Tran Minh Trieu

I'm

About

Hi, I am a computer vision researcher working in Postdoctoral Position at Chonnam National University, South Korea. I obtained a Ph.D. degree in Computer Science from Chonnam National Univesity (South Korea) in 2022, advised by Prof. Guee-Sang Lee. I achieved Master degree in Electronics Engineering under the supervision of Dr. Nguyen Thanh Dung and Master of Engineering Trinh Hoang Duy at the University of Technology and Education (Vietnam) in 2018. Before that, I was a Teacher at Vietnam Aviation Academy. I am mainly interested in the intersection of machine learning and computer vision to build machines that can engage in the physical world contributively. Now I am focusing on a wide range of topics, including document processing, medical prognosis systems, and AI agriculture disease detection.

Post-doctoral Researcher

  • Chonnam National University
  • City: Gwangju, South Korea
  • Degree: Doctor of Philosophy in Computer Science
  • Email: tmtvaa@gmail.com

Publications

Papers

Citations

PhD Thesis

  1. Tran Minh Trieu.
    “Overall Survival Prediction in Glioblastoma Patients via Local Context of Brain Tumor MRI”. Presented 2 June 2022. Link

Korean Copyright

  1. Tran M-T, Lee G-S.
    “ Binarization of music score with complex background by deep convolutional neural networks. ”. Registration of copyright number 206371-0001063, Korea 2021. Link

Journals

  1. Tran M-T, Yang H-J, Kim S-H and Lee G-S.
    “Prediction of Survival of Glioblastoma Patients Using Local Spatial Relationships and Global Structure Awareness in FLAIR MRI Brain Images”. In: IEEE Access 11 (2023), p. 37437-37449. DOI: 10.1109/ACCESS.2023.3266771. IEEE
  2. Tran M-T, Yang H-J, Kim S-H, Oh I-J, Kang S-R, and Lee G-S.
    “Esophagus Segmentation in CT Images via Spatial Attention Network and STAPLE Algorithm.”. In: Sensors 21 (2021), p. 4556. DOI:10.3390/s21134556. MDPI
  3. Tran M-T, Yang H-J, Kim S-H, and Lee G-S.
    “Multi-Task Learning for Medical Image Inpainting Based on Organ Boundary Awareness.”. In: Applied Sciences 11 (2021), p. 4247 DOI:10.3390/app11094247. MDPI
  4. Tran M-T, Vo Q-N and Lee G-S.
    “Binarization of music score with complex background by deep convolutional neural networks.”. In: Multimedia Tools & Applications 80 (2021), p. 11031-11047 DOI:10.1007/s11042-020-10272-2. Springer
  5. Ngo D-K, Tran M-T, Yang H-J, Kim S-H, and Lee G-S.
    “Multi-Task Learning for Small Brain Tumor Segmentation from MRI.”. In: Applied Sciences 10 (2020), p. 7790 DOI:10.3390/app10217790. MDPI
  6. Tran M-T and Lee G-S.
    “Staff-line Removal for Music Score Images using U-net.”. In: KIISE Transactions on Computing Practices (KTCP) 26 (2020), p. 26-31 DOI:10.5626/KTCP.2020.26.1.26. KIISE
  7. Tran M-T and Lee G-S.
    “Super-resolution in music score images by instance normalization.”. In: Smart Media Journal 8 (2019), p. 64-71 DOI:10.30693/SMJ.2019.8.4.64 Smart Media Journal

