INTERNATIONAL JOURNAL OF SCIENTIFIC DEVELOPMENT AND RESEARCH International Peer Reviewed & Refereed Journals, Open Access Journal ISSN Approved Journal No: 2455-2631 | Impact factor: 8.15 | ESTD Year: 2016
open access , Peer-reviewed, and Refereed Journals, Impact factor 8.15
In past decade, Tumor is one of the dangerous diseases in the world causing death of many people. MRI is one of the imaging technique which is widely used for tumor detection and classification. Also there are various methods for detection of brain tumor other than LIPC . Convolution neural network(CNN) is used in convolving a signal or an image with kernels to obtain feature maps. The image processing techniques such as equalized image, feature extraction and histogram equalization have been developed for extraction of the tumor in the MRI images of the cancer affected patients. Support Vector Machine(SVM) algorithm that works on structural risk minimization to classify the images. The SVM algorithm is applied to MRI images for the tumor extraction and a Simulink model is developed for the tumor classification function. Typical structure for this proposed system has four steps. In The initial stage is pre-processing using Gaussian filter. Thresholding has been employed in the second steps for segmentation. The third step is to check the feature extraction of MRI images. The fourth steps is classification that classified the tumor of MRI images using local independent projection based classification.(LIPC).
Keywords:
MRI images, Feature Extraction, LIPC
Cite Article:
"Brain Tumor Detection Using Local Independent Projection Based Classification(LIPC)", International Journal of Science & Engineering Development Research (www.ijsdr.org), ISSN:2455-2631, Vol.4, Issue 3, page no.50 - 52, March-2019, Available :http://www.ijsdr.org/papers/IJSDR1903011.pdf
Downloads:
000336256
Publication Details:
Published Paper ID: IJSDR1903011
Registration ID:190170
Published In: Volume 4 Issue 3, March-2019
DOI (Digital Object Identifier):
Page No: 50 - 52
Publisher: IJSDR | www.ijsdr.org
ISSN Number: 2455-2631
Facebook Twitter Instagram LinkedIn