CannerVision : Web Application for Automatic Classification of Defective and Non-Defective Beverage Cans

Deskripsi

The project is an application called CannerVision, which is designed to help classify defective and non-defective beverage cans in the manufacturing and industrial sectors. The goal of this project is to improve the efficiency of the production process by detecting defective products automatically and quickly, thus reducing the time and cost required for manual inspection. With CannerVision, we hope to make a real contribution to improving the quality and efficiency of the manufacturing industry. We use the TensorFlow framework and Keras library to build and train AI models. In addition, we utilize OpenCV for image processing and improving defect detection accuracy. The model we have created is then integrated into a website using Streamlit, so that this application can be accessed and used easily by users.