Jae-Chern Yoo
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Jae-Chern Yoo has a total of 20 co-authors. Here are the top co-authors by number of shared publications:
- Moo-Jung Seo
College of Information and Communication Engineering, Sungkyunkwan University, Suwon 440-746, Korea
5 shared publications - Se-Yeol Rhyou
Department of Electrical and Computer Engineering, College of Information and Communication Engineering, Sungkyunkwan University, Suwon 440-746, Republic of Korea
4 shared publications - Minyung Yu
Department of Electrical and Computer Engineering Sungkyunkwan University Suwon South Korea
2 shared publications - Chang Wook Ahn
Gwangju Institute of Science and Technology
1 shared publication - Da Ye Seul Lim
College of Information and Communication Engineering, Sungkyunkwan University, Suwon, Gyeonggi-do 440-746, Korea
1 shared publication Dayeseul Lim
College of Information & Communication Engineering, Sungkyunkwan University, Suwon, South Korea
1 shared publication
Latest Publications
- Open Access
Speech-Driven Facial Expression Synthesis Using Emotion-Aware Parametric Facial Descriptors
Speech-driven facial expression synthesis aims to generate realistic and emotionally consistent facial motion from speech signals for natural human–computer interaction and expressive virtual agents. This paper presents an emotion-aware framework based on parametric facial descriptors that explicitly models the relationship among speech, emotion, and facial motion. The framework consists of three components. First, a Speech Emotion Recognition (SER) module predicts frame-wise emotion probabilities over six categories: neutral, happy, anger, surprise, sad, and fear. Second, an emotion-conditioned facial descriptor represents interpretable facial expression parameters through a lip descriptor and a head–eye descriptor. The lip descriptor models speech-synchronous mouth articulation using a lookup table of canonical lip geometries, while the head–eye descriptor captures emotion-dependent head pose, eyebrow motion, eyelid activity, and gaze direction. Third, an envelope-driven temporal modulation mechanism generates Animated Facial Expression Parameters (AFP) according to the temporal energy structure of speech. The resulting AFP sequence drives a LivePortrait-based portrait synthesis model to generate emotionally expressive facial images. Experimental results demonstrate visually coherent and temporally consistent facial motion aligned with both speech articulation and emotional state.
Open AccessSpeech-Driven Facial Expression Synthesis Using Emotion-Aware Parametric Facial Descriptors
Speech-driven facial expression synthesis aims to generate realistic and emotionally consistent facial motion from speech signals for natural human–computer interaction and expressive virtual agents. This paper presents an emotion-aware framework based on parametric facial descriptors that explicitly models the relationship among speech, emotion, and facial motion. The framework consists of three components. First, a Speech Emotion Recognition (SER) module predicts frame-wise emotion probabilities over six categories: neutral, happy, anger, surprise, sad, and fear. Second, an emotion-conditioned facial descriptor represents interpretable facial expression parameters through a lip descriptor and a head–eye descriptor. The lip descriptor models speech-synchronous mouth articulation using a lookup table of canonical lip geometries, while the head–eye descriptor captures emotion-dependent head pose, eyebrow motion, eyelid activity, and gaze direction. Third, an envelope-driven temporal modulation mechanism generates Animated Facial Expression Parameters (AFP) according to the temporal energy structure of speech. The resulting AFP sequence drives a LivePortrait-based portrait synthesis model to generate emotionally expressive facial images. Experimental results demonstrate visually coherent and temporally consistent facial motion aligned with both speech articulation and emotional state.
- Open Access
- 1 September 2026
- Published by Korea Computer Graphics Society in Journal of the Korea Computer Graphics Society
- Vol. 32 (4) , 67-77
PO-IoU: Point-Offset-Guided Zero-Shot Knee Joint Segmentation for Osteoarthritis Assessment
사단법인 한국컴퓨터그래픽스학회의 논문지로서 그래픽스 분야와 그에 연관된 연구영역의 새로운 발견과 최첨단 연구결과를 발표하는 토론의 장입니다. 학회를 대표하는 학술지인 논문지는 1995년에 논문지 발간을 시작으로 2000년부터 3월, 6월, 9월, 12월 총 4회 발간되었고, 2015년부터는 KCGS 학술대회 특별호를 7월에 발간하면서 총 5회 발간되고 있습니다.
- 1 September 2026
- Published by Korea Computer Graphics Society in Journal of the Korea Computer Graphics Society
- Vol. 32 (4) , 67-77
Open AccessPO-IoU: Point-Offset-Guided Zero-Shot Knee Joint Segmentation for Osteoarthritis Assessment
사단법인 한국컴퓨터그래픽스학회의 논문지로서 그래픽스 분야와 그에 연관된 연구영역의 새로운 발견과 최첨단 연구결과를 발표하는 토론의 장입니다. 학회를 대표하는 학술지인 논문지는 1995년에 논문지 발간을 시작으로 2000년부터 3월, 6월, 9월, 12월 총 4회 발간되었고, 2015년부터는 KCGS 학술대회 특별호를 7월에 발간하면서 총 5회 발간되고 있습니다.
