A5091718811- Speech and Audio Processing
- Gaze Tracking and Assistive Technology
- AI in cancer detection
- Emotion and Mood Recognition
- Cell Image Analysis Techniques
- EEG and Brain-Computer Interfaces
- Color perception and design
- Infrastructure Maintenance and Monitoring
- Digital Imaging for Blood Diseases
- Elevator Systems and Control
- Music and Audio Processing
- Hand Gesture Recognition Systems
Seoul National University of Science and Technology
2021-2024
The demand for wheelchairs has increased recently as the population of elderly and patients with disorders increases. However, society still pays less attention to infrastructure that can threaten wheelchair user, such sidewalks cracks/potholes. Although various studies have been proposed recognize challenges, they mainly depend on RGB images or IMU sensors, which are sensitive outdoor conditions low illumination, bad weather, unavoidable vibrations, resulting in unsatisfactory unstable...
Microscopic image-based analysis has been intensively performed for pathological studies and diagnosis of diseases. However, mis-authentication cell lines due to misjudgments by pathologists recognized as a serious problem. To address this problem, we propose deep-learning-based approach the automatic taxonomy cancer types. A total 889 bright-field microscopic images four were acquired using benchtop microscope. Individual cells further segmented augmented increase image dataset. Afterward,...
Gesture interaction is considered one of the promising approaches to control smart devices. In this paper, we present Knock&Tap, an audio-based approach that can perform gesture classification and localization using deep transfer learning. Knock&Tap consists a single 4-microphone array record sound user's knocking tapping gestures wood/glass panel for tapping. be used in situation or environment where vision-based recognition impossible due lighting condition camera installation issue....