Improved Spatial Gray Level Dependence Matrices for Texture Analysis

Olfa Ben Sassi
2012 International Journal of Computer Science & Information Technology (IJCSIT)  
In this paper, we will focus on the Spatial Gray Level Dependence Matrices SGLDM to extract the Haralick's texture features of the ultrasound breast lesions. This method relies on the manual selection of the region of interest, which results in the dependence of parameters values on the extracted region. For that reason, an improved Spatial Gray Level Dependence Matrices based on the segmented masses using active contour was applied. This method outperforms the existing SGLDM method because it
more » ... method because it allows establishing a well determined threshold for the classification of lesions.
doi:10.5121/ijcsit.2012.4615 fatcat:g3s47sikmzd7fcwfts4f6cg5y4