Conferences

  1. Tran M-T and Lee G-S.
    “Preserving Text Characteristics Through Feature Concatenation for The Detection of Occluded Scene Text. ”. In Proceedings of the International Conference on Smart Media and Applications, 2023. At: Asia University, Taichung, Taiwan. Link
  2. Tran M-T, Yang H-J, Kim S-H and Lee G-S.
    “Deep Learning-Based Inpainting for Chest X-ray Image.”. In Proceedings of the International Conference on Smart Media and Applications, 2020. At: Jeju, South Korea. DOI: 10.1145/3426020.3426088
  3. Do T-B-T, Trinh D-L, Tran M-T, Lee G-S, Yang H-J, Kim S-H.
    “Deep Learning Based Ensemble Approach for 3D MRI Brain Tumor Segmentation.”. In Proceeding of 7th International Workshop, BrainLes 2021, Held in Conjunction with MICCAI 2021. DOI: 978-3-031-09002-8_19
  4. Dinh M-T, Dang Q-V, Tran M-T, Lee G-S..
    “Robust Scene Text Detection Under Occlusion via Multi-scale Adaptive Deep Network.”. In: Na, I., Irie, G. (eds) Frontiers of Computer Vision. IW-FCV 2023. Communications in Computer and Information Science, vol 1857. Springer, Singapore. DOI: 10.1007/978-981-99-4914-4_10
  5. Tran M-T and Lee G-S.
    “Staff Line Removal for Music Score Images with Super Resolution Technique.”. In Proceedings of the Korea Computer Congress, 2019. At: Jeju, South Korea. DOI: 10.5626/KTCP.2020.26.1.26
  6. Tran M-T and Lee G-S.
    “Summarization of Single Document by using Local Context Optimization.”. In Proceedings of the Conference of KISM, Korean Institute of Smart Media, 2023. At: Jeju National University, South Korea. Link
  7. Tran M-T, Irfan H, Lee G-S, Yang H-J, Kim S-H.
    “Facial Expression Awareness for Driver Distraction Detection.”. In Proceedings of the International Conference on Smart Media and Applications, 2022. At: Saipan, USA. Link
  8. Tran M-T, Do T-B-T, Lee G-S.
    “Survivor Class Prediction by Local Spatial Relationship in FLAIR MRI Brain Images.”. In Proceedings of the International Conference on Multimedia Information Technology and Applications, 2022. At: Jeju, South Korea. Link
  9. Tran M-T, Kang S-R, Oh I-J, Lee G-S, Yang H-J, Kim S-H.
    “A Deep Learning-Based Method for Glioblastoma Survival Prediction using Local Context.”. In Proceedings of the International Conference on Smart Media and Applications, 2022. At: Gunsan-si, South Korea. Link
  10. Vo C-M, Tran M-T, Lee G-S.
    “Emotion Recognition using Sentiment Information of the Scene.”. In Proceedings of the Conference of KISM, Korean Institute of Smart Media, 2021. At: Silla University, Busan, South Korea. Link
  11. Tran M-T, Lee G-S, Yang H-J, Kim S-H.
    “Medical Image Inpainting With Deep Neural Network.”. In Proceedings of the Conference of KISM, Korean Institute of Smart Media, 2021. At: Chosun University IT Convergence College, Gwangju, South Korea. Link
  12. Tran M-T, Lee G-S, Yang H-J, Kim S-H.
    “Lung tumor segmentation by fusing 2D and 3D models.”. In Proceedings of the International Workshop Frontiers of Computer Vision, 2020. At: Ibusuki, Kagoshima, Japan. Link
  13. Tran M-T, Lee G-S, Yang H-J, Kim S-H.
    “ Utilizing 3D Information From Three-Dimensional Images In Lung Tumor Segmentation.”. In Proceedings of the International Conference on Smart Media and Applications, 2019. At: Guam, USA. Link
  14. Tran M-T, Lee G-S, Yang H-J, Kim S-H.
    “Lung Tumor Segmentation Using Deep Neural Networks.”. In Proceedings of the Conference of KISM, Korean Institute of Smart Media, 2019. At: Gwangju, South Korea. Link
  15. Tran M-T and Lee G-S.
    “Super-resolution of music score images.”. In Proceedings of the Conference of KISM, Korean Institute of Smart Media, 2019. At: Korea National University of Transportation, Chungju, South Korea. Link

Skills

Programming Languages

Python80%
Matlab70%

OS

Linux80%
Windows70%

Text Editors

Office80%
Latex70%

Languages

VietnameseMothertongue
EnglishGood
KoreanBasic

Resume

Download CV

Education

Doctor of Philosophy in Computer Science

2018 - 2022

Chonnam National University--South Korea

“Overall Survival Prediction in Glioblastoma Patients via Local Context of Brain Tumor MRI”. 2022.

