CLASSIFICATION OF TUMOR FROM MRI IMAGES USING GABOR PATTERN
G. Thamarai Selvi, Karthik Duraisamy, K. S. Rangasamy · 2014
Recognizing automatically the medical images is very tedious in the field of medical image processing. Medical images acquired from different modalities such as Computed Tomography (CT), Magnetic Resonance Imaging (MRI), functional Positron Emission Tomography (fPET), Ultrasonograpy, etc are used for the diagnosis purpose. The main complex problem in the medical field is the classification of the brain tumor images. The misclassification of MRI images such as normal or abnormal images occurs due to the human interpretation. In our research work, we extract the brain tumor from the MRI images using the Non - Local Gabor XOR pattern (NLGXP). The extracted feature is applied to a Feed Forward Neural Network (FFNN) which gives high accuracy.