Detection of regions of interest's in mammograms by using local binary pattern, dynamic k-means algorithm and gray level co-occurrence matrix

Abstract

This paper presents a method for the detection of the regions of interest's (ROIs) in mammograms by using dynamic k-means clustering algorithm. In this approach, a method has been developed to determine the initialization number of clusters in mammograms by using a data mining algorithm based on the Local Binary Pattern (LBP) and co-occurrence matrix technique (GLCM). Our method consists of three phases: firstly preprocessing images by using Thresholding and filtering methods; secondly determining the initialization number of clusters in mammography images; thirdly detecting of regions of interest's (ROIs) in mammography images. The proposed method was tested using data from Mini-MIAS (Mammogram Image Analysis Society, UK) database, consisting of 322 mammograms. The results from the tests confirm the effectiveness of the proposed method the determination number of clusters and detected of Regions of interest's (ROIs) in mammography images.