Quantifying the Defect Visibility in Digital Images by Proper Color Space Selection

The selection of color space is one of the determinants of quantifying the visibility of the defects like scratches, spots, edge defects etc in glass sheets. We propose an evaluation system that assigns each color space a corresponding level according to the extent of visibility of the defect that objectively agrees with human visual perception. By “objective,” we mean that the evaluation corresponds, on average, with the assessment of a group of inspectors. The basic idea is to use the human visual perception to evaluate defects. In the process, the Visibility–test is done to evaluate the level of defect visibility in terms of a five point Likert scale. The conversion time from RGB color space to the other is also considered to evaluate the maximum visibility of the defect in each color space used.