Deokhwan Park
Papers
1
Total Citations
34
H-Index
1
About
Deokhwan Park is a leading researcher at the intersection of computer vision and dietary technology, specializing in deep learning methods for food image analysis and automated diet management. His most impactful work tackles the critical bottleneck of data scarcity in training intelligent systems: his highly cited 2021 paper, "Deep Learning based Food Instance Segmentation using Synthetic Data" (34 citations), pioneers a novel approach to overcome the labor-intensive challenges of collecting and annotating real-world food images. By generating and leveraging synthetic data, Park’s research enables deep neural networks to accurately segment and recognize food instances without the prohibitive cost of manual labeling. This contribution is foundational for building scalable, automated dietary assessment tools that can operate in real-world settings. Park’s work directly addresses a key obstacle in the field—bridging the gap between the need for large, diverse training datasets and the practical difficulties of obtaining them—making his research highly influential for students and engineers developing next-generation health-monitoring and nutrition-tracking applications.
Research Focus
Key Achievements
Top Papers
- 1Deep Learning based Food Instance Segmentation using Synthetic Data34 citations · 2021