Selective Image segmentation driven by region, edge and saliency functions

Abstract In this paper, we propose a novel level set method based on selective homogeneous and inhomogeneous object segmentationdriven by an image region, edge and saliency functions. Initially, we adapt an intensity edge term based on the zero crossingfeature detector (ZCD), which is used to highlight significant edges of an image. Secondly, a saliency function is formulatedto detect salient regions from an image. We have also included a globally tuned region based SPF (signed pressure force)term to move contour away and capture homogeneous regions. ZCD, saliency and global SPF are jointly incorporated withsome scaled value for the level set evolution to develop an effective image segmentation model. Moreover, proposed method iscapable to perform selective object segmentation, which enables us to choose any single or multiple objects inside an image.Saliency function and ZCD detector are considered feature enhancement tools, which are used to get important features of animage, so this method has a solid capacity to segment nature images (homogeneous or inhomogeneous) precisely. Finally, theadaption of the Gaussian kernel removes the need of any penalization term for level set reinitialization. Experimental resultswill exhibit the efficiency of the proposed method.