Glass container surface defect detection method based on visual inspection

Abstract

The invention discloses a glass bottle surface defect detection method based on visual detection, relates to the technical field of surface defect detection, and aims to solve the problem of inaccurate glass bottle surface detection. According to the method, information combination is carried out on the types, the number and the severity of the defects, weight distribution is carried out, then comprehensive scoring is carried out, various factors can be comprehensively considered in the mechanism, a more comprehensive and accurate scoring result is obtained, and defect boundaries are extracted through a contour detection method. According to the method, the defect position can be accurately positioned, the defect boundary can be accurately extracted, a reliable data basis is provided for subsequent analysis and processing, defect candidate areas are generated through a threshold segmentation method, screening is carried out through size filtering, shape matching, texture analysis and other methods, candidate areas without defects can be eliminated, and the defect detection accuracy is improved. And an image of the defective glass bottle can is accurately obtained.

Images