Open AccessTexture Characterization and Classification to Detect Brain Tumor
Author(s) -
N. Kavitha,
Satya Ganti,
Kirti Rani,
K. Mani Kumari,
B. Bhagyasree
Publication year - 2020
Publication title -
international journal of innovative technology and exploring engineering
Language(s) - English
Resource type - Journals
ISSN - 2278-3075
DOI - 10.35940/ijitee.e2470.039520
Subject(s) - artificial intelligence , pattern recognition (psychology) , computer science , support vector machine , segmentation , classifier (uml) , texture (cosmology) , image texture , brain tumor , feature extraction , computer vision , image segmentation , image processing , image (mathematics) , pathology , medicine
In the field of medical sciences, brain tumor detection has immense significance. Extraction of peculiar tumor portion along with certain features is possible with the use of methods that come under image processing. In the recent years techniques like segmentation and morphological have been undertaken to detect the set of unusual cells that grow in the brain which might be malignant or benign. This paper deals with characterization of texture to obtain Haralick features, with texture being the principle attribute of an image and finds lot of application in image processing. This involves the use of SVM classifier in the algorithm to classify texture in order to detect brain tumor. It has been tested for 70 images and statistical parameters have been calculated and the obtained accuracy is 97.1%, precision is 98.4% and sensitivity is 98%.