The thesis presents a new method of brain tumor detection and localization by using image segmentation and convolution neural network. In order to ensure the quality of the medical images, there are several image preprocessing techniques applied, which include the procedure of removing the noise and non-brain tissue and enhancing the contrast. By using active contour for segmentation, the tumor area is separated from the image as its energy appears different in pixels and the feature extraction reveals the mathematical properties of the tumor.After the tumor localization, the target regions are imported into to the CNN and CNN classifies them into categories based on the training results from the learning procedure. This thesis uses the 4-fold cross validation for result testing. With over 80% accuracy, the CNN shows great potential in tumor detection. In addition, this thesis covers the section of how parameter settings influencing the CNN performance.