Analysis of Feature Extraction Technique LBP and Classification Model SVM for CECT Images

Extraction of various features from an image means identification of different attributes that characterize an image. This process is quite challenging because of the image resolution and its complexity. Medical field has been widely using image processing techniques for detection and diagnosis of diseases. Here we are trying to detect the cancerous tissues in the liver organ where the extraction of tissue features further requires differentiating between the cancerous and non-cancerous tissue patches. Also, it is necessary to achieve simpler computational complexity for an algorithm. In this paper, local binary pattern technique is used for identifying the texture characteristics of tumor in liver organ. This technique is a local descriptor of an image based on its neighborhood for any given pixel. 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.