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

For the problems of low recognition rate and slow recognition speed oftraditional detection methods in IC appearance defect detection, we propose anIC appearance defect detection algo-rithm IH-ViT. Our proposed model takesadvantage of the respective strengths of CNN and ViT to acquire image featuresfrom both local and global aspects, and finally fuses the two features fordecision making to determine the class of defects, thus obtaining betteraccuracy of IC defect recognition. To address the problem that IC appearancedefects are mainly reflected in the dif-ferences in details, which aredifficult to identify by traditional algorithms, we improved the tra-ditionalViT by performing an additional convolution operation inside the batch. For theproblem of information imbalance of samples due to diverse sources of datasets, we adopt a dual-channel image segmentation technique to further improvethe accuracy of IC appearance defects. Finally, after testing, our proposedhybrid IH-ViT model achieved 72.51% accuracy, which is 2.8% and 6.06% higherthan ResNet50 and ViT models alone. The proposed algorithm can quickly andaccurately detect the defect status of IC appearance and effectively improvethe productivity of IC packaging and testing companies.

IH-ViT: Vision Transformer-based Integrated Circuit Appear-ance Defect Detection