A brain tumour develops when cells in the brain multiply abnormally and out of control. The possibility of fatality makes this growth dangerous. The brain regulates everything from memory to vision to emotions. Recognizing these tumours is a challenging and complex task due to their location, size, and shape. There have been a number of successful attempts to enhance detection. However, the current level of precision is insufficient. This study details a method with a high likelihood of success in identifying brain cancers. The approach is implemented in Python LAB by use of an image segmentation technique and a classifier. One such classifier is the Random Forest Algorithm. The Principal Component Analysis (PCA) and the Discrete Wavelet Transform (DWT) are also employed. The created method is put to the test using a dataset available on the Kaggle platform. The acquired results were approximately 97.68% accurate. A confusion matrix and a comparison of the developed method to other research in the literature are included in the investigation to facilitate the implementation of the proposed strategy in image testing. This Research shows that the offered system is superior to others in terms of detection rate, false positive rate, and recall. Results from this study showed that the developed method was effective at detecting brain tumours due to its high levels of accuracy, precision, and recall. According to the proposed strategy, it is essential to provide professionals who diagnose brain tumours with access to such technology.