GESTURE RECOGNITION OF MACHINE LEARNING AND CONVOLUTIONAL NEURAL NETWORK METHODS FOR KAZAKH SIGN LANGUAGE

Aug 4, 2026

Machine learning and neural networks have gained broad public interest due to rapid advances that improve computer recognition of objects, sounds, texts, and other data. This progress in computer vision supports increasingly sophisticated models for recognizing hand gestures and enabling more natural human-computer interaction. The study examines popular hand-gesture recognition models—CNN, LSTM, and SVM—comparing approaches, processing time, and training data requirements. Experiments train the models for Kazakh sign language recognition using the dactyl alphabet and evaluate performance through detailed method descriptions, effectiveness, and recorded experimental results.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages16

Reading Time40 min

AccessFree to download

Introduction

Literature review and problem statement

DOI: 10. 37943/15LPCU4095 © Samat Mukhanov, Raissa Uskenbayeva, Young Im Cho, Kabyl Dauren, Les Nurzhan, Maqsat Amangeldi 85 DOI: 10.37943/15LPCU4095 Samat Mukhanov* Master of Technical Sciences, senior-lecturer, Department of Computer Engineering [s.mukhanov@iitu.edu.kz](s.mukhanov@iitu.edu.kz), [orcid.org/0000-0001-8761-4272](orcid.org/0000-0001-8761-4272)[ ](orcid.org/0000-0001-8761-4272)International Information Technology University, Almaty, Kazakhstan Raissa Uskenbayeva Doctor of technical science, professor, Head of Institute of Automation, and Information Technologies [r.k.uskenbayeva@satbayev.university](r.k.uskenbayeva@satbayev.university), [orcid.org/0000-0002-8499-2101](orcid.org/0000-0002-8499-2101)[ ](orcid.org/0000-0002-8499-2101)Satbayev University, Almaty, Kazakhstan Young Im Cho PhD, professor [yicho@gachon.ac.kr](yicho@gachon.ac.kr), [orcid.org/0000-0003-0184-7599](orcid.org/0000-0003-0184-7599) Faculty of Computer Engineering Gachon University, Seoul, South Korea Kabyl Dauren Master student [d_kabyl@kbtu.kz](d_kabyl@kbtu.kz), [orcid.org/0009-0005-4837-8728](orcid.org/0009-0005-4837-8728) Kazakh British Technical University, Almaty, Kazakhstan Les Nurzhan Master student [38530@iitu.edu.kz](38530@iitu.edu.kz), [orcid.org/0009-0008-2909-3606](orcid.org/0009-0008-2909-3606) International Information Technology University, Almaty, Kazakhstan MaqsatAmangeldi Master student [38517@iitu.edu.kz](38517@iitu.edu.kz), [orcid.org/0009-0002-0899-2975](orcid.org/0009-0002-0899-2975) International Information Technology University, Almaty, Kazakhstan GESTURE RECOGNITION OF MACHINE LEARNING AND CONVOLUTIONAL NEURAL NETWORK METHODS FOR KAZAKH SIGN LANGUAGE Abstract: Recently, there has been a growing interest in machine learning and neural networks among the public, largely due to advancements in technology which have led to improved methods of computer recognition of objects, sounds, texts, and other data types. Asa result, human-computer interactions are becoming more natural and comprehensible to the average person. The progress in computer vision has enabled the use of increasingly sophisticated models for object recognition in images and videos, which can also be applied to recognize hand gestures. In this research, popular hand gesture recognition models, such asthe Convolutional Neural Network (CNN), Long Short-Term Memory (LSTM), and Support Vector Machine (SVM) were examined. These models vary in their approaches, processing time, and training data size. The important feature of this research work is the use of various machine learning algorithms and methods such as CNN, LSTM, and SVM. Experiments showed different results when training neural networks for sign language recognition in the Kazakh sign language based on the dactyl alphabet. This article provides a detailed description of each method, their respective purposes, and effectiveness in terms of performance and training. Numerous experimental results were recorded in a table, demonstrating the accuracy of rec Copyright © 2023, Authors. This is an open access article under the Creative Commons CC BY-NC-ND license Received: 31.07.2023 Accepted: 13.09.2023 Published: 30.09.2023 86 Scientific Journal of Astana IT University ISSN (P): 2707-9031 ISSN (E): 2707-904X VOLUME 15, SEPTEMBER 2023 ognizing each gesture. Additionally, specific hand gestures were isolated for testing in front of the camera to recognize the gesture and display the result on the screen. An important feature was the use of mathematical formulas and functions to explain the working principle of the machine learning algorithm, as well as the logical scheme and structure of the LSTM algorithm. Keywords: Hand gesture recognition; neural networks; CNN; LSTM; SVM. Introduction At present, Kazakhstan has a population of over 200,000 individuals who are unable to speak and more than 80,000 who are hearing-impaired. On a global scale,

FAQs

Which hand gesture recognition models are examined in the research?

The research examines CNN, LSTM, and SVM models for hand gesture recognition in Kazakh sign language.

How is the Kazakh sign language dataset prepared for training and testing?

Experiments train the models for recognition in Kazakh sign language based on the dactyl alphabet, and specific gestures are isolated for testing in front of the camera.

What factors are compared across the models?

The models are compared by their approaches, processing time, and training data size, with effectiveness assessed via performance results.

Aug 4, 2026

Upload by Emma Wilson