Breast cancer, a leading cause of mortality among women globally, requires innovative approaches for early detection. This study presents a method using machine learning on histopathological images from the BreakHis dataset to distinguish between benign and malignant cases. Unlike previous studies, this model integrates advanced feature extraction techniques, including Gray-Level Co-occurrence Matrix (GLCM) and histogram analysis, offering a deeper insight into textural variations. The results show promising accuracy rates of 85.05%, 88.49%, 82.60%, and 86% for magnifications of 40 \(\times \) , 100 \(\times \) , 200 \(\times \) , and 400 \(\times \) , respectively, demonstrating the effectiveness of the proposed approach.