HanGyu Lee

Computer Vision Company

Team Leader • July, 2020 — Present

Leading an artificial intelligence team that is specialized in computer vision

• Developed a program retrieves of sketched images of key frames of ad videos for users on the website of the Korea Broadcast Advertising Promotion Corporation (KOBACO)
• I devloped an image retrieval system for examiners in the patent office.

Former Software Developer at a Computer Vision Company

Software Developer • Nov, 2017 — Mar, 2020

In this role, I was part of the development team at KPST, where I worked on research and development projects that were frequently commissioned by ETRI."

Hanbat National University

bachelor of computer engineering • 2009 — 2017

Automated Tagging AI Server

Team Leader • 2021 — Present

Lead a team that is developing an Automated Tagging System server for object detection, face detection, pose estimation, and license plate detection.

Create Storyboard from Sentences

Team Leader • 2021 — 2021

The project involved creating a storyboard based on a user's sentence. The project utilized various computer vision skills including face detection, swapping, text detection and removal, inpainting, sketching images, captioning images, and retrieving similar sentences to the user's input.

Illegal Copying Detection System

main developer • 2020 — 2020

As the main developer, created a program to help patent examiners detect illegal copying by retrieving similar images from a database of 3 million images, saving examiners time during the examination process.

Compare performance of tensorflow and pytorch

Researcher • 2019 — 2019

Conducted research to compare the performance of TensorFlow and PyTorch for pose estimation and converting TensorFlow code to PyTorch and training a TensorFlow-trained dataset with PyTorch.

Detect food

devloper • 2018 — 2019

Worked as a developer on a project that aimed to detect food, requiring classification of more than a thousand classes and processing hundreds of thousands of images.

(Languages) Python, C, C++, C#

Primarily use Python, but have experience with C++ for projects where speed performance is critical. Have experience converting torch models to optimized models for deployment on mobile apps (tflite, PyTorch Mobile, TorchScript), web (WEBGL with tflite), and API servers (Triton, Kserve, Flask, Django, FastAPI).

(Computer Vision) Object Detection, OCR, Image Retrieval, Segmentation, OpenCV, OpenVX

Experienced in object detection, from small datasets with small objects to large datasets. Familiar with image retrieval and segmentation.

(Serving) Docker, Kubernetes (Kserve), Triton, Flask, Django, Streamlit, Gradio

Not an expert in serving models, but have experience deploying AI models with inference server engines.

(Deep learning)

Capable of implementing cutting-edge AI models from research papers.

• Portfolio
• Github Profile