Micro-crack inspection in heterogeneously textured solar wafers using anisotropic diffusion

This paper proposes a machine vision scheme for detecting micro-crack defects in solar wafer manufacturing. The surface of a polycrystalline silicon wafer shows heterogeneous textures, and the shape of a micro-crack is similar to the multi-grain background. They make the automated visual inspection task extremely difficult.The low gray-level and high gradient are two main characteristics of a micro-crack in the sensed image with front-light illumination. An anisotropic diffusion scheme is proposed to detect the subtle defects. The proposed diffusion model takes both gray-level and gradient as features to adjust the diffusion coefficients. It acts as an adaptive smoothing process. Only the pixels with both low gray-levels and high gradients will generate high diffusion coefficients. It then smoothes the suspected defect region and preserves the original gray-levels of the faultless background. By subtracting the diffused image from the original image, the micro-crack can be distinctly enhanced in the difference image. A simple binary thresholding, followed by morphological operations, can then easily segment the micro-crack. The proposed method has shown its effectiveness and efficiency for a test set of more than 100 wafer images. It has also achieved a fast computation of 0.09 s for a 640 × 480 image.