Textile fabric flaw detection using singular value decomposition

This paper proposes a textile fabric defect detection method based on the technique of matrix singular value decomposition (SVD). The matrix SVD extracts orthonormal eigen-vectors from training defect-free images of a fabric. These eigen-vectors carry structure features of the given fabric and are expressed in the format of image. For this fabric, the extracted structure features remain unchanged regardless of image sampling position as long as there is no defect. Thus the extracted structure features usually are used in projection based defect detection methods. Compared to model-based projection fabric defect detection methods, the proposed method only assumes that eigen-vectors are independent to each other. The proposed method is assessed with a number of defective fabric images. The results show that the proposed method achieves a high detection rate. In addition, factors related to such an excellent defect detection performance are also discussed.