Level set methods have been widely used to implement active contours for image segmentation application due to their good boundary detection accuracy. However, there are several disadvantages in the weighted level set evolution, since the edge stopping function depends on the image gradient, only objects with edges defined by gradient can be segmented. Another disadvantage is that in practice, the edge-stopping function is never exactly zero at the edges, and so the curve may eventually pass through object boundaries. This proposed method based on weighted p(x) Dirichlet integral, an external energy, and a level set regularization term. Due to the good properties of the weighted p(x)-Dirichlet integral term, it extracts the weak boundaries in noisy and intensity in homogeneity images. An added benefit of the proposed method is that the level set function can be initialized to a constant function. This implies that the model is free of manual initialization. The proposed methods leads to more accurate boundary detection results than the state-of-the –art based method