- Open Access
- 1 June 2026
- Published by Korea Computer Graphics Society in Journal of the Korea Computer Graphics Society
- Vol. 32 (2) , 33-45
차량 가림 환경에서 부분적으로 가시적인 보행자의 포즈 유도 재구성
사단법인 한국컴퓨터그래픽스학회의 논문지로서 그래픽스 분야와 그에 연관된 연구영역의 새로운 발견과 최첨단 연구결과를 발표하는 토론의 장입니다. 학회를 대표하는 학술지인 논문지는 1995년에 논문지 발간을 시작으로 2000년부터 3월, 6월, 9월, 12월 총 4회 발간되었고, 2015년부터는 KCGS 학술대회 특별호를 7월에 발간하면서 총 5회 발간되고 있습니다.
- 1 June 2026
- Published by Korea Computer Graphics Society in Journal of the Korea Computer Graphics Society
- Vol. 32 (2) , 33-45
Open Access차량 가림 환경에서 부분적으로 가시적인 보행자의 포즈 유도 재구성
사단법인 한국컴퓨터그래픽스학회의 논문지로서 그래픽스 분야와 그에 연관된 연구영역의 새로운 발견과 최첨단 연구결과를 발표하는 토론의 장입니다. 학회를 대표하는 학술지인 논문지는 1995년에 논문지 발간을 시작으로 2000년부터 3월, 6월, 9월, 12월 총 4회 발간되었고, 2015년부터는 KCGS 학술대회 특별호를 7월에 발간하면서 총 5회 발간되고 있습니다.
- Open Access
- 28 February 2025
- Published by MDPI AG in Diagnostics
- Vol. 15 (5) , 588
Mixture of Expert-Based SoftMax-Weighted Box Fusion for Robust Lesion Detection in Ultrasound Imaging
Background/Objectives: Ultrasound (US) imaging plays a crucial role in the early detection and treatment of hepatocellular carcinoma (HCC). However, challenges such as speckle noise, low contrast, and diverse lesion morphology hinder its diagnostic accuracy. Methods: To address these issues, we propose CSM-FusionNet, a novel framework that integrates clustering, SoftMax-weighted Box Fusion (SM-WBF), and padding. Using raw US images from a leading hospital, Samsung Medical Center (SMC), we applied intensity adjustment, adaptive histogram equalization, low-pass, and high-pass filters to reduce noise and enhance resolution. Data augmentation generated ten images per one raw US image, allowing the training of 10 YOLOv8 networks. The mAP@0.5 of each network was used as SoftMax-derived weights in SM-WBF. Threshold-lowered bounding boxes were clustered using Density-Based Spatial Clustering of Applications with Noise (DBSCAN), and outliers were managed within clusters. SM-WBF reduced redundant boxes, and padding enriched features, improving classification accuracy. Results: The accuracy improved from 82.48% to 97.58% with sensitivity reaching 100%. The framework increased lesion detection accuracy from 56.11% to 95.56% after clustering and SM-WBF. Conclusions: CSM-FusionNet demonstrates the potential to significantly improve diagnostic reliability in US-based lesion detection, aiding precise clinical decision-making.
- 28 February 2025
- Published by MDPI AG in Diagnostics
- Vol. 15 (5) , 588
Open AccessMixture of Expert-Based SoftMax-Weighted Box Fusion for Robust Lesion Detection in Ultrasound Imaging
Background/Objectives: Ultrasound (US) imaging plays a crucial role in the early detection and treatment of hepatocellular carcinoma (HCC). However, challenges such as speckle noise, low contrast, and diverse lesion morphology hinder its diagnostic accuracy. Methods: To address these issues, we propose CSM-FusionNet, a novel framework that integrates clustering, SoftMax-weighted Box Fusion (SM-WBF), and padding. Using raw US images from a leading hospital, Samsung Medical Center (SMC), we applied intensity adjustment, adaptive histogram equalization, low-pass, and high-pass filters to reduce noise and enhance resolution. Data augmentation generated ten images per one raw US image, allowing the training of 10 YOLOv8 networks. The mAP@0.5 of each network was used as SoftMax-derived weights in SM-WBF. Threshold-lowered bounding boxes were clustered using Density-Based Spatial Clustering of Applications with Noise (DBSCAN), and outliers were managed within clusters. SM-WBF reduced redundant boxes, and padding enriched features, improving classification accuracy. Results: The accuracy improved from 82.48% to 97.58% with sensitivity reaching 100%. The framework increased lesion detection accuracy from 56.11% to 95.56% after clustering and SM-WBF. Conclusions: CSM-FusionNet demonstrates the potential to significantly improve diagnostic reliability in US-based lesion detection, aiding precise clinical decision-making.
