aiInternal Project
Product Side Correctness
Computer vision application using CNN and GAN to accurately identify and verify product orientations, contributing to a 10% profit increase.
Developed at ProManage
Lead Data Scientist
2019-2020
Internal project - no public access
Screenshots
About This Project
Built a product matching application that uses deep learning models including Convolutional Neural Networks (CNN) and Generative Adversarial Networks (GAN) to accurately identify and verify correct product side orientations. The system ensures products are correctly positioned in manufacturing and packaging processes.
Key Features
- CNN-based product side classification
- GAN-powered synthetic data augmentation
- Multi-angle product orientation detection
- Real-time inference for production line integration
- Automated quality verification pipeline
- Configurable product type and orientation profiles
Challenges & Solutions
- Training accurate models with limited product orientation data
- Using GANs to generate realistic product images for data augmentation
- Achieving real-time inference speed for production environments
- Handling variations in lighting and product appearance
Results & Impact
- 10% profit increase for the customer
- High accuracy in product side identification
- Seamless integration with existing production workflows
Technologies Used
PythonOpenCVTensorFlowCNNGANNumPy
Project Details
- Category
- ai
- My Role
- Lead Data Scientist
- Duration
- 5 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.