About Me

---

 

 

E-mail : yellowjs0304@gmail.com

 

GitHub : github.com/yellowjs0304

ORCiD : orcid.org/0000-0002-9522-3981

Interests : Document AI, CV, Multi-modal Information Task

 

2015.03 ~ 2019.02, B.S. in Computer Science, Kyonggi University, Korea

2019.03 ~ 2021.02, M.S. in Computer Science, Kyonggi University, Korea

Skills : Python, Pytorch, Docker, OpenCV, Tensorflow, ROS2, V-REP, JAVA, ROSJAVA

Projects
Modeling
- VLN(Vison Language Navigation)
- Multi-modal Guess what?!
- Several(Place, Character) recognition

Development
- Generate robot experiment environments(by Vrep, Gazebo)
- Develop robot perception module by python, ROS, depth camera(kinect / realsense)

2021.08 ~ Current, AI Researcher in AgileSoDA

Skills: Python, Pytoch, OpenCV, Docker, Triton, Tensorflow

Projects
Modeling
- OCR(STD, STR)
- NER(Named Entity Recognition)
- TSR(Table Structure Recognition)
- Several(strikethrough, checkmark, circled number, document contour) detection
- DLA(Document Layout Analysis)

Serving
- Docker
- Triton
- FastAPI

ETC
- Generate synthetic data (with image processing)
- Manage labeling tool(label-studio, labelme)
- Manage data annotation
- Support PoC

 

---