Detection of metal surface defects: improved image processing methods for bullet case mouth surface analysis

Detection of metal surface defects is of critical importance for the reliability and safety of components manufactured in manufacturing processes. In particular, the examination of bullet case mouth surfaces requires the detection of small defects that may affect ballistic performance or cause failures. This study proposes a fully automated image processing framework focused exclusively on the detection of circularity deviations in bullet case mouths. The core objective is to quantify structural irregularities and identify deviations from ideal circular geometry. The proposed methodology involves eight stages: image acquisition under controlled lighting, Otsu-based binarization for foreground segmentation, morphological filtering to remove noise and artifacts, and geometric feature extraction via region-based statistics. The methodology continues with a combination of classical and advanced shape analysis tools: Hough Circle Transform is used to detect inner and outer rings of the case mouth, followed by precise centroid deviation analysis to measure concentricity. The framework also incorporates radius difference checks and circular variance computation to assess uniformity of radial symmetry. The proposed system was applied on a dataset consisting of 200 images obtained under controlled illumination and 96.5% classification accuracy was achieved. By focusing on continuous shape metrics and model-free inference, the proposed approach offers a reliable foundation for integrating visual quality control into high-throughput manufacturing pipelines.