DEFECT INSPECTION OF PATTERNED TFT-LCD PANELS USING A FAST SUB-IMAGE BASED SVD

Thin Film Transistor Liquid Crystal Displays (TFT-LCDs) have become increasingly attractive and popular as display devices. In this paper, we propose a machine vision approach for automatic inspection of micro defects in patterned TFT-LCD surfaces. The proposed method is based on a global image reconstruction scheme using singular value decomposition (SVD) that involves orthogonal bases. A partition procedure, which separates the input image into non-overlapping sub-images, is utilized to reduce the computation time of SVD. Taking the pixel image as a matrix, the singular values on the decomposed diagonal matrix represent different degrees of information from the TFT-LCD image. By selecting the dominant singular values that represent the repetitive orthogonal-line texture of the TFT-LCD surface and reconstructing the matrix by excluding the dominant singular values, the reconstructed image effectively removes the background texture and distinctly preserves anomalies. In the experiments, we have evaluated a variety of TFT-LCD micro defects including pinholes, scratches, particles and fingerprints at different image resolutions. The experimental results reveal that the proposed method is effective and efficient for micro defects inspection of TFT-LCD panels.