The invention discloses a solar
silicon wafer visual detection method, and particularly relates to the technical field of
silicon wafer detection. The method comprises the following steps: acquiring optical images of different incident angles, synchronously acquiring
infrared transmission images, performing normalization
processing,
edge enhancement filtering and self-adaptive threshold segmentation on the acquired multi-angle images, extracting suspected crack areas, and respectively calculating a gray gradient change rate and a stress abnormal degree, so as to obtain a suspected crack area; calculating a crack credibility
score according to the gray gradient change rate and the stress abnormal degree through a weighted scoring method, and comparing the crack credibility
score with a preset crack
detection threshold value to distinguish real hidden cracks and stress pseudo defects; if the credibility
score is lower than the threshold value, secondary sampling is carried out by adjusting the
illumination angle, and the judgment result is further optimized; according to the method, the
false rejection rate caused by lattice stress pseudo defect misjudgment is effectively reduced, meanwhile, missing detection of real subfissures is avoided, and the accuracy, stability and production yield of
silicon wafer defect detection are improved, so that the long-term reliability of a photovoltaic module is enhanced.