International Journal of Innovative Research in Computer and Communication Engineering
ISSN Approved Journal | Impact factor: 8.771 | ESTD: 2013 | Follows UGC CARE Journal Norms and Guidelines
| Monthly, Peer-Reviewed, Refereed, Scholarly, Multidisciplinary and Open Access Journal | High Impact Factor 8.771 (Calculated by Google Scholar and Semantic Scholar | AI-Powered Research Tool | Indexing in all Major Database & Metadata, Citation Generator | Digital Object Identifier (DOI) |
| TITLE | Blood Group Detection Using Fingerprint Image |
|---|---|
| ABSTRACT | Blood group identification is essential for transfusion, organ transplantation and emergency treatment. The standard serological method is accurate but invasive, slow, and dependent on trained staff and laboratory facilities. This paper presents a non-invasive desktop system that predicts a blood group label from a fingerprint image using a Convolutional Neural Network (CNN). Fingerprint images are converted to grayscale, resized to 128 × 128 pixels and passed to a three-block CNN (32, 64 and 128 filters) with global average pooling, dropout and a softmax output layer. The model is trained with the Adam optimizer and sparse categorical cross-entropy loss using an 80/20 stratified split and early stopping. The application is built in Python with TensorFlow/Keras, Pillow, NumPy, scikit-learn and a Tkinter graphical interface, and it reports the predicted class with a confidence score within seconds. The system was verified with 15 functional test cases covering dataset loading, training, prediction and error handling. The work is an experimental, dataset-based study and is not a medically validated blood group test. |
| AUTHOR | BHOOMIKA T R, NISHA K S, POOJA N E, RANI K J, ER.RAMESH KUMAR H K Final-Year B.E. Students, Department of Computer Science and Engineering, STJ Institute of Technology, Ranebennur, Karnataka, India Assistant Professor, Department of Computer Science and Engineering, STJ Institute of Technology, Ranebennur, Karnataka, India |
| VOLUME | 189 |
| DOI | DOI: 10.15680/IJIRCCE.2026.1410022 |
| pdf/22_Blood Group Detection Using Fingerprint Image.pdf | |
| KEYWORDS | |
| References |
[1] R. D. Devi, K. Likhitha, M. Varsha, M. Sathwika and K. Balamani, "Blood Group Detecting Using Fingerprint," IEEE International Conference on Sustainability, Innovation & Technology (ICSIT), 2025. [2] J. L. Alekhya, B. Choppara, E. Jaswanth and N. Jaswanth, "Blood Group Detection Using CNN from Fingerprint Images," 2026 IEEE International Students' Conference on Electrical, Electronics and Computer Science, 2026. [3] C. Sivamurugan, V. K. Murthi, B. Perumal, Y. N. Sankar, Y. Siddarthha and Y. Varun, "Enhanced Blood Group Prediction with Fingerprint Images using Deep Learning," IEEE. [4] Rashmi K. A., Divya M., Chethana T., Hadiya Amber and Divya Shree K. S., "Blood Group Detection Using Fingerprint," 3rd International Conference on Knowledge Engineering and Communication Systems (ICKECS), 