Description
Detect defects and quality issues during production using visual and other data
Benefits & ROI
0.4
Linked Case Studies
Case Study
University of Lincoln
Researchers from the University of Lincoln have built a learning computer system to early detect potentially harmful flaws in production and packaging of potatoes
Case Study
Wikimedia
Wikimedia identifies and prioritises missing citations with an accuracy of up to 90% using a recurrent neural network
Case Study
Kewpie
Kewpie, a Japanese food manufacturing company, used deep machine vision that identified defective potato cubes on the production line with the same level as accuracy as humans
Case Study
Foxconn
Foxconn to identify and predict defects in manufacturing process with machine vision
Case Study
Netflix
Netflix increases quality control efficiency by using machine learning to predict which video assets are likely to fail
Case Study
AngloGold Ashanti
Researchers investigate a cost-effective machine learning method for identifying gold from waste during ore sorting at an AngloGold Ashanti mine
←Back to Use Case Library
Source: mckinsey.com · Editor: original-sdg