Min-Ho Oh
Ulsan National Institute of Science and Technology · 工学
研究室紹介
Professor Min-Ho Oh's research lab specializes in developing advanced deep learning and computer vision solutions for scientific imaging and real-world applications. The lab focuses on autonomous image quality assessment and parameter optimization in scanning electron microscopy (SEM), enabling high-resolution imaging with minimal expert intervention. Additionally, the lab pioneers innovative AI-driven pipelines for digital content creation—such as automated flat-coloring in comics—and real-time detection systems for critical safety applications like fire and smoke detection. Their work bridges cutting-edge AI with practical challenges in materials science, creative technology, and public safety.
Research Overview
Research Output Trend
Figures are computed from collected data and may differ slightly.
Selected Papers
5Journal Article Deep-Learning Based Autofocus Score Prediction of Scanning Electron Microscope Get access Huisoo Kim, Huisoo Kim Egovid Inc., UNIST-gil 50, Ulsan 44919, Korea Search for other works by this author on: Oxford Academic Google Scholar Moohyun Oh, Moohyun Oh Egovid Inc., UNIST-gil 50, Ulsan 44919, Korea Search for other works by this author on: Oxford Academic Google Scholar Heerang Lee, Heerang Lee Egovid Inc., UNIST-gil 50, Ulsan 44919, Korea Search for other works by this author o
Hyun Jong Yang, Moohyun Oh, Jonggyu Jang, Hyeonsu Lyu, Junhee Lee; Robust Deep-learning Based Autofocus Score Prediction for Scanning Electron Microscope,
By virtue of their ultra high resolution, scanning electron microscopes (SEMs) are essential to study topography, morphology, composition, and crystallography of materials, and thus are widely used for advanced researches in physics, chemistry, pharmacy, geology, etc. The major hindrance of using SEMs is that obtaining high quality images from SEMs requires a professional control of many control parameters. Therefore, it is not an easy task even for an experienced researcher to get high quality
The process of drawing digital comics and animations is a complex process that involves multiple stages. Flat-coloring, the task of filling segmented regions in a line art image with uniform tone and hue, is a particularly time-consuming and labor-intensive task. We have identified that artists suffer from not only adjusting colors in overflowing regions due to line discontinuity but also finding to replace misaligned pixels near the line due to region-bleeding problems (aliasing issues). To add
In this letter, we propose a novel, fast model for detecting fire flames and smoke using object detection and 3D classification, referred to as FastFireDet3D. This model uses NanoDet to quickly identify potential areas representing fire and smoke, followed by a novel 3D classification model based on a spatio-temporal convolutional neural network (STCNN). This two-step process allows for efficient and accurate detection. The average processing time for FastFireDet3D is approximately 40-90 ms when