A mobile phone cover glass defect detection and classification method

Abstract

A mobile phone cover glass defect detection and classification method uses two different modes of structured light, black and white periodic stripes and sinusoidal stripes, to irradiate the surface of the mobile phone cover glass, and uses an industrial camera to capture a sequence of cover glass images reflecting the structured light. The enhanced picture of the mobile phone cover glass based on the image sequence synthesis of reflected black and white periodic stripe structured light can stably highlight all the defects with diffuse reflection, and is used for defect detection and classification recognition. The phase map based on the image sequence analysis of reflected sinusoidal fringe structured light is sensitive to the transformation of the concave-convexity of the cover glass surface, and is used for the identification of surface damage defects. Starting with measurement, the input of defect information is strengthened, the accuracy and stability of defect detection and classification of mobile phone cover glass are improved, and the problem of impracticality of existing methods is solved.

Description

technical field [0001] The invention belongs to the technical field of detection and relates to defect detection, in particular to a defect detection and classification method for mobile phone cover glass. Background technique [0002] With the advent of the mobile Internet era, smartphones are becoming more and more popular around the world. As an important component of smart phones, mobile phone cover glass has a huge market demand. The manufacturing process of mobile phone cover glass includes: opening the original glass, engraving the shape and inner hole, chamfering, polishing, hardening, silk screen printing, oiling and other steps. [0003] Therefore, defective products will inevitably appear in the production process, including scratches, pits, glass surface dirt, ink spots and other defects caused by slotting, chamfering, and polishing. At present, most mobile phone cover glass manufacturers use manual defect detection in the production process, and quality inspec...

AI Technical Summary

Problems solved by technology

[0010] Although the image acquisition scheme based on sinusoidal fringe structured light has a strong ability to highlight surface damage defects, it has been proven that this method is not capable of detecting non-surface damage defects such as watermarks, fingerprints, and slight transparent stains.

Images