Nordic Aviation Capital uses Amazon Rekognition to streamline aircraft maintenance document review
Nordic Aviation Capital (NAC), a leading regional aircraft lessor, automated the review of extensive and unstructured aircraft maintenance documents using Amazon Rekognition Custom Labels. The AI solution precisely identifies critical documents requiring specialist review, greatly reducing reliance on external contractors and accelerating the leasing process. The custom computer vision model was trained on only a few hundred examples, achieving over 99% recall accuracy after iterative refinement.
- Organization
- Nordic Aviation Capital
- Industry
- Manufacturing
- Location
- Denmark
- Published
- April 2022
Planned next steps
- The source says the organization aims to achieve: Improved review accuracy and efficiency.
Why do we believe this deployment?Customer identity, provider attribution, maturity, and source checks
- Customer
- Nordic Aviation Capital
- Provider
- AWS
- Maturity
- Production
- Linked source
- AWS Machine Learning Blog
Reducing operational costs and improving process speeds were key objectives
Primary read
Use case focus
Showing 3 of 3
- 1Document Processing
- 2Computer Vision
- 3Operational Efficiency
- Implemented a custom computer vision solution using Amazon Rekognition Custom Labels for image classification and document identification.
- Used Amazon S3 for storing training data and leveraged Rekognition's automatic labeling features to reduce the manual effort in model training.
- Iteratively improved model performance by adding challenging examples, achieving recall above 99%, far exceeding the minimum business baseline.
Sources & evidence1
- Customer explicitly identified
- Deployment status explicitly supported
- Technical implementation details available
AI-generated summary. Verify important details with the linked sources before relying on this case.
Explore related AI use cases
Was this useful?
Community
Comments
No published comments yet.