Automated defect detection in medical imaging has become an emerging field in several medical diagnostic applications. Automated detection of tumors in MRI is crucial as it provides information about abnormal tissues that are necessary for treatment. The conventional method for defect detection in magnetic resonance brain images is human inspection. This method is impractical due to the large amount of data. Hence, trusted and automatic classification schemes are essential to preventing the human death rate. So, automated tumor detection methods are being developed to save radiologist time and obtain tested accuracy. MRI brain tumor detection is a complicated task due to the complexity and variability of tumors. In this work, machine learning algorithms are proposed to overcome the drawbacks of traditional classifiers when tumors are detected in brain MRIs using machine learning algorithms. The outcome of the model is to predict whether a tumor is present or not in the image.