A Review on Fingerprint Based Blood Group Prediction

Abstract

Blood group identification is a critical process in medical diagnostics, emergency transfusions, and forensic applications. Conventional methods rely on invasive blood sampling and laboratory-based biochemical analysis, which can be timeconsuming and resource dependent. This paper presents the design and implementation of a non-invasive system for predicting human blood groups using fingerprint images and deep learning techniques. The proposed approach utilizes Convolutional Neural Networks (CNNs) to automatically extract distinctive fingerprint features such as ridge patterns, minutiae points. A labeled dataset of fingerprint images corresponding to different blood groups (A, B, AB, and O) is used to train and evaluate the model. The system aims to provide a fast, cost-effective, and accessible alternative to traditional blood typing methods. Experimental results demonstrate that the proposed model achieves promising accuracy, highlighting the potential of integrating biometric analysis with artificial intelligence for healthcare applications. This work contributes toward developing efficient, contactless, and real-time diagnostic tools suitable for both medical and forensic domains.

Introduction

This paper proposes a non-invasive blood group prediction system that uses fingerprint images and Convolutional Neural Networks (CNNs) to predict a person's blood group (A, B, AB, or O). Traditional blood group identification methods rely on blood sample testing, which is accurate but invasive, time-consuming, costly, and dependent on laboratory facilities. The proposed approach aims to provide a faster, safer, and more accessible alternative.

The study is based on the concept of dermatoglyphics, which suggests a possible genetic relationship between fingerprint patterns and blood groups since both develop during early fetal growth. Previous research has reported correlations between fingerprint types (loops, whorls, and arches) and different blood groups, motivating the use of AI and deep learning for automated prediction.

The proposed system consists of three main modules: blood group prediction, blood donation management, and hospital management, all connected through a centralized SQLite database. In the prediction module, fingerprint images undergo preprocessing, feature extraction, and classification using a CNN model that automatically learns fingerprint characteristics such as ridge flow, texture, and minutiae points. The system then predicts the blood group and stores the results for future use.

Implementation is carried out using Python, TensorFlow/Keras, and OpenCV, with the CNN trained on labeled fingerprint datasets. The model processes fingerprint images through convolutional, pooling, and fully connected layers, using a Softmax classifier for multi-class blood group prediction. Performance is evaluated using standard metrics such as accuracy, precision, recall, and F1-score.

Experimental results show that CNNs can successfully extract fingerprint features and perform blood group classification with satisfactory accuracy. The system offers several advantages, including being non-invasive, cost-effective, fast, scalable, hygienic, and suitable for remote healthcare environments. It also supports emergency decision-making and can be integrated with blood donation and hospital management services.

However, the approach has limitations. Prediction accuracy depends heavily on dataset quality and size, and the correlation between fingerprints and blood groups is not perfectly established. The model may struggle with poor-quality fingerprint images, different populations, and varying acquisition methods. Therefore, while promising, the system cannot yet replace conventional blood testing and requires further medical validation before real-world clinical deployment.

Conclusion

The proposed study on blood group detection using fingerprint analysis presents an innovative, non-invasive, and costeffective approach for biological identification. Conventional blood group determination methods depend on serological testing, which involves blood sample collection, chemical reagents, and specialized laboratory facilities. These processes are often time-consuming and may introduce the possibility of human error. In contrast, the proposed system utilizes the unique ridge patterns of fingerprints to predict an individual’s blood group through advanced image processing and deep learning techniques. By employing Convolutional Neural Networks (CNNs) and machine learning models, the system offers an automated, efficient, and reliable solution while minimizing the need for laboratory infrastructure and physical sampling. In addition, the proposed method provides notable benefits in terms of speed, safety, and accessibility. It is especially useful for large-scale screening, remote locations, and emergency situations where traditional blood testing may not be feasible. The obtained results demonstrate encouraging accuracy, supporting the potential of fingerprint-based blood group prediction as an effective biometric approach. Despite its advantages, certain improvements can be made to enhance system performance. Increasing the dataset size with more diverse samples, refining feature extraction methods, and adopting advanced or hybrid deep learning models can further improve accuracy and robustness. Moreover, integrating the system into mobile or web-based platforms can enable realtime applications in healthcare, forensics, and identification systems. Overall, fingerprint-based blood group prediction represents a promising advancement in the integration of biometrics and artificial intelligence. With further development, it has the potential to become a reliable, fast, and non-invasive alternative for blood group identification in various real-world applications.

