Auslan Sign Language Image Recognition Using Deep Neural Network

Authors

  • Shahnaz Aqsa Qambrani Department of Information and Computing, Faculty of Science and Technology, University of Sufism and Modern Sciences, Bhitshah Sindh Pakistan, Email: aqsa999qambrani@gmail.com
  • Faiza Ahmed Dahri Department of Information and Computing, Faculty of Science and Technology, University of Sufism and Modern Sciences, Bhitshah Sindh Pakistan, Email: faizadahri8@gmail.com
  • Shabana Bhatti Department of Information and Computing, Faculty of Science and Technology, University of Sufism and Modern Sciences, Bhitshah Sindh Pakistan, Email: shabobhatti9@gmail.com
  • Santosh Kumar Banbhrani Department of Information and Computing, Faculty of Science and Technology, University of Sufism and Modern Sciences, Bhitshah Sindh Pakistan, Email: banbhrani@gmail.com

DOI:

https://doi.org/10.70670/sra.v3i3.1008

Keywords:

Sign Language Recognition; Auslan; Convolutional Neural Network; Random Forest; Support Vector Machine (SVM); Canny Edge Detection; Media Pipe; Real-Time Recognition.

Abstract

Sign language recognition improves accessibility for the deaf and hard-of-hearing by translating hand gestures into machine-interpretable labels. This paper presents a hybrid pipeline for static Auslan digit recognition (classes 0–2) that combines convolutional neural networks (CNNs) for automated feature extraction with classical classifiers, Support Vector Machine (SVM) and Random Forest (RF). A grayscale dataset of 6,000 images (2,000 per class) was pre-processed using Canny edge detection to emphasize contour information, then resized for model inputs. Two CNN feature-extractors were trained and their flattened feature vectors fed to an RBF-kernel SVM and a 100-tree Random Forest. Experimental evaluation shows the CNN + Random Forest hybrid attained the highest validation accuracy (99.75%), outperforming the baseline end-to-end CNN (≈95%) and the CNN+SVM (99.67%). The trained pipeline was also integrated into a Mediapipe-based real-time testing setup to demonstrate practical applicability. Results indicate that combining deep feature extraction with ensemble/classical classifiers improves robustness and generalization for static gesture recognition. Future work will expand class coverage, incorporate dynamic gesture modelling, and investigate model compression for embedded deployment.

Downloads

Published

04-09-2025

How to Cite

Shahnaz Aqsa Qambrani, Faiza Ahmed Dahri, Shabana Bhatti, & Santosh Kumar Banbhrani. (2025). Auslan Sign Language Image Recognition Using Deep Neural Network. Social Science Review Archives, 3(3), 1762–1773. https://doi.org/10.70670/sra.v3i3.1008