Publications by authors named "Mehwish Leghari"
Roman Urdu text is very widespread on many websites. People mostly prefer to give their social comments or product reviews in Roman Urdu, and Roman Urdu is counted as non-standard language. The main reason for this is that there is no rule for word spellings within Roman Urdu words, so people create and post their own word spellings, like "2mro" is a nonstandard spelling for tomorrow.
View Article and Find Full Text PDFArticle Synopsis
- The article discusses an extensive dataset created for detecting and recognizing Urdu text in natural scene images, an area of interest in computer vision.
- Over 2500 images were captured to form three distinct datasets: isolated Urdu character images, cropped word images, and an end-to-end text spotting dataset, focusing primarily on Urdu text.
- The newly developed datasets can also support advancements in Arabic and Persian text recognition systems, as well as enhance multi-language translation tools for tourists.