Current Volume 9
This project develops a non-invasive system to predict human blood group using fingerprint images and deep learning. Fingerprints from the SOCOFing dataset are preprocessed and classified using a CNN/EfficientNet-B0 model into eight blood groups (A+, A−, B+, B−, AB+, AB−, O+, O−). A Python interface enables users to upload a fingerprint and receive an instant prediction, demonstrating that fingerprint patterns can support fast blood group screening without lab tests.
Blood group prediction, CNN, deep learning, EfficientNet-B0, fingerprint recognition, non-invasive, SOCOFing dataset.
IRE Journals:
Harshitha M, Harish T, Kishan P, Likith P, Madan Y "Blood Group Prediction Using Fingerprint Samples" Iconic Research And Engineering Journals Volume 9 Issue 11 2026 Page 3731-3735 https://doi.org/10.64388/IREV9I11-1718042
IEEE:
Harshitha M, Harish T, Kishan P, Likith P, Madan Y
"Blood Group Prediction Using Fingerprint Samples" Iconic Research And Engineering Journals, 9(11) https://doi.org/10.64388/IREV9I11-1718042