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

Visual quality inspection in high performance manufacturing can benefit fromautomation, due to cost savings and improved rigor. Deep learning techniquesare the current state of the art for generic computer vision tasks likeclassification and object detection. Manufacturing data can pose a challengefor deep learning because data is highly repetitive and there are few images ofdefects or deviations to learn from. Deep learning models trained with suchdata can be fragile and sensitive to context, and can under-detect new defectsnot found in the training data. In this work, we explore training defectdetection models to learn specific defects out of context, so that they aremore likely to be detected in new situations. We demonstrate how models trainedon diverse images containing a common defect type can pick defects out in newcircumstances. Such generic models could be more robust to new defects notfound data collected for training, and can reduce data collection impedimentsto implementing visual inspection on production lines. Additionally, wedemonstrate that object detection models trained to predict a label andbounding box outperform classifiers that predict a label only on held out testdata typical of manufacturing inspection tasks. Finally, we studied the factorsthat affect generalization in order to train models that work under a widerrange of conditions.

A Novel Strategy for Improving Robustness in Computer Vision Manufacturing Defect Detection