Automatic Detection of Dispersed Defects in Resin Eyeglass Based on Machine Vision Technology

Wei Ding,Jianfeng Zhu,Qingguo Wang

doi:10.1109/access.2020.2978001

Abstract

This paper is concerned with detection of dispersed defects in the resin eyeglass. At present, manual detection is always used in industry, which inevitably causes impairing eyes and a high rate of false-negative detection. Statistics show that its average accuracy and the average detection time are about 85% and 10s, respectively. We for the first time propose an automatic approach to detection of dispersed defects in resin eyeglass, based on the machine vision technology. It is observed that the refractivity of the normal and the defective regions of an eyeglass are different, and thus the reflection image is also collected in our system in addition to the normal transmission image. Such an optical imaging system is modelled and its analysis shows the gray-scale gradient difference between the normal and defective regions in the acquired image is dramatically enhanced under the illumination of a point light source with our designed system. An image processing algorithm is then developed to reveal the above difference and detect dispersed defects in resin eyeglasses. Our simulation study verifies the proposed approach. Further, its experimental evaluation was carried out and the result was consistent with the simulation one, showing that its detection accuracy and the average detection time were 97.50% and 0.636s, respectively, which meet the requirements for online detection of dispersed defects.

Highlights

It is predicted in [1] that by 2050 there will be 4758 million people with myopia and 938 million people with high myopia, accounting for 49.8% and 9.8% of the population in the world, respectively
The experimental results show that with the designed image-processing algorithm used, the detection accuracy and the average detection time are 97.50% and 0.636s, respectively, both of which satisfy the requirements for online detection of dispersed defects
The current methods to detect dispersed defects in the resin eyeglass rely on manual detection, which inevitably impairs eyes and leads to frequent false-negative detection

Summary

INTRODUCTION

It is predicted in [1] that by 2050 there will be 4758 million people with myopia and 938 million people with high myopia, accounting for 49.8% and 9.8% of the population in the world, respectively. W. Ding et al.: Automatic Detection of Dispersed Defects in Resin Eyeglass Based on Machine Vision Technology urgently needed. To the best knowledge of the authors, until now, no research on automatic detection methods for dispersed defects in resin eyeglass has been carried out. Machine vision is an effective technology to support online defect detection [4]–[6], and the existing relevant work focuses mainly on detection of defects on optical components made of glass and resin. The simulation results on the imaging system show that the contrast between the normal and defective regions is clearly presented under the illumination of a point light source: the density of rays in the dispersed defect region is 1.13%, and that in the normal region is 6.64%.

THE PROPOSED APPROACH

EXPERIMENTAL STUDY

Findings

CONCLUSION