The invention relates to an algorithm for detecting glass bottle neck damage and bottle bottom dirt, comprising the following steps: obtaining, filtering and binarizing the pictures of the bottle neck and the bottle bottom; positioning a zone to be processed; calculating the number of disturbance points in the zone; when the number is less than a certain threshold value, judging that no disturbance exists; and otherwise, eliminating the disturbance with a Gravity method and judging whether defects exist again. The algorithm has the characteristics of high speed and high precision and is suitable for the existing glass bottle detection device in China.