Brain Tumor Classification and Segmentation Based on Morphological Operations using Image Processing Techniques
Kotha Tirumala Naga Sriveni1, Madala Vani Pujitha2

1Kotha Tirumala Naga Sriveni*, Dept of CSE, Velagapudi Rama Krishna Siddhartha Engineering College, Vijayawada, India. 
2Madala Vani Pujitha, Computer Science and Engineering Department,VelagapudiRamaKrishnaSiddharthaEngineeringCollege,Vijay awada, India.
Manuscript received on April 04, 2020. | Revised Manuscript received on April 11, 2020. | Manuscript published on April 30, 2020. | PP: 2384-2388 | Volume-9 Issue-4, April 2020. | Retrieval Number: D8319049420/2020©BEIESP | DOI: 10.35940/ijeat.D8319.049420
Open Access | Ethics and Policies | Cite | Mendeley
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC BY-NC-ND license (

Abstract: : Brain Tumour is the solitary cause for the assassination of many individuals. A brain tumour is an accretion or widening of isolated cells in your brain. It can be identified by several tests like MRI (Magnetic Resonance Imaging), CT (Computer Tomography) scan along with several tests like biopsy, spinal tap etc. Classification and Segmentation activity take part a significant role in interpretation of brain tumours. In this paper the images should be taken in the form of jpeg format. The images are processed using data mining and machine learning classification methods. Previous research studies are intended as long as identifying brain tumours using dissimilar classification and segmentation approaches. The initiated system consists of certain process for recognition of the tumour. The first step is about Pre-processing and the next is about segmentation, Feature extraction is the third step in this process and Classification is used to detect the tumour. Morphological Operations are performed in this process based on the tumour size, shape and colour. Neural Network is used for classification along with -Support Vector Machine (SVM) classifiers are worn for structured recognition. Due to this we can reduce the inappropriate or false diagnosis error rate of brain tumour identification for the patients and also, we can get faster and accurate results.
Keywords: Brain Tumor, Computer Tomography, Diagnosis, Magnetic Resonance Imaging, Neural Network.