Alzheimer’s disease is the most dreadful. Despite the various Alzheimer’s treatments available nowadays, the survival rate of Alzheimer’s patients is very much low. Detection of Alzheimer’s disease in an earlier stage is one of the most important things to reduce the death rate. Magnetic Resonance Imaging (MRI) is an important tool in medical informatics and clinical diagnosis. This MRI image helps to diagnose and detect Alzheimer’s disease at advanced stages. There are several approaches implemented to discover Alzheimer’s by MRI data. Features are extracted discriminately and combinations of different classification techniques for classification is implemented in the proposed work. In this paper, the curvelet-based transform technique is utilized for extracting the features. The AdaBoost classifier is utilized for combining multiple weak classifiers into one strong classifier to improve the accuracy of the result. To improve the efficiency of the result, AdaBoost classifier with SVM was used to obtain better results than existing ones. The proposed model with 95.66% accuracy predicts the AD from the brain MRI images at an earlier stage. This accuracy value is far better than other classifiers like Decision Tree and Random Forest. © The Editor(s) (if applicable) and The Author(s), under exclusive license to Springer Nature Switzerland AG 2021.