The COVID-19 pandemic has underscored the critical need for accurate and efficient diagnostic tools. Traditional chest X-ray analysis for detecting COVID-19 is challenging due to the subtle and varied nature of disease manifestations. This study proposes a machine learning approach to classify normal and COVID-19 chest X-ray images by leveraging texture features extracted using Local Binary Pattern (LBP) and Gray Level Co-occurrence Matrix (GLCM) methods. The methodology involved acquiring 2000 chest X-ray images (1000 normal and 1000 COVID-19) from public libraries, followed by pre-processing and feature extraction. The extracted LBP and GLCM features were combined to form a comprehensive dataset, which was then used to train and evaluate Support Vector Machine (SVM) and Artificial Neural Network (ANN) classifiers. The results demonstrated that the fusion of LBP and GLCM features significantly improved classification performance, with the highest accuracy of 91% achieved by the ANN model. This study concludes that integrating diverse texture features enhances the diagnostic accuracy of AI-driven systems, providing a robust and reliable tool for COVID-19 detection. These findings contribute to the development of advanced diagnostic solutions in the medical field, aiding in the ongoing battle against the pandemic.