Exploring cGANsfor Urdu Alphabets and Numerical System Generation
Journal Title: International Journal of Innovations in Science and Technology - Year 2025, Vol 7, Issue 5
Abstract
Urdu ligatures play a crucial role in text representation and processing, especially in Urdu language applications. While extensive research has been conducted on handwritten characters in various languages, there is still a significant gap in studying raster-based generated images of Urdu characters. This paper presents a generative model designed to produce high-quality samples that closely resemble yet differ from existing datasets. Utilizing the power of Generative Adversarial Networks (GANs), the model is trained on a diverse dataset comprising 40 classes of Urdu alphabets and 20 classes of numerals (both modern and Arabic-style), with each class containing 1,000 augmented images to capture variations. The generator network creates synthetic Urdu character samples based on class conditions, while the discriminator network evaluates their similarity to real datasets. The model’s effectiveness is assessed using key metrics such as the Peak Signal-to-Noise Ratio (PSNR), Structural Similarity Index (SSIM), and Fréchet Inception Distance (FID). The results confirm that the proposed GAN-based approach achieves high fidelity and structural accuracy, making it highly valuable for applications in text digitization and Optical Character Recognition (OCR).
Authors and Affiliations
Suleman Khalil, Syed Yasser Arafat, Fatima Bibi, Faiza Shafique
Keywords
Related Articles
- EP ID EP764474
- DOI -
- Views 13
- Downloads 0
https://journal.50sea.com/index.php/IJIST/article/view/645/1249
Ransomware has emerged as a prominent cyber threat in recent years, targeting numerous businesses. In response to the escalating frequency of attacks, organizations are increasingly seeking effective tools and strategi...
Monsoon 2022 Floods and Its Impacts on Agriculture Land Using Geospatial Approaches:A Case Study of Khyber Pakhtunkhwa Province Pakistan.
Pakistan lies among the most vulnerable countries facing severe episodes of climate change-induced hydro-climatic disasters, including heatwaves, floods, droughts, and rainfall-induced landslides. These disasters have...
Clinical Prediction of Female Infertility Through Advanced Machine Learning Techniques
Infertility in females implies failure by such women to conceive even after having at least one year of intercourse without using any contraceptives. Infertility can be caused by a variety of factors, including ovulati...
Developing AQuranic QA System: Bridging Linguistic Gaps in Urdu Translation Using NLP and Transformer Model
The limited access to Quranic knowledge for Urdu speakers is due to inadequate Natural Language Processing (NLP) tools, which hinder precise Quranic understanding and retrieval. This research introduces a Transformer-b...
Effect of Crack Location and Orientation on Crack Growth in Boiler Tube: Theoretical and Computational Investigation
Introduction/Importance of Study: Safety is the paramount concern in the operations and inspections of pressure vessels, such as water tube boilers. Defects in the boiler tubes can lead to the development of cracks. N...