πŸ”¬ About Me

Nimol Thuon, research focuses on document analysis and low-resource language processing for applied AI in digital humanities. My early research, from 2011 to 2016, involved leading the development of the first Khmer Semantic Search Engine for the Institute of Technology of Cambodia (ITC) and the Ministry of Education, Youth and Sport (MoEYS). This was a crucial effort in addressing the complexities of processing low-resource languages like Khmer.

Since 2018, I have been conducting research in Computer Vision and Pattern Recognition at institutions such as the University of Science and Technology of China (USTC), Chinese Academy of Sciences (CAS), China, the University of Mons, Belgium, and FAU Erlangen-NΓΌrnberg, Germany. Additionally, I have worked on analyzing historical palm leaf manuscripts based on scripts in Southeast Asia like Khmer, Sundanese, and Balinese. And currently working with Tamil Scripts from south asia as well.

Although my achievements might not compare to top-tier researchers. However, they are deeply meaningful to me. Despite these accomplishments, I remain eager to gain more experience and continue learning from experts and researchers around the world.

I also welcome students, interested in these fields to reach out for online guideline on their theses or existing research.

πŸ“š Research Projects


Palm Leaf Manuscript Analysis
Document AnalysisComputer VisionPattern Recongtions

PALM-GLOBAL: Cross Domains Palm Leaf Manuscript Analysis for South and Southeast Asia Regions

The bridge the two regions of south aisa region and southeast region for palm leaf analysis.

In progress, Coming soon..→


Palm Leaf Manuscript Analysis
Document AnalysisComputer VisionPattern Recongtions

PALM-SEA:Historical Palm Leaf Manuscript Analysis for Southeast Asia Regions (Completed)

A unique of historical scripts from Southeast Asia (Sundanese, Balinese, Khmer) used to document religious texts, historical records, and cultural.

View Project Details →
Khmer Document Information Extraction and Khmer Sementic Search Engi
Document RetrievalNLPDocument Analysis

Khmer Document Information Extraction and Retrieval (Completed)

Developing tools for search engines and keyword extraction to address the challenge of finding relevant Khmer documents, despite the daily generation of significant content.

View Project Details →
Khmer Document Information Extraction and Khmer Sementic Search Engi
NLPDocument Analysis

Form Understanding For non-Latin Low-resources Documents

Developing tools for Form Understanding to address the challenge of finding relevant non-Latin documents.

In progress, Coming soon.. →

Cambodian Complex System
Complex SystemsOCRDocument Retrieval

Open Education Resource for Document Management System (Completed)

Research and development of several complex systems, including an Open Education Resource (OER) platform and a national Financial Document Management system.

View Project Details →

Selected Publications

Publication thumbnail

Multi-low resource languages in palm leaf manuscript recognition: Syllable-based augmentation and error analysis

Nimol Thuon, J Du, P Theang, R Thuon

Pattern Recognition Letters, Elsevier, 2025.

Publication thumbnail

A Low-Intervention Dual-Loop Iterative Process for Efficient Dataset Expansion and Classification in Palm Leaf Manuscript Analysis

Nimol Thuon, J Du, P Theang, R Thuon

International Journal on Document Analysis and Recognition (IJDAR) , 2025.

Publication thumbnail

Generate, transform, and clean: the role of GANs and transformers in palm leaf manuscript generation and enhancement

Nimol Thuon, J Du, Z Zhang, J Ma, P Hu

International Journal on Document Analysis and Recognition (IJDAR) , 2024.

Publication thumbnail

KhmerFormer: Multi-scale cnns-transformer with external attention for ancient khmer palm leaf isolated glyph classification

Nimol Thuon, J Du

2024 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC), IEEE , 2024.

Publication thumbnail

Improving isolated glyph classification task for palm leaf manuscripts

Nimol Thuon, J Du, J Zhang

International Conference on Frontiers in Handwriting Recognition (ICFHR 2022), Springer , 2022.

Publication thumbnail

Syllable analysis data augmentation for khmer ancient palm leaf recognition

Nimol Thuon, J Du, J Zhang

2022 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC), IEEE , 2022.

🀝 Services

Presentations & Talks

  • Presentation on International Conference on Document Analysis and Recognition (ICDAR 2025)", Wuhan, China(September,2025)
  • Invited Talk on "AI for Digital Humanities in Southeast Asia" at the National University of Singapore, Singapore, 2025.
  • Presentation on International Conference on Document Analysis and Recognition (ICDAR 2024)", Athens, Greece
  • Presentation on Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC 2024)", Macao, China
  • Invited Talk on "AI Integration in Cultural Heritage" at Kyoto University, Japan, 2024.
  • Presentation on Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC 2022)", Chiang Mai, Thailand
  • Presentation on International Conference on Frontiers in Handwriting Recognition (ICFHR 2022)", Hyderabad, India
  • Presentation on Renewable Energy in Cambodia",Norwegian University of Science and Technology (NTNU) , Norway 2022
  • Presentation on "Khmer Semantic Search Engine", University of Mons , Belgium, 2017

Professional Services (Reviewer)

  • International Conference on Image and Graphics (ICIG), 2025.
  • Chinese Conference on Pattern Recognition and Computer Vision (PRCV),2023, 2024, 2025
  • International Journal on Document Analysis and Recognition (IJDAR).

πŸ“˜ Teaching

6178101: Introduction to Computer Vision for Image Understanding

An overview of computer vision, key definitions, real-world applications like autonomous driving, and a hands-on exercise using OpenCV for edge detection.

πŸ‘‰ Read more
Page 1

πŸ“£ Blog

Khmer Semantic Search Analysis And Breakdown by SEO Expert

Khmer Semantic Search Analysis And Breakdown by SEO Expert

πŸ‘‰ Read more
Page 1

πŸŽ– Honors and Awards

  • IAPR Support Grant for Summer School on Document Analysis and Recognition (SSDA 2023), Switzerland, 2023
  • CuriousU Summer School Scholarship, University of Twente, 2022
  • IEEE USTC Outstanding Young Researcher Award, 2022
  • CAS-TWAS Fellowship, 2018
  • Erasmus+ for PhD Scholarship, 2018
  • ARES-CCD Scholarship by Belgium, 2017
  • Excellence Award for Innovative Technology by the Ministry of Education of Cambodia, 2017
  • ITC Scholarship, Cambodia
  • Winner ASEAN CTF Cyber Security Challenges in 2016
  • Runner Cyber Security Challenges in Cambodia 2015