Approach to efficient level-set model with shape priors for images segmentation is considered. The use of edge based level-set model in combination with principal component analysis (PCA) based shape priors for image segmentation is investigated. Shape priors considered as a tool to cope with proper segmentation of overlapping or partially visible objects on input image. It is argued that in some cases consequent optimization of different groups of parameters can be advantageous in comparison to simultaneous optimization of all parameters. The approach was applied for segmentation of fractographic images obtained by scanning electron microscope (SEM). Experimental results for image segmentation using level-set model with shape priors are presented.