Deployment Strategies for AI-based Computer Vision in Industrial Quality Control

The integration of Artificial Intelligence (AI) and Computer Vision (CV) revolutionizes industrial quality control through automated defect detection. This paper investigates deployment strategies for AI-based CV systems across edge and cloud platforms, analyzing trade-offs between accuracy, latency, and computational cost. ResNet18 and EfficientNet-B0 are systematically evaluated using advanced data augmentation techniques on the MVTec-AD dataset. Results demonstrate that EfficientNet-B0 achieves superior classification performance (86.22% accuracy), while edge GPU deployment ensures lowest inference latency (120ms) for real-time inspection. Cloud deployment offers scalability and reduced capital expenditure but incurs latency penalties (192-311ms) limiting time-critical applications.