Hybrid Active Contour Method Combining Local and Differential Image Information for Image Segmentation

In this paper, a hybrid active contour model integrating the local and differential gray intensity information is proposed for inhomogeneous image segmentation. In the energy function of the model, the gray intensity of each pixel within a region is fitted to a local weighted mean. To solve the local minimization problem of above energy, the differential information of the original image, obtained by subtracting the original image gray from a averaging convolution operator result of it, is also integrated in the energy of region. A normalization term is added to the energy and the minimization of the energy is implemented with level set method. Experimental results show the proposed model can obtain improved segmentation result compared to related methods, in both segmentation accuracy and initial contour sensitivity.