B.Tech Projects
Leather
Defect
Detection
Deep learning ensemble model for leather defect detection with Flask integration.
Changed
Created experience in model comparison, backend integration, and API-based deployment.
Took away
Model accuracy depends heavily on environment, data quality, and deployment context.
Tools / frame
Context
Built as a computer-vision project focused on visual quality inspection.
Problem
Defect detection requires accuracy, consistency, and a deployable interface for practical use.
Contribution
Built a deep learning ensemble using CNN, VGG, AlexNet, DenseNet, Xception, and Inception, integrated into a Flask backend and RESTful API.
Tools used
Impact / learning
Created experience in model comparison, backend integration, and API-based deployment.
Model accuracy depends heavily on environment, data quality, and deployment context.
Future direction
Present this as a machine-learning deployment case with more attention to data and operating context.