Fabric defect detection based on adaptive local binary patterns

Adaptive local binary patterns method is proposed in this paper, on which an effective fabric defect detection algorithm is designed. ALBP method selects the frequently occurred patterns to construct the main pattern set, which avoids using the same pattern set to describe different texture structures in uniform local binary patterns method. The features of free defect image are extracted according to the set and the threshold is confirmed. The image to be tested is divided into same size detection windows from which ALBP features are also extracted. Defective window is found through comparing ALBP features with threshold. The experiment exhibited the detection effect of the proposed method is comparatively better than traditional LBP method from human visual aspect and detection accuracy.