Brain MR Image segmentation is a very important and challenging task that is needed for the purpose of diagnosing brain tumors and other neurological diseases.Medical imaging plays a central role in the diagnosis of brain tumors. Early imaging methods invasive and sometimes dangerous, such as cerebral angiography and Pneumoencephalography have been abandoned in favor of non-invasive, high-resolution techniques, especially Magnetic Resonance Imaging (MRI) and Computed Tomography (CT) scans. Deep Neural Network (DNN) is used to show superior results in both image and speech applications. Brain tumors have different characteristics such as size, shape, location and image intensities. They may deform neighbouring structures and if there is edema with the tumor, intensity properties of the nearby region change. To analyze the brain tumor and edema by segmenting the MR Images using wavelets and deep neural networks. Each tissue is appeared clearly (tumor, edema, CSF, WM, and GM).Deep Neural Networks (DNNs) are often successful in problems needing to extract information from complex, high-dimensional inputs, for which useful features are not obvious to design. In the proposed method, first the input image is converted into gray level and then it uses the edge detection. After the edge detection, segmentation is applied, and then applies the CNN and Harr transform in-order to get the desired output.