Nguyen Huy Thanh

Nguyen Huy Thanh

AI Computer vision Research Engineer/Project Manager

Panasonic R&D Center Vietnam

About

  • Collaborative AI researcher/AI specialist at Viceph - an AI driven application for orthodontist Viceph.net.
  • Assistant Manager of Advanced Technology Solution Department (ATSD) at Panasonic R&D Center Vietnam.
  • Researching member at Vietnam Orthodontic Research Group [VORG]
  • Senior Research Engineer with +8 years of full-time work experience of Computer Vision at Panasonic R&D Center Vietnam.
  • Embedded Software engineer with +2 years of experience of Machine Vision/Embedded system at Foxconn Vietnam R&D Center Foxconn Company.
  • Master’s graduate in Computer Science and Digital Image Processing from the Institute of photonics and communications at the National Kaohsiung University of Applied Sciences (Class of 2015).

Interests

  • 2D&3D Computer Vision | Embedded AI system
  • Explainable AI (XAI)
  • 3D image processing & reconstruction
  • Bioimage Informatics
  • Data science
  • N-dimension Tensor data decomposition
  • DevOps, MLOps, Cloud Computing System (AWS, Azure)

Education

  • Master of Computer Science, 2015-2017

    National Kaohsiung University of Applied Sciences

  • B.E in Electronics and Telecommunication Engineering, 2008-2013

    Hanoi University of Transport and telecommunication

Experience

 
 
 
 
 

Collaborative AI researcher/AI Specialist/Co-developer

MEDBrain

Mar 2022 – Present Hanoi
  • Researching and developing AI solution for medical image processing/ bioimage informatics and for orthodontic analysis.
  • Co-developer of Viceph - An AI Driven Engine for orthodontist.
 
 
 
 
 

Assistant Manager/Assistant Principal Engineer/AI specialist/

Panasonic R&D Center Vietnam

Apr 2020 – Present Hanoi
  • Researching and developing AI related technical solutions for developing Panasonic advanced technology products.
  • Project manager and technical leader at Advanced Technology Solution Department at Panasonic R&D Center Vietnam.
  • Building-up AI related-business for Advanced Technology Solution Department.
  • Building-up and training AI team for company.
 
 
 
 
 

Senior Computer Vision research engineer

Panasonic R&D Center Vietnam

Sep 2018 – Apr 2020 Hanoi
  • Researched and developed digital image processing algorithms and AI models for computer vision projects such as: 2D image object recognition and segmentation, 3D BIM modeling, objects tracking for Panasonic Lumix camera, defect inspection in factory, etc.
  • Researched and developed deep learning model compression methods such as quantization, pruning for deep learning models that can be deployed on edge devices and mobile phones.
 
 
 
 
 

Machine Vision/Embedded software engineer

Foxconn LTD.

Mar 2017 – Sep 2018 Bac Ninh
  • Developed Linux-based embedded system for GPON/dual bands WiFi router, Linux/Android Set Top box.
  • Designed and developed Automatic Optical Inspection (AOI) system for detecting defects in factory production lines such as defects inspection on printed circuit board (PCB), electrical components detection, solder paste checking, cover surface checking, etc.
 
 
 
 
 

Electronic and Telecommunication engineer

Viet Thang Industrial Equipment and Technology Transfer Company

Sep 2013 – Feb 2015 Hanoi
  • Deployed telecommunication system for Security force and Military.
  • Transferred Security technologies and products for B2B business.

Projects

Visit my Github profile for complete list

*
All Deep Learning xAI DevOps & MLOps Tensor Decomposition Medical image

Automated 3D BIM modeling for Digital Twin development

This project focuses on fully automatically 3D BIM modeling using 3D point cloud data. In this project, we firstly collected 3D point cloud data of small room by using iPhone 12 Pro (integrated LiDAR sensor).

Automatic Cephalometric landmark detection

Landmark identification is crucial in quantifying cephalometric analysis such as Steiner, Bjork, Ricketts, Kim, Nagasaki, etc. For applying these analysis to cephalometric image, dentist or orthodontist need to annotate some group of landmarks that corresponding to specified analysis.

Fully automated Cervical Vertebral Maturation assessment

Cervical vertebra maturation (CVM) staging in lateral cephalometric radiographs is an efficient method to determine skeletal maturation, as lateral cephalometric radiography is routinely required for orthodontic diagnosis and treatment planning in orthodontic practice with no additional radiographs required to assess the CVM stages.

Room layout recognition

In this project, we focus on building-up an Instance segmentation model for recognizing drawing room layout data. We trained and tested our model (Unet architecture) on both public dataset (Cubicasa, R3D) and own dataset (more than 1000 images of drawing layout) To ensuring generalization of the trained model, we added CVF-FP dataset (public) to test set for evaluation.

Synthesizing data by using 3D object models

In this project, we focus on synthesizing 360 panoramic image data from 3D models without real image. We first collected 3D models of in-house objects such as table, curtain, chairs, air-conditioner, TV, etc from online storage.

Video object tracking and segmentation for digital camera

In this project, we focus on optimizing video object tracking and segmentation model for running on digital still camera. We used the Siamese network based model for tracking object on input video.

xAI for video action recognition

Researching some (xAI methods) for time series data. Eg: video action recognition. Implementing GradCAM, Contrastive Layer-wise Relevance Propagation (CLRP), Deep Taylor Decomposition algorithms for visualizing heat map (target feature map) that pretrained deep learning model focused on.

Recent Posts

Publications

Skills

3D 3D BIM 3D object recognition 3D point cloud Action recognition Bioimage informatics C# C++ Camera Catboost Cephalometric Cloud Database Deep learning Docker EfficientDet GradCAM Instance Segmentation IoT Kubenetes Landmark detection LiDAR LightGBM LRP Machine Learning Mask-RCNN Medical image analysis MobileNet Object Tracking Objet Segmentation OpenCV Pruning Python Pytorch Quantization REVIT APIs Simulation SlowFast Tensor Decomposition Tensorflow Torchserve XGBoost YoloV5

Activities

Activities

Honours

  • Panasonic R&D Center Vietnam - Company best project award - 2021
  • Panasonic R&D Center Vietnam - Company best employee award - 2020
  • First Place Award in the 13th Digital Image Processing and Creative Design Competition - Taiwan 2017
  • Foxconn full education scholarship award - Master Student at National Kaohsiung University of Applied Science - 2015

Contact

Drop me an email to hear back from me!