- 5 January 2025
- Published by Elsevier in Medical Image Analysis
- Vol. 101, 103453
Automated ultrasonography of hepatocellular carcinoma using discrete wavelet transform based deep-learning neural network
- 5 January 2025
- Published by Elsevier in Medical Image Analysis
- Vol. 101, 103453
Automated ultrasonography of hepatocellular carcinoma using discrete wavelet transform based deep-learning neural network
- Open Access
- 2 January 2025
- Published by MDPI AG in Electronics
- Vol. 14 (1) , 160
Automatic Lower-Limb Length Measurement Network (A3LMNet): A Hybrid Framework for Automated Lower-Limb Length Measurement in Orthopedic Diagnostics
Limb Length Discrepancy (LLD) is a common condition that can result in gait abnormalities, pain, and an increased risk of early degenerative osteoarthritis in the lower extremities. Epidemiological studies indicate that mild LLD, defined as a discrepancy of 10 mm or less, affects approximately 60–90% of the population. While more severe cases are less frequent, they are associated with secondary conditions such as low back pain, scoliosis, and osteoarthritis of the hip or knee. LLD not only impacts daily activities, but may also lead to long-term complications, making early detection and precise measurement essential. Current LLD measurement methods include physical examination and imaging techniques, with physical exams being simple and non-invasive but prone to operator-dependent errors. To address these limitations and reduce measurement errors, we have developed an AI-based automated lower-limb length measurement system. This method employs semantic segmentation to accurately identify the positions of the femur and tibia and extracts key anatomical landmarks, achieving a margin of error within 4 mm. By automating the measurement process, this system reduces the time and effort required for manual measurements, enabling clinicians to focus more on treatment and improving the overall quality of care.
- 2 January 2025
- Published by MDPI AG in Electronics
- Vol. 14 (1) , 160
Open AccessAutomatic Lower-Limb Length Measurement Network (A3LMNet): A Hybrid Framework for Automated Lower-Limb Length Measurement in Orthopedic Diagnostics
Limb Length Discrepancy (LLD) is a common condition that can result in gait abnormalities, pain, and an increased risk of early degenerative osteoarthritis in the lower extremities. Epidemiological studies indicate that mild LLD, defined as a discrepancy of 10 mm or less, affects approximately 60–90% of the population. While more severe cases are less frequent, they are associated with secondary conditions such as low back pain, scoliosis, and osteoarthritis of the hip or knee. LLD not only impacts daily activities, but may also lead to long-term complications, making early detection and precise measurement essential. Current LLD measurement methods include physical examination and imaging techniques, with physical exams being simple and non-invasive but prone to operator-dependent errors. To address these limitations and reduce measurement errors, we have developed an AI-based automated lower-limb length measurement system. This method employs semantic segmentation to accurately identify the positions of the femur and tibia and extracts key anatomical landmarks, achieving a margin of error within 4 mm. By automating the measurement process, this system reduces the time and effort required for manual measurements, enabling clinicians to focus more on treatment and improving the overall quality of care.
- Open Access
Dynamic Focusing (DF) Cone-Based Omnidirectional Fingertip Pressure Sensor with High Sensitivity in a Wide Pressure Range
It is essential to detect pressure from a robot’s fingertip in every direction to ensure efficient and secure grasping of objects with diverse shapes. Nevertheless, creating a simple-designed sensor that offers cost-effective and omnidirectional pressure sensing poses substantial difficulties. This is because it often requires more intricate mechanical solutions than when designing non-omnidirectional pressure sensors of robot fingertips. This paper introduces an innovative pressure sensor for fingertips. It utilizes a uniquely designed dynamic focusing cone to visually detect pressure with omnidirectional sensitivity. This approach enables cost-effective measurement of pressure from all sides of the fingertip. The experimental findings demonstrate the great potential of the newly introduced sensor. Its implementation is both straightforward and uncomplicated, offering high sensitivity (0.07 mm/N) in all directions and a broad pressure sensing range (up to 40 N) for robot fingertips.