References

[1] Nihar, T. Yeswanth, K. Prabhakar, K.. (2024). Blood group determination using fingerprint. MATEC Web of Conferences. 392. 10.1051/matecconf/202439201069. [2] P. N. Vijaykumar and D. R. Ingle, ”A Novel Approach to Predict Blood Group using Fingerprint Map Reading,” 2021 6th International Conference for Convergence in Technology (I2CT), Maharashtra, India, 2021, pp. 1-7, doi: 10.1109/I2CT51068.2021.9418114. [3] P, Swathi K, Sushmita Horadi, Prof. (2024). Fingerprint Based Blood Group using Deep Learning. International Journal of Advanced Research in Science, Communication and Technology. 699-708. 10.48175/IJARSCT-15393. [4] Patil, Amit, Amrit Malik, and Treza Shirole. ”Fingerprint patterns in relation to gender and blood groups-A study in Navi Mumbai.” Indian Journal of Forensic and Community Medicine 4, no. 3 (2017): 204 208. [5] Smail, Harem Othman, Dlnya Ahmed Wahab, and Zhino Yahia Abdullah. ”Relationship between pattern of fingerprints and blood groups.” J Adv Lab Res Biol 10, no. 3 (2019): 84-90. [6] Raja, D. Siva Sundhara, and J. Abinaya. ”A cost-effective method for blood group detection using fingerprints.” International Journal of Advance Study and Research Work 2 (2019). [7] Bashir, Abdallah. ”RELATIONSHIP BETWEEN FINGERPRINT PAT-TERNS AND BLOOD GROUPS IN LIBYAN STUDENTS: A COMPARATIVE STUDY.” Global Journal of Medical and Pharmaceutical Sciences 3, no. 07 (2024): 1-6. [8] Al Habsi, Tariq, Hussein Al Khabori, Sara Al Qasmi, Tasnim Al Habsi, Mohamed Al Mushaiqri, Srijit Das, and Srinivasa Rao Sirasanagandla. [9] ”The association between fingerprint patterns and blood groups in the Omani population.” Arab Gulf Journal of Scientific Research 41, no. 3 (2023): 283-292. [10] Aamir, Yasmin Masood, Riffat Irshad, Nasim Malik, Dr Farid, Noreen Shahab, Muhammad. (2022). Relationship between Pattern of Fingerprints and Blood Groups. Pakistan Journal of Medical and Health Sciences. 16. 698-700. 10.53350/pjmhs22169698. [11] Fayrouz, I. Noor Eldin, Noor Farida, and A. H. Irshad. ”Relation between fingerprints and different blood groups.” Journal of forensic and legal medicine 19, no. 1 (2012): 18-21. [12] Patil, Vijaykumar, and D. R. Ingle. ”An association between fingerprint patterns with blood group and lifestyle based diseases: a review.” Artificial intelligence review 54, no. 3 (2021): 1803-1839. [13] Ravindran, G., T. Joby, M. Pravin, and P. Pandiyan. ”Determination and classification of blood types using image processing techniques.” International Journal of Computer Applications 157, no. 1 (2017): 1216. [14] Banu, A. Narkis, and V. Kalpana. ”An automatic system to detect human blood group of many individuals in a parellel manner using image processing.” International Journal of Pure and Applied Mathematics 118, no. 20 (2018): 3119-3127. [15] Joshi, S., D. Garg, P. Bajaj, and V. Jindal. ”Efficacy of fingerprint to determine gender and blood group.” J Dent Oral Care Med 2, no. 1 (2016): 103. [16] Kc, Sudikshya, Niroj Maharjan, Nischita Adhikari, and Pragya Shrestha. ”Qualitative analysis of primary fingerprint pattern in different blood group and gender in Nepalese.” Anatomy research international 2018, no. 1 (2018): 2848974. [17] Rashmi K. A., Divya M., Chethana T., Hadiya Amber, and Divya Shree K. S., “Blood Group Detection Using Fingerprint,” in Proceedings of the 3rd IEEE International Conference on Knowledge Engineering and Communication Systems (ICKECS – 2025), Chikballapur, India, Apr. 28–29, 2025, pp. 1–6. doi:10.1109/ICKECS65700.2025.11034795.

Copyright

Copyright © 2026 Aarsha K S, Arya M A, Nandana T Arjun, Sandra Sadasivan, Gishma K M. 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.