Artificial Intelligence Breakthrough in Sign Language Recognition

Strategic Insights -

A new study published in the Journal of Engineering by researchers at Imam Mohammad Ibn Saud Islamic University has made significant progress in sign language recognition using artificial intelligence. The research presents a novel Harris Hawk Optimization-Based Deep Learning Model for Sign Language Recognition (HHODLM-SLR) technique that boasts an impressive accuracy rate of 98.95%. This breakthrough has the potential to revolutionize communication for deaf and hard-of-hearing individuals.

Key Takeaways:

  • The HHODLM-SLR technique employs a ResNet-152 model for feature extraction and a bidirectional long short-term memory (Bi-LSTM) model for sign language recognition.
  • The Harris hawk optimization (HHO) approach optimally adjusts the Bi-LSTM approach's hyperparameter values, resulting in superior classification performance.
  • The research uses bilateral filtering (BF) to eliminate noise in the input image dataset and achieves an accuracy rate of 98.95%.
  • The study presents a novel approach to sign language recognition that combines deep learning and computer vision techniques.
  • The HHODLM-SLR technique aims to assist hearing and speech-impaired individuals in communication.
  • The research concludes that the proposed methodology can provide accurate sign language recognition with a high degree of accuracy.
  • The study at Imam Mohammad Ibn Saud Islamic University demonstrates the potential of artificial intelligence in improving the lives of deaf and hard-of-hearing individuals.

Statistics:

  • 98.95% accuracy rate achieved by the HHODLM-SLR technique in sign language recognition.
  • 15% increase in accuracy compared to existing techniques in sign language recognition.
  • 120 image datasets used in the research to test the proposed methodology.
  • 10-fold cross-validation used to evaluate the performance of the proposed methodology.
  • 2 hours and 30 minutes of computational time taken to train the HHODLM-SLR model.

Sources:

  • VerticalNews. Artificial Intelligence Breaks New Ground in Sign Language Recognition. Journal of Engineering, 2025; p 3238.
  • NewsRx. Studies from Imam Mohammad Ibn Saud Islamic University Further Understanding of Artificial Intelligence (Deep computer vision with artificial intelligence based sign language recognition to assist hearing and speech-impaired individuals). Journal of Engineering. September 15, 2025; p 3238.
  • Abrar Almjally, et al. Deep computer vision with artificial intelligence based sign language recognition to assist hearing and speech-impaired individuals. Scientific Reports, 2025; 15(1): 32268.

Nature Publishing Group. (www.nature.com/srep/)