Automated Blood Group Detection Using Fingerprint Biometrics and Deep Learning

Abstract

Blood group classification plays a vital role in medical emergencies, transfusion management, and personalized healthcare. Traditional methods rely on serological testing, which requires invasive sampling and laboratory infrastructure. This study proposes a novel, non-invasive system for predicting human blood groups using fingerprint images. Our solution leverages a hybrid deep learning model combining Convolutional Neural Networks (CNNs) and Graph Neural Networks (GNNs) to capture both local texture patterns and high-level fingerprint topology. The proposed system consists of a robust preprocessing pipeline that converts grayscale fingerprint images to a normalized format suitable for hybrid feature extraction. The CNN component extracts spatial texture features, while the GNN component analyzes relational structures and ridge connectivity. The final classification is performed through a dense layer that outputs the predicted blood group among the eight major categories (A+, A-, B+, B-, AB+, AB-, O+, O-). To facilitate real-world deployment and ease of use, the system includes optional IoT integration via the R307S fingerprint scanner. Users can either upload fingerprint images through a web interface or scan their fingerprints directly using the R307S scanner connected to a microcontroller (e.g., Arduino). A unified Python backend (predict.py) handles both data paths seamlessly, supporting flexible deployment in both standalone and server-based applications. The dataset comprises over 6000 fingerprint samples across all blood group classes. With 100 training epochs and a batch size of 32, the model achieved a training accuracy of ~70% and demonstrated early signs of generalizability, despite the inherent biological variability in fingerprint patterns across individuals. This project serves as a proof-of-concept that fingerprint morphology can be correlated to blood groups using deep learning, offering a low-cost, non-invasive alternative to traditional blood group testing. It also opens up possibilities for use in rural healthcare, forensic identification, and embedded biometric devices.

Introduction

This work explores a novel, non-invasive method for blood group identification using fingerprint images and deep learning, addressing limitations of traditional invasive blood grouping techniques. Motivated by studies linking fingerprint patterns (dermatoglyphics) with genetic traits like blood type, the authors propose a hybrid deep learning model that combines Convolutional Neural Networks (CNNs) to extract local fingerprint textures and Graph Neural Networks (GNNs) to capture global ridge connectivity.

The system supports real-time fingerprint acquisition using an R307S biometric scanner, enabling either direct scanning or image upload for blood group prediction. A large dataset of over 6000 fingerprint images evenly representing eight major blood groups (A+, A-, B+, B-, AB+, AB-, O+, O-) was used to train the model after preprocessing steps like grayscale conversion, resizing, and normalization.

Literature review highlights past approaches ranging from classical statistical correlation studies to machine learning classifiers and CNNs, noting their limitations in capturing structural fingerprint information. GNNs are introduced as a solution to model topological relationships within fingerprints. The hybrid CNN-GNN architecture leverages the strengths of both for improved accuracy.

The methodology details dataset structuring, image preprocessing, model design, training with categorical cross-entropy loss, and real-time prediction modes via web uploads or direct hardware scanning. Integration with IoT devices and practical deployment using Python and PHP frameworks is described.

Results confirm successful fingerprint image acquisition and preprocessing using the R307S scanner, with effective image normalization and timely scanning. The study demonstrates potential for a portable, non-invasive blood group prediction system useful in low-resource or emergency healthcare scenarios.

Conclusion

The integration of biometric technology with machine learning has opened up new avenues in healthcare diagnostics. In this project, we successfully developed a fingerprint-based system capable of predicting a person’s blood group using a trained deep learning model. The solution is built around two major components: the R307S fingerprint scanner for real-time image acquisition, and a CNN model for classification. Together, they form a seamless pipeline that allows either scanned or uploaded fingerprint images to be processed and analyzed. One of the major achievements of this work is the complete automation of the fingerprint scanning, conversion, and prediction process. Despite the limitations of raw image output from the sensor, appropriate preprocessing techniques were implemented to enhance image quality and make it suitable for accurate blood group classification. This work not only showcases the potential of biometric data beyond identification but also serves as a practical demonstration of how AI can assist in medical predictions without the need for invasive procedures.

References

[1] D. Maltoni, D. Maio, A. K. Jain, and S. Prabhakar, Handbook of Fingerprint Recognition, 2nd ed. London, U.K.: Springer-Verlag, 2009. [2] A. Kumar and K. R. Prathyusha, “Personal authentication using hand vein triangulation and knuckle shape,” IEEE Transactions on Image Processing, vol. 18, no. 9, pp. 2127–2136, Sep. 2009. [3] S. S. Ayyappan, R. M. Sudha, and M. Tamilselvi, “A machine learning approach to predict blood group from fingerprints,” Journal of Medical Systems, vol. 44, no. 1, pp. 1–7, 2020. [4] M. Saini, A. Goyal, and S. Rajpal, “Blood group detection using fingerprint biometric features,” Procedia Computer Science, vol. 132, pp. 537–543, 2018. [5] PyFingerprint Library – GitHub Repository. [Online]. Available: https://github.com/bastianraschke/pyfingerprint [6] Y. LeCun, Y. Bengio, and G. Hinton, “Deep learning,” Nature, vol. 521, no. 7553, pp. 436–444, May 2015. [7] P. Viola and M. J. Jones, “Robust real-time face detection,” International Journal of Computer Vision, vol. 57, no. 2, pp. 137–154, 2004. [8] R307S Fingerprint Scanner Datasheet, Growrays India, 2022. [Online]. Available: https://www.electronicwings.com/sensors/r307-optical-fingerprint-reader-sensor-module

Copyright

Copyright © 2025 Chelli Dileep, Prof. Kunjam Nageswara Rao. 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.