Real-Time Kazakh Sign Language Alphabet Recognition Using SVM and YOLOv8n

The development of Kazakh Sign Language (KSL) recognition is an important step in enhancing opportunities and communication for the deaf and hard-hearing communities. This work focuses on the recognition of the Kazakh Sign Language alphabet using YOLOv8n for real-time gesture recognition and a support vector machine (SVM) for classifying gesture images. SVM achieved an accuracy rate of 99% for classification and YOLOv8n detected all gestures in real-time. This paper demonstrates the first use of YOLOv8n model to KSL alphabet recognition, making a significant contribution to this field. This research gives a foundation for upcoming works and shows a need in expanding datasets with dynamic gestures and recognizing words with full sentences The results of this work not only advance sign language recognition systems in Kazakhstan but also demonstrate the potentials of broader applications in other sign languages. This research represents an important step toward closing gaps for the deaf community.