A computer vision approach to study surface deformation of materials

Characterization of the deformation of materials across different length scales has continuously attracted enormous attention from the mechanics and materials communities. In this study, the possibility of utilizing a computer vision algorithm to extract deformation information from materials has been explored, which greatly expands the use of computer vision approaches to studying the mechanics of materials and potentially opens new dialogues between the two communities. The computer vision algorithm is first developed and tested on computationally deformed images (% error < 0.035%, L2-norm < 2.5), before evaluating experimentally collected images on speckle painted samples before and after deformation. Moreover, a virtual experiment shows the feasibility of mapping the surface strain of a sample based on its natural pattern with significantly improved accuracy compared to the digital image correlation result obtained from the open-source software Ncorr, which provides new opportunities in experimentation and computer algorithms for studying the deformation mechanics of materials. Validation experiments include evaluating the performance of strain mapping using the computer vision approach in the uniaxial tensile test and three-point bending test, compared with extensometer reading and digital image correlation, respectively.