Brain tumors significantly impact global health, posing serious challenges for accurate diagnosis due to their diverse nature and complex characteristics. Effective diagnosis and classification are essential for selecting the best treatment strategies and forecasting patient outcomes. Presently, histopathological examination of biopsy samples is the established method for brain tumor identification and classification. However, this method is invasive, time-consuming, and susceptible to human error. To address these limitations, we required a fully automated approach to classify brain tumors. Recent advancements in deep learning, particularly convolutional neural networks (CNNs), have shown promise in enhancing the accuracy and efficiency of brain tumor classification from magnetic resonance imaging (MRI) scans. In response, we developed a model integrating machine learning (ML) and deep learning (DL) techniques. The process started by splitting the data into training, testing, and validation sets before resizing the images and then performing cropping to enhance model quality and efficiency. Further, the relevant texture features are extracted using a modified Visual Geometry Group (VGG) architecture. These features were fed to various supervised ML models, including support vector machine (SVM), k-nearest neighbors (KNN), logistic regression (LR), stochastic gradient descent (SGD), random forest (RF), and AdaBoost, with GridSearchCV-based hyperparameter tuning. The evaluation of the model’s performance was conducted using several key metrics, including accuracy, precision, recall, F1-score, and specificity. The experimental results demonstrate that the presented approach offers a robust, automated solution for brain tumor classification, achieving the highest accuracy of 94.02% with VGG19 and 96.30% with VGG16. The proposed model can significantly assist healthcare professionals in early detection of tumors and improving diagnosis accuracy.