Analysis Of Feature Extraction Techniques In Different Contrast Enhanced CT Images Of Liver
Main Article Content
Abstract
Feature extraction is an important part of segmentation techniques applied to images. Extraction of various features mean identification of different attributes that characterize an image. This process is quite challenging because of the image resolution and its complexity. In this paper we are trying to detect the cancerous tissues from the liver organ where the extraction of tissue features further requires differentiating between the cancerous and non-cancerous tissue patches. It is important to identity texture features that best describe a healthy and an unhealthy tissue from the digital image. Also, it is necessary to include a good number of texture features for better classification. In this paper, two feature extraction techniques, namely Gray-Level Co-Occurance Matrix (GLCM) and Gray-level run-length matrix (GLRLM) are used for identifying the texture characteristics of tumor in liver organ. These techniques depend on the spatial distribution of intensity values or gray levels in the liver region. The extracted features are then classified using SVM classifier. The accuracy of the model is satisfactory and effective for tumor diagnosis and decision making process for treatment of tumor.