Professor+Ki-Hun+Jeong
-
AI Light-Field Camera Reads 3D Facial Expressions
Machine-learned, light-field camera reads facial expressions from high-contrast illumination invariant 3D facial images
A joint research team led by Professors Ki-Hun Jeong and Doheon Lee from the KAIST Department of Bio and Brain Engineering reported the development of a technique for facial expression detection by merging near-infrared light-field camera techniques with artificial intelligence (AI) technology.
Unlike a conventional camera, the light-field camera contains micro-lens arrays in front of the image sensor, which makes the camera small enough to fit into a smart phone, while allowing it to acquire the spatial and directional information of the light with a single shot. The technique has received attention as it can reconstruct images in a variety of ways including multi-views, refocusing, and 3D image acquisition, giving rise to many potential applications.
However, the optical crosstalk between shadows caused by external light sources in the environment and the micro-lens has limited existing light-field cameras from being able to provide accurate image contrast and 3D reconstruction.
The joint research team applied a vertical-cavity surface-emitting laser (VCSEL) in the near-IR range to stabilize the accuracy of 3D image reconstruction that previously depended on environmental light. When an external light source is shone on a face at 0-, 30-, and 60-degree angles, the light field camera reduces 54% of image reconstruction errors. Additionally, by inserting a light-absorbing layer for visible and near-IR wavelengths between the micro-lens arrays, the team could minimize optical crosstalk while increasing the image contrast by 2.1 times.
Through this technique, the team could overcome the limitations of existing light-field cameras and was able to develop their NIR-based light-field camera (NIR-LFC), optimized for the 3D image reconstruction of facial expressions. Using the NIR-LFC, the team acquired high-quality 3D reconstruction images of facial expressions expressing various emotions regardless of the lighting conditions of the surrounding environment.
The facial expressions in the acquired 3D images were distinguished through machine learning with an average of 85% accuracy – a statistically significant figure compared to when 2D images were used. Furthermore, by calculating the interdependency of distance information that varies with facial expression in 3D images, the team could identify the information a light-field camera utilizes to distinguish human expressions.
Professor Ki-Hun Jeong said, “The sub-miniature light-field camera developed by the research team has the potential to become the new platform to quantitatively analyze the facial expressions and emotions of humans.” To highlight the significance of this research, he added, “It could be applied in various fields including mobile healthcare, field diagnosis, social cognition, and human-machine interactions.”
This research was published in Advanced Intelligent Systems online on December 16, under the title, “Machine-Learned Light-field Camera that Reads Facial Expression from High-Contrast and Illumination Invariant 3D Facial Images.” This research was funded by the Ministry of Science and ICT and the Ministry of Trade, Industry and Energy.
-Publication“Machine-learned light-field camera that reads fascial expression from high-contrast and illumination invariant 3D facial images,” Sang-In Bae, Sangyeon Lee, Jae-Myeong Kwon, Hyun-Kyung Kim. Kyung-Won Jang, Doheon Lee, Ki-Hun Jeong, Advanced Intelligent Systems, December 16, 2021 (doi.org/10.1002/aisy.202100182)
ProfileProfessor Ki-Hun JeongBiophotonic LaboratoryDepartment of Bio and Brain EngineeringKAIST
Professor Doheon LeeDepartment of Bio and Brain EngineeringKAIST
2022.01.21 View 9618 -
Ultrafast, on-Chip PCR Could Speed Up Diagnoses during Pandemics
A rapid point-of-care diagnostic plasmofluidic chip can deliver result in only 8 minutes
Reverse transcription-polymerase chain reaction (RT-PCR) has been the gold standard for diagnosis during the COVID-19 pandemic. However, the PCR portion of the test requires bulky, expensive machines and takes about an hour to complete, making it difficult to quickly diagnose someone at a testing site. Now, researchers at KAIST have developed a plasmofluidic chip that can perform PCR in only about 8 minutes, which could speed up diagnoses during current and future pandemics.
The rapid diagnosis of COVID-19 and other highly contagious viral diseases is important for timely medical care, quarantining and contact tracing. Currently, RT-PCR uses enzymes to reverse transcribe tiny amounts of viral RNA to DNA, and then amplifies the DNA so that it can be detected by a fluorescent probe. It is the most sensitive and reliable diagnostic method.
But because the PCR portion of the test requires 30-40 cycles of heating and cooling in special machines, it takes about an hour to perform, and samples must typically be sent away to a lab, meaning that a patient usually has to wait a day or two to receive their diagnosis.
Professor Ki-Hun Jeong at the Department of Bio and Brain Engineering and his colleagues wanted to develop a plasmofluidic PCR chip that could quickly heat and cool miniscule volumes of liquids, allowing accurate point-of-care diagnoses in a fraction of the time. The research was reported in ACS Nano on May 19.
The researchers devised a postage stamp-sized polydimethylsiloxane chip with a microchamber array for the PCR reactions. When a drop of a sample is added to the chip, a vacuum pulls the liquid into the microchambers, which are positioned above glass nanopillars with gold nanoislands. Any microbubbles, which could interfere with the PCR reaction, diffuse out through an air-permeable wall. When a white LED is turned on beneath the chip, the gold nanoislands on the nanopillars quickly convert light to heat, and then rapidly cool when the light is switched off.
The researchers tested the device on a piece of DNA containing a SARS-CoV-2 gene, accomplishing 40 heating and cooling cycles and fluorescence detection in only 5 minutes, with an additional 3 minutes for sample loading. The amplification efficiency was 91%, whereas a comparable conventional PCR process has an efficiency of 98%. With the reverse transcriptase step added prior to sample loading, the entire testing time with the new method could take 10-13 minutes, as opposed to about an hour for typical RT-PCR testing. The new device could provide many opportunities for rapid point-of-care diagnostics during a pandemic, the researchers say.
-Publication
Ultrafast and Real-Time Nanoplasmonic On-Chip Polymerase Chain Reaction for Rapid and Quantitative Molecular Diagnostics
ACS Nano (https://doi.org/10.1021/acsnano.1c02154)
-Professor
Ki-Hun Jeong
Biophotonics Laboratory
https://biophotonics.kaist.ac.kr/
Department of Bio and Brain Engineeinrg
KAIST
2021.06.08 View 8349