Original Article

Photometric stereo for tool wear monitoring: addressing challenges of specular surfaces in sheet metal forming

¹ Institute for Production Engineering and Forming Machines - PTU, Technical University Darmstadt, 64287 Darmstadt, Germany
² Institute for Computer Graphics Research IGD, 64283 Darmstadt, Germany
³ Technical University Darmstadt, Karolinenplatz 5, 64287 Darmstadt, Germany
⁴ Computer Vision, Imaging and Data Analysis Lab, Hochschule Darmstadt, 64283 Darmstadt, Germany
⁵ ACIDA Lab, Technische Hochschule Würzburg-Schweinfurt, 97421 Schweinfurt, Germany

^* e-mail: This email address is being protected from spambots. You need JavaScript enabled to view it.

Received: 4 August 2025
Accepted: 29 October 2025

Abstract

The progressive forming of sheet metal through stages such as blanking, deep-drawing and ironing is an economically attractive route to complex components. Wear control is decisive for product quality, as it prevents defects and minimizes scrap. Optical sensors are increasingly supplementing conventional monitoring, thanks to ongoing digitization and continuous improvement of availability. This paper introduces a modular, adaptive, camera-based measurement stage that captures component geometry and delivers cause-specific feedback on tool wear, enabling anomalies to be linked to individual forming steps. The system employs photometric stereo analysis: several images are taken under different illumination angles. A normal map is reconstructed, and pixel-wise brightness differences reveal the surface topology. Deviations from target geometry are then localized by comparing actual and nominal data. A key contribution of the present work is the systematic investigation of highly reflective workpiece materials-in contrast to previous studies based on CR DC04 steel, whose matte finish approximates Lambertian behavior. Specular surfaces, such as the ETSR TS245, distort the incident light field, violating this assumption and reducing detection accuracy. Therefore, it is necessary to analyze how variations in reflectivity and surface finishes influence the photometric stereo pipeline. In addition, calibration and illumination strategies are proposed that restore reliable anomaly detection even for glossy substrates. This study lays the groundwork for efficient, robust and adaptive manufacturing systems by providing process insights without disrupting production and addressing the challenges posed by non-Lambertian reflections. It advances intelligent forming technology across varying materials in manufacturing processes.