This study addresses the challenge of monitoring oxide layer formation in 1045 steel, a critical issue affecting mechanical properties and phase stability during high-temperature processes (900 °C). To tackle this, an image processing algorithm was developed to detect and segment regions of interest (ROIs) in oxidized steel surfaces, utilizing infrared thermography as a non-contact, real-time measurement technique. Controlled heating experiments ensured standardized data acquisition, and the algorithm demonstrated exceptional accuracy with performance metrics such as 96% accuracy and a Dice coefficient of 96.15%. These results underscore the algorithm's capability to monitor oxide scale formation, directly impacting surface quality, thermal uniformity, and material integrity. The integration of thermography with machine learning techniques enhances steel manufacturing processes by enabling precise interventions, reducing material losses, and improving product quality. This work highlights the potential of advanced monitoring systems to address challenges in industrial steel production and contribute to the sustainability of advanced steel materials.