Image segmentation via brittle fracture mechanics

Brittle material like ceramic and rock has the nature that it is hard to crack, but if it is to crack it will crack into not dangling pieces, but separate pieces whose boundaries are contours that link up positions of strong stress in a continuous and often smooth fashion. Image segmentation desires similar results: it is to partition the image so that each partition corresponds to a separate surface or object in the imaged scene, whose boundaries are continuous and often smooth contours with a dense concentration of large intensity gradients. This work explores the adaptation of brittle fracture mechanics model toward image segmentation. An image is regarded as a plate experiencing brittle fracture when external forces arc exerted on it according to intensity gradient distribution in the image. Stress concentrations due to the external forces and its change over time due to changing crack distribution are what determine the development of cracks. Real image results indicate that the model is promising.