Open AccessDynamic Focusing (DF) Cone-Based Omnidirectional Fingertip Pressure Sensor with High Sensitivity in a Wide Pressure Range
It is essential to detect pressure from a robot’s fingertip in every direction to ensure efficient and secure grasping of objects with diverse shapes. Nevertheless, creating a simple-designed sensor that offers cost-effective and omnidirectional pressure sensing poses substantial difficulties. This is because it often requires more intricate mechanical solutions than when designing non-omnidirectional pressure sensors of robot fingertips. This paper introduces an innovative pressure sensor for fingertips. It utilizes a uniquely designed dynamic focusing cone to visually detect pressure with omnidirectional sensitivity. This approach enables cost-effective measurement of pressure from all sides of the fingertip. The experimental findings demonstrate the great potential of the newly introduced sensor. Its implementation is both straightforward and uncomplicated, offering high sensitivity (0.07 mm/N) in all directions and a broad pressure sensing range (up to 40 N) for robot fingertips.
- Open Access
- 31 March 2023
- Published by Elsevier in Artificial Intelligence in Medicine
- Vol. 139, 102541
Aggregated micropatch-based deep learning neural network for ultrasonic diagnosis of cirrhosis
- 31 March 2023
- Published by Elsevier in Artificial Intelligence in Medicine
- Vol. 139, 102541
Open AccessAggregated micropatch-based deep learning neural network for ultrasonic diagnosis of cirrhosis
- Open Access
Omnidirectional Fingertip Pressure Sensor Using Hall Effect
When grasping objects with uneven or varying shapes, accurate pressure measurement on robot fingers is critical for precise robotic gripping operations. However, measuring the pressure from the sides of the fingertips remains challenging owing to the poor omnidirectionality of the pressure sensor. In this study, we propose an omnidirectional sensitive pressure sensor using a cone-shaped magnet slider and Hall sensor embedded in a flexible elastomer, which guarantees taking pressure measurements from any side of the fingertip. The experimental results indicate that the proposed pressure sensor has a high sensitivity (61.34 mV/kPa) in a wide sensing range (4–90 kPa) without blind spots on the fingertip, which shows promising application prospects in robotics.
Open AccessOmnidirectional Fingertip Pressure Sensor Using Hall Effect
When grasping objects with uneven or varying shapes, accurate pressure measurement on robot fingers is critical for precise robotic gripping operations. However, measuring the pressure from the sides of the fingertips remains challenging owing to the poor omnidirectionality of the pressure sensor. In this study, we propose an omnidirectional sensitive pressure sensor using a cone-shaped magnet slider and Hall sensor embedded in a flexible elastomer, which guarantees taking pressure measurements from any side of the fingertip. The experimental results indicate that the proposed pressure sensor has a high sensitivity (61.34 mV/kPa) in a wide sensing range (4–90 kPa) without blind spots on the fingertip, which shows promising application prospects in robotics.
- Open Access
Cascaded Deep Learning Neural Network for Automated Liver Steatosis Diagnosis Using Ultrasound Images
Diagnosing liver steatosis is an essential precaution for detecting hepatocirrhosis and liver cancer in the early stages. However, automatic diagnosis of liver steatosis from ultrasound (US) images remains challenging due to poor visual quality from various origins, such as speckle noise and blurring. In this paper, we propose a fully automated liver steatosis prediction model using three deep learning neural networks. As a result, liver steatosis can be automatically detected with high accuracy and precision. First, transfer learning is used for semantically segmenting the liver and kidney (L-K) on parasagittal US images, and then cropping the L-K area from the original US images. The second neural network also involves semantic segmentation by checking the presence of a ring that is typically located around the kidney and cropping of the L-K area from the original US images. These cropped L-K areas are inputted to the final neural network, SteatosisNet, in order to grade the severity of fatty liver disease. The experimental results demonstrate that the proposed model can predict fatty liver disease with the sensitivity of 99.78%, specificity of 100%, PPV of 100%, NPV of 99.83%, and diagnostic accuracy of 99.91%, which is comparable to the common results annotated by medical experts.
Open AccessCascaded Deep Learning Neural Network for Automated Liver Steatosis Diagnosis Using Ultrasound Images
Diagnosing liver steatosis is an essential precaution for detecting hepatocirrhosis and liver cancer in the early stages. However, automatic diagnosis of liver steatosis from ultrasound (US) images remains challenging due to poor visual quality from various origins, such as speckle noise and blurring. In this paper, we propose a fully automated liver steatosis prediction model using three deep learning neural networks. As a result, liver steatosis can be automatically detected with high accuracy and precision. First, transfer learning is used for semantically segmenting the liver and kidney (L-K) on parasagittal US images, and then cropping the L-K area from the original US images. The second neural network also involves semantic segmentation by checking the presence of a ring that is typically located around the kidney and cropping of the L-K area from the original US images. These cropped L-K areas are inputted to the final neural network, SteatosisNet, in order to grade the severity of fatty liver disease. The experimental results demonstrate that the proposed model can predict fatty liver disease with the sensitivity of 99.78%, specificity of 100%, PPV of 100%, NPV of 99.83%, and diagnostic accuracy of 99.91%, which is comparable to the common results annotated by medical experts.