(* indicates equal contribution)
AI-based visual inspection involves using machine learning to automatically verify product quality by analyzing unstructured image and video data. AI and computer vision technologies enable manufacturers to automate product defect detection, saving time and money while improving quality control.
Image Deblurring
We proposes a novel image deblurring algorithm for Mura images acquired by intentionally out-of-focus cameras.
•
Sung-Jun Min*, Kyeongbo Kong*, Suk-Ju Kang, "Out-of-Focus Image Deblurring for Mobile Display Vision Inspection", IEEE Transactions on Circuits and Systems for Video Technology, 2023. (IF: 5.859)
•
Sung-Jun Min*, Kyeongbo Kong*, Suk-Ju Kang, "Deep Anti-Aliasing: Image Restoration for Enhancing Display Defects Detection", International Meeting on Information Display (IMID), Aug, 2022. (Invited)
Image Demoireing
When the camera is focused on the display for accurately detecting Mura defects, a moire pattern occurs in a captured image because of the frequency difference between the subpixels of the display and the color filter array of the camera.
•
Jung-Hyun Kim, Kyeongbo Kong, Suk-Ju Kang, "Image Demoireing Via U-Net for Detection of Display Defects", IEEE Access, 2022.
Anomaly Detection
Anomaly segmentation, which localizes defective areas, is an important component in large-scale industrial manufacturing.
•
Jou Won Song*, Kyeongbo Kong*, Ye In Park, Seong-Gyun Kim, Suk-Ju Kang, "AnoSeg: Anomaly Segmentation Network Using Self-Supervised Learning", AAAIW, 2022. (Top-tier AI conference workshop)
•
Jou Won Song*, Kyeongbo Kong*, Ye In Park, Seong-Gyun Kim, Suk-Ju Kang, "Direct anomaly segmentation with location information", (Revision)