aiInternal Project
Missing Part Detection System
Computer vision system for product classification and defect detection with 95% accuracy.
Developed at ProManage
Lead Data Scientist
2019-2020
Internal project - no public access
Screenshots
About This Project
Designed and implemented a computer vision system for manufacturing quality control that detects missing parts and classifies products with high accuracy. The system uses N-Shot Learning to handle diverse product variations with limited training images, making it adaptable to new product lines without extensive retraining.
Key Features
- Product classification with N-Shot Learning
- Missing parts detection in assembly lines
- Real-time processing for production integration
- Adaptable to new product variants with minimal data
- Anomaly detection for quality assurance
- Integration with manufacturing execution systems
Challenges & Solutions
- Achieving high accuracy with limited training images
- Handling diverse product variations and lighting conditions
- Meeting real-time processing requirements
- Minimizing false positives in production environment
Results & Impact
- 95% accuracy in product classification and defect detection
- 90%+ accuracy in anomaly detection
- 20% improvement in client investment returns through predictive maintenance
Technologies Used
PythonPyTorchOpenCVN-Shot LearningTensorFlowDocker
Project Details
- Category
- ai
- My Role
- Lead Data Scientist
- Duration
- 8 months
- Year
- 2019-2020
- Company
- ProManage
- Status
- Internal / Private
Internal Project
This project was developed for internal use at ProManage. Source code and live demo are not publicly available due to confidentiality.