Browsing by Author "Obaid Ur Rehman"

Now showing 1 - 2 of 2
  • No Thumbnail Available
    Item
    Deep learning models for natural to pakistan sign language text translation.
    (UMT Lahore, 2022) Muhammad Bilal; Obaid Ur Rehman; Muhammad Ahmed
    In order to show emotions, reactions, sharing ideas communication plays an important role. The main objective of this research is making communication easy and cost efficient between the deaf and un impaired person. Deaf communicate with each other by using gesture-based language but with the un impaired it's very hard for the deaf to communicate and for un impaired it’s also very hard to communicate. This research will address this problem and by using Neural Machine will solve this problem. In this research the problem that will be addressed is the translation of Natural English Language to Pakistan Sign Language text translation. The deep learning models that will be used in order achieve translation goal of translation are Gated Recurrent Unit (GRU), BI- Directional Gated Recurrent unit (BIGRU), Long Short-Term Memory (LSTM) and Bi-Directional Long Short-Term Memory (Bi-LSTM). The dataset that will be used to solve this problem consisting of English language sentences with its corresponding Pakistan sign language sentences. The evaluation measures that will be used to evaluate the prediction of translations are BLEU score, Word error rate and Translation Error Rate.
  • No Thumbnail Available
    Item
    The illusion
    (UMT, Lahore, 2025) Obaid Ur Rehman