This research aims to propose a novel approach to evaluate and minimize the scrap rate in the industrial production of premium food cans with distortion printing. Beyond cost considerations, a critical aspect of modern food can manufacturing is the aesthetic quality of the graphical display. In addition to traditional formability requirements, a waving requirement is defined. Detailed real production conditions are provided and discussed. The material of interest is a double cold-reduced (DR) low-carbon steel sheet and chromium-coated tin-free steel with a thickness of 0.16 mm. These sheets are laminated on both sides with PET film before distortion printing on the exterior. A material parameter identification method is proposed and illustrated to address the challenges in characterizing such a thin sheet. The thickness profile and flange length are key criteria for this identification. Digital image correlation (DIC) and a microscope are used to measure the thickness distribution and flange length. Within the manufacturing system, uncertainties arising from material properties and forming processes can lead to scraps or defects. Finite element analysis (FEA) is adopted for process analysis and validated with experiment. Uncertainty propagation via metamodeling, employing radial basis function (RBF) neural networks, is adopted for the scrap rate evaluation. The study concludes with process optimization recommendations to reduce scrap.