Magnetic Resonance Imaging (MRI) is a diagnostic technique that utilizes radio waves and a strong magnetic field to produce detailed images of the body’s tissues and organs. It is commonly employed for detecting brain tumors, which are abnormal masses of cells that grow and multiply uncontrollably. These tumors can arise from various cell types found in the brain, such as glial cells, neurons, blood vessels, or lymphatic tissue, or they can metastasize from cancers originating in other parts of the body. Tumors are typically categorized as either malignant (cancerous) or benign (non-cancerous). Detecting and identifying brain tumors through MRI are a crucial yet labor-intensive task that requires significant effort from medical professionals. This paper proposes an automated approach for brain tumor classification and detection using MRI segmentation (K-means). The methodology involves multiple steps, including preprocessing, filtering, feature extraction using wavelet transforms, segmentation, and classification. The preprocessing stage employs median filtering to reduce noise, followed by Discrete Wavelet Transform (DWT) for extracting GLCM features, and clustering segmentation to localize the tumor. Finally, experimental results are provided to assess the performance and accuracy of the proposed algorithm.