Abstract: The apparel and textile industry relies on high-quality products, but traditional quality control methods, like manual inspection, are labor-intensive and error-prone. This study introduces an AI-based Quality Control System for Garment Factories, leveraging machine learning for automated garment quality assessment. Using a Random Forest Classifier, the system evaluates factors like fabric type, texture, thickness, and weave quality to classify garments as high-grade or low-quality. Built with Python and Flask for scalable backend processing, the system ensures real-time predictions. Its frontend, designed in HTML, CSS, and JavaScript, offers a user- friendly interface. The workflow includes a homepage overview, secure user registration, and login for factory users. Once data is submitted, the trained Random Forest model provides results, classifying garment quality effectively. This system enhances efficiency and consistency in quality control processes.
Keywords: Quality Control, Garment Factories, Machine Learning, Random Forest Classifier, User Interface, Weave Quality, Prediction
Copyright Form