Visual Inspection
Visual inspection, the process of examining objects or systems for defects, is undergoing a transformation driven by advancements in artificial intelligence and computer vision. Current research focuses on automating inspection tasks across diverse domains, from manufacturing quality control to infrastructure monitoring, using deep learning models like convolutional neural networks (CNNs), transformers, and autoencoders, often coupled with techniques like active learning and explainable AI to improve efficiency and reliability. This automation promises significant improvements in speed, accuracy, and consistency compared to traditional manual methods, impacting various industries by enhancing safety, reducing costs, and improving overall productivity.
Papers
Automated Detection and Counting of Windows using UAV Imagery based Remote Sensing
Dhruv Patel, Shivani Chepuri, Sarvesh Thakur, K. Harikumar, Ravi Kiran S., K. Madhava Krishna
Local Concept Embeddings for Analysis of Concept Distributions in DNN Feature Spaces
Georgii Mikriukov, Gesina Schwalbe, Korinna Bade