Global threshold and region-based active contour model for accurate image segmentation

In this contribution, we develop a novel global threshold-based active contour model. This model deploys a new edge-stopping function to control the direction of the evolution and to stop the evolving contour at weak or blurred edges. An implementation of the model requires the use of selective binary and Gaussian filtering regularized level set (SBGFRLS) method. The method uses either a selective local or global segmentation property. It penalizes the level set function to force it to become a binary function. This procedure is followed by using a regularisation Gaussian. The Gaussian filters smooth the level set function and stabilises the evolution process. One of the merits of our proposed model stems from the ability to initialise the contour anywhere inside the image to extract object boundaries. The proposed method is found to perform well, notably when the intensities inside and outside the object are homogenous. Our method is applied with satisfactory results on various types of images, including synthetic, medical and Arabic-characters images.