WoodDefect Detection Dataset for Automated Visual Inspection in wood Processing

Dataset Description: WoodDefect DetectionDomain: Automated visual inspection in hardwood processingTask: Multi-class defect detection with bounding-box labelsOrigin and acquisitionThe images were collected by GoldenY through a high-resolution industrial camera under controlled diffuse LED illumination in a European sawmill.All data were taken from the planed surface of kiln-dried European beech (Fagus sylvatica) boards with thickness 26–50 mm. No magnification filters or digital zoom were applied, guaranteeing a native pixel resolution of ≈ 0.08 mm px⁻¹ on the wood surface.Volume and splitsTotal annotated images: 3 785.Current partitioning:– Training: 3105 images (82 %)– Validation: 680 images (18 %)The split is stratified so that the global defect-class distribution is preserved within each subset.