Deep Learning-Based Blood Group Detection Using Fingerprint

Abstract

This project presents an experimental system that uses deep learning techniques to analyze fingerprint images for classification of blood groups. A convolutional neural network (CNN) is used to extract patterns from fingerprint structures such as ridges, loops, and whorls. These extracted features are used for classification into different categories. The study demonstrates the application of artificial intelligence in biometric analysis. However, the system is purely experimental and not intended for medical diagnosis or real-world blood group identification.

Introduction

The text describes a research project that uses fingerprint biometrics and deep learning to predict blood groups in a non-invasive way.

Fingerprints are widely used in biometric systems because they are unique, and recent advances in Artificial Intelligence and Convolutional Neural Networks (CNN) suggest they may also contain patterns that correlate with blood groups. The project explores this idea by training a deep learning model on fingerprint images labeled with blood group data to enable automatic prediction.

Traditional blood group testing requires blood samples, lab equipment, and skilled technicians, making it slow, invasive, and unsuitable for emergencies or remote areas. This motivates the need for a faster, safer, and more accessible alternative.

The proposed system processes fingerprint images through preprocessing steps such as grayscale conversion, resizing, and noise removal. A CNN model is then trained to learn relationships between fingerprint features (like ridge patterns and texture) and blood groups. Once trained, it can predict blood groups from new fingerprint inputs.

The methodology includes dataset collection, preprocessing, feature extraction, CNN training, and prediction. The system aims to reduce testing time, cost, and discomfort while improving accessibility in healthcare settings such as hospitals and rural areas.

Conclusion

The project demonstrates how deep learning can be used for biometric image classification. However, fingerprint-based blood group detection is not scientifically validated and should not be used for real-world medical applications.

References

[1] Vijaykumar, Patil N, and D.R.Ingle. \"A Novel Approach to Predict Blood Group using Fingerprint Map Reading.\"2021 6th International Conference for Convergence in Technology (I2CT). IEEE, 2021. [2] Patil, Vijaykumar, and D. R. Ingle. \"An association between fingerprint patterns with blood group and lifestyle based diseases: a review.\"Artificial intelligence review 54 (2021): 1803-1839. [3] Ali, Mouad MH, et al. \"Fingerprint recognition for person identification and verification based on minutiae matching.\"2016 IEEE 6th international conference on advanced computing (IACC). IEEE, 2016. [4] Alshehri, Helala, et al. \"Cross-sensor fingerprint matching method based on orientation, gradient, and Gabor-hog descriptors with score level fusion.\"IEEE Access 6 (2018): 28951-28968. [5] Fayrouz, I. Noor Eldin, NoorFarida, and A. H. Irshad. \"Relation between fingerprints and different blood groups.\"Journal of forensic and legal medicine 19.1 (2012): 18-21. [6] Pimenta, Sara, Graça Minas, and Filomena Soars. \"Spectrophotometric approach for automatic human blood typing.\"2012 IEEE 2nd Portuguese Meeting in Bioengineering (ENBENG). IEEE, 2012. [7] Fernandez, Jose, et al. \"A complete blood typing device for automatic agglutination detection based on absorption spectrophotometry.\"IEEE Transactions on Instrumentation and Measurement 64.1 (2014): 112-119. [8] Saponara, Sergio, Abdussalam Elhanashi, and Qinghe Zheng. \"Recreating fingerprint images by convolution neural network auto encoder architecture. \"IEEE Access 9 (2021): 147888-147899. [9] Ezeobiejesi, Jude, and Bir Bhanu. \"Patch based latent fingerprint matching using deep learning.\"2018 25thIEEE International Conference on Image.

Copyright

Copyright © 2026 Aishwarya ., Akshata , Archana , Ashish , Prof. Padmapriya Patil. This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.