Master in Electronic Engineering

2016 - 2018

University of Technology and Education --Vietnam

“Foreign Object Debris (FOD) Detection for Aviation via Image Processing Technology”. 2018

Link

Bachelor in Electronics and Telecommunications Engineering

2012 - 2016

Vietnam Aviation Academy--Vietnam

“Face Recognition and License Plate Detection for Smart Parking”. 2016

Professional Experience

Post-doctoral Research Fellow

Chonnam National University --South Korea
2022-Current
  • Development of DL model to predict the overall survival days of Glioblastoma Patients;
  • Development of DL model to detect scene text under occlusion.

Teaching Assistant

Chonnam National University --South Korea
2020-2022
  • Supporting and evaluating students in class Advanced Project for AI Convergence.

National Project

Vietnam Aviation Academy --Vietnam
2017-2021
  • Ministry-level Research Topic on Foreign Object Debris Detection in Runway.
    • Certificate Link

Photos

Projects

Classifying Diseases on Strawberry Leaves

Disease leaf segmentation in agriculture is a computer vision task that automatically identifies and delineates diseased regions on plant leaves from images

Occluded Scene Text Detection using Deep Learning

Occluded scene text detection is crucial for scene text reading systems and is an active research area due to its usefulness in real world applications. However, key challenges remain. The domain shift from clean to occluded text is a major issue. Most data is normalized text, but models trained on clean data struggle when tested on occluded text since the features are quite different. Recent methods attempt adaptation but primarily use synthetic data, which does not reflect real occluded text well. We propose an efficient occluded text detector trained only on clean data. By concatenating multi-level features, our model learns textual representations suitable for occluded detection without domain-specific data. Experimental results show that our method achieves good results for occluded text detection..

Flight Trajectory Prediction using Machine Learning/Deep Learning

Flight trajectory prediction using deep learning involves developing models that can accurately forecast the future path and behavior of aircraft during a flight. By leveraging historical flight data, weather conditions, and other relevant factors, deep learning models can provide valuable insights for air traffic management, flight planning, and aviation safety.

Glioblastoma Survival Prediction

By recognizing intra- and inter-image differences, the network can learn the relationships between local spatial windows in the same image and across different images. In addition to analyzing local information, we also incorporate a global structure awareness network to capture global information from the entire image. Our proposed method shows a strong correlation between local spatial relationships and survivor class prediction in FLAIR MRI brain images.

Lung/Esophagus Medical Image Segmentation

One essential step in radiotherapy treatment planning is the organ at risk of segmentation in Computed Tomography (CT). Many recent studies have focused on several organs such as the lung, heart, esophagus, trachea, liver, aorta, kidney, and prostate. However, among the above organs, the esophagus is one of the most difficult organs to segment because of its small size, ambiguous boundary, and very low contrast in CT images. To address these challenges, we propose a fully automated framework for the esophagus segmentation from CT images. The proposed method is based on the processing of slice images from the original three-dimensional (3D) image so that our method does not require large computational resources. We employ the spatial attention mechanism with the atrous spatial pyramid pooling module to locate the esophagus effectively, which enhances the segmentation performance.

References

Guee-Sang Lee

Professor

Department of AI Convergence

Chonnam National University

gslee@jnu.ac.kr

Hyung-Jeong YANG

Professor

Department of AI Convergence

Chonnam National University

hjyang@jnu.ac.kr

Soo-Hyung Kim

Professor

Department of AI Convergence

Chonnam National University

shkim@jnu.ac.kr

Nguyen Thanh Phuong

Assitant Professor

Department of Information Engineering, Computer Science and Mathematics

University of L’Aquila

phuong.nguyen@univaq.it

Nguyen Thanh Dung

Vice Director

Vietnam Aviation Academy

dungnt@vaa.edu.vn

Trinh Hoang Duy

Lecturer

Vietnam Aviation Academy

duytrinh12@gmail.com