Jasmin Jahan Puspo

I am an M.Sc(Thesis) student in Computer Science and Engineering (CSE) at Shahjalal University of Science and Technology (SUST). My advisor is Mohammad Shahidur Rahman. I also received my B.Sc.(Engineering) in Computer Science and Engineering (CSE) from North East University Bangladesh (NEUB). My undergrad thesis supervisor was Muhammad Mahir Hasan Chowdhury.


My research interest in Computer Vision lies in implementing machine learning algorithms in medical imaging. I am broadly interested in Computer Vision and Machine Learning.


Email | GitHub | Google Scholar | LinkedIn | CV 

jasminjahanpuspo AT {gmail.com}
profile photo

News

  • [23 Oct 2025] Successfully defended master's thesis.
  • [21 Aug 2025] Completed the IELTS Academic Test.
  • [13 Jun 2025] A paper based on my master’s thesis accepted at QPAIN 2025.
  • [25 Mar 2025] My initial manuscript has been accepted in a Q1 (IF: 2.6) journal.
  • [23 Jan 2025] One paper accepted at ECCE 2025.
  • [28 Nov 2024] First sole-author paper accepted at ICCIT 2024.
  • [28 Aug 2023] Appeared for the GRE General Test.

Publications

Journal
mosquito_diseases TransembleNet: Enhancing vector mosquito species classification through transfer learning-based ensemble model.
Abdullah Al Maruf, Md. Mahmudul Haque, Rownuk Ara Rumy, Jasmin Jahan Puspo, Dr. Zeyar Aung.
Plos One, Q1, 2025
paper / project page

Conference
bengali_taka BengaliTaka: A Comparative Analysis of Transformer and CNNs on Bangladeshi Currency Recognition.
Jasmin Jahan Puspo, M. Shahidur Rahman
QPAIN 2025
paper / project page
skin_cancer SkinNet: An EnsembleNet Technique to Detect Skin Cancer Using Pre-Trained Models.
Jasmin Jahan Puspo, Muhammad Mahir Hasan Chowdhury
ECCE 2025
paper / project page
breast_cancer A Novel Approach to Classify Breast Cancer Using Transfer Learning.
Jasmin Jahan Puspo
ICCIT 2024
paper / project page

Academic Thesis
breast_cancer One Stage Detection, Segmentation, Shape, and Stage Classification in Digital Mammography.
Jasmin Jahan Puspo, Muhammad Mahir Hasan Chowdhury.
Undergraduate Thesis, NEUB | 2021
project page

Personal Dataset Collection
bengali taka Bengali Taka [Kaggle]
- 397 high-resolution images (2408x1496) captured via mobile device, including six categories (10, 20, 50, 100, 500, and 1000 Taka denominations), size at 66 MB.
sign_language Bangla Sign Language [Kaggle]
- 30 files (224×224) captured via web camera, including three categories (সাহায্য, হ্যাঁ, না).
Template