improvement in the accuracy of complex texture discrimination. Peer Rev Bimonthly Int J 9(04):5108–5121. Helix-The Scientific Explorer
Bommagani G, Shaik F (2021) Histogram equalized thresholding method for analysis of diabetic myonecrosis related images. Peer Rev Bimonthly Int J 11(5):32–46. Helix-The Scientific Explorer
Acknowledgements
Thanks to the Vasavi college of Engineering for sponsoring and supporting to develop this project successfully.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2024 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Baswaraj, D., Srinivas, K. (2024). Usage of Generative Adversarial Network to Improve Text to Image Synthesis. In: Gunjan, V.K., Kumar, A., Zurada, J.M., Singh, S.N. (eds) Computational Intelligence in Machine Learning. ICCIML 2022. Lecture Notes in Electrical Engineering, vol 1106. Springer, Singapore. https://doi.org/10.1007/978-981-99-7954-7_17
Download citation
DOI: https://doi.org/10.1007/978-981-99-7954-7_17
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-99-7953-0
Online ISBN: 978-981-99-7954-7
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)