Brain tumor classification using mixed method approach

In this paper, we propose an effective mixed method approach for classification of brain tumor tissues. Here proposed system will be using Genetic Algorithm for feature Extraction and Support Vector machine for classification. These features are compared with stored features. Feature extraction is a method used to capture visual content of the image. The feature extraction is the method to signify raw image in its concentrated form to facilitate decision making such as pattern classification. The choice of features, which compose a big difficulty in classification techniques, is solved by using Genetic Algorithm. These features along with Support Vector Machine will be used to classify that tumor is normal and abnormal. If the tumor is get detected then by detecting the mean, mod, median of the tumor region we will classify this tumor tissues in gliomas, miningiomas, pitutatory, nerve sheath tumor etc. The performance of the algorithm is evaluated on a series of brain tumor images.