Lithium-ion batteries are pervasive in contemporary life, providing power for a vast array of devices, including smartphones and electric vehicles. With the projected sale of millions of electric vehicles globally by 2022 and over a million electric vehicles in Europe alone in the first quarter of 2023, the necessity of securing a sustainable supply of lithium-ion batteries has reached a critical point. As the demand for electric vehicles and renewable energy storage (ESS) systems increases, so too does the necessity to address the shortage of lithium batteries and implement effective recycling and recovery practices. A considerable number of electric vehicle batteries will reach the end of their useful life in the near future, resulting in a significant increase in the number of used batteries. It is of paramount importance to accurately identify the manufacturer and model of cylindrical batteries to ascertain their State of Health (SoH) and guarantee their efficient reuse. This study focuses on the automation of the identification of cylindrical cells through optical character recognition (OCR) and the analysis of the external color of the cell and the anode morphology based on computer vision techniques. This is a novel work in the current limited literature, which aims to bridge the gap between industrialized lithium-ion cell recovery processes and an automated SoH calculation. Accurate battery identification optimizes battery reuse, reduces manufacturing costs and mitigates environmental impact. The results of the work are promising, achieving 90% accuracy in the identification of 18,650 cylindrical cells.