A graph-based two-stage classification network for mobile screen defect inspection

Chaofan ZHOU, Meiqin LIU, Senlin ZHANG, Ping WEI, Badong CHEN

PDF(920 KB)
PDF(920 KB)
Front. Inform. Technol. Electron. Eng ›› 2023, Vol. 24 ›› Issue (2) : 203-216. DOI: 10.1631/FITEE.2200524
Orginal Article
Orginal Article

A graph-based two-stage classification network for mobile screen defect inspection

Author information +
History +

Abstract

Defect inspection, also known as defect detection, is significant in mobile screen quality control. There are some challenging issues brought by the characteristics of screen defects, including the following: (1) the problem of interclass similarity and intraclass variation, (2) the difficulty in distinguishing low contrast, tiny-sized, or incomplete defects, and (3) the modeling of category dependencies for multi-label images. To solve these problems, a graph reasoning module, stacked on a classification module, is proposed to expand the feature dimension and improve low-quality image features by exploiting category-wise dependency, image-wise relations, and interactions between them. To further improve the classification performance, the classifier of the classification module is redesigned as a cosine similarity function. With the help of contrastive learning, the classification module can better initialize the category-wise graph of the reasoning module. Experiments on the mobile screen defect dataset show that our two-stage network achieves the following best performances: 97.7% accuracy and 97.3% F-measure. This proves that the proposed approach is effective in industrial applications.

Keywords

Graph-based methods / Multi-label classification / Mobile screen defects / Neural networks

Cite this article

Download citation ▾
Chaofan ZHOU, Meiqin LIU, Senlin ZHANG, Ping WEI, Badong CHEN. A graph-based two-stage classification network for mobile screen defect inspection. Front. Inform. Technol. Electron. Eng, 2023, 24(2): 203‒216 https://doi.org/10.1631/FITEE.2200524

RIGHTS & PERMISSIONS

2023 Zhejiang University Press
PDF(920 KB)

Accesses

Citations

Detail

Sections
Recommended

/