English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

The presence of any type of defect on the glass screen of smart devices has agreat impact on their quality. We present a robust semi-supervised learningframework for intelligent micro-scaled localization and classification ofdefects on a 16K pixel image of smartphone glass. Our model features theefficient recognition and labeling of three types of defects: scratches, lightleakage due to cracks, and pits. Our method also differentiates between thedefects and light reflections due to dust particles and sensor regions, whichare classified as non-defect areas. We use a partially labeled dataset toachieve high robustness and excellent classification of defect and non-defectareas as compared to principal components analysis (PCA), multi-resolution andinformation-fusion-based algorithms. In addition, we incorporated twoclassifiers at different stages of our inspection framework for labeling andrefining the unlabeled defects. We successfully enhanced the inspectiondepth-limit up to 5 microns. The experimental results show that our methodoutperforms manual inspection in testing the quality of glass screen samples byidentifying defects on samples that have been marked as good by humaninspection.

Smart-Inspect: Micro Scale Localization and Classification of Smartphone Glass Defects for Industrial Automation