To address the external defect detection challenges of lightning arresters in power systems, this paper proposes a novel visual detection method, Ar-YOLOv10, based on an improved YOLOv10 model for ...

An AI-powered visual defect detection system using ResNet-50 and Grad-CAM. Trained on the MVTec dataset to classify products as “Good” or “Defective.” Includes a Streamlit app for real-time image ...

By leveraging artificial intelligence and image recognition models, AI-based systems can provide consistent and objective defect detection, minimizing the impact of human subjectivity. These systems ...

This project aims to build an automated visual inspection system that classifies manufactured products as defective or non-defective using deep learning and transfer learning techniques. In industrial ...

Distribution line project acceptance is a key link in the quality control of distribution line grid project, which is an important factor affecting the safe and stable operation of distribution ...