Sonar image segmentation using snake models based on cellular neural network

Abstract

In order to solve the problem of deformation and blurred edge in sonar image segmentation, a snake model based on the cellular neural network (CNN) architecture is presented. The approach is generated in snake models which evolve pixel by pixel from their initial shapes and locations until delimiting the objects of interest. The model deformation is guided by external information from the image under consideration which attracts them towards the target characteristics and by internal forces which try to maintain the smoothness of the contour curve. As the amount of deformation within a class can be controlled, the CNN-based snake model can be applied to a wide range of applications. We have used the proposed snake model to segment sonar images. The results show that this algorithm is efficient, precise and very immune to image deformation and noise when compared to results obtained from several other snake model-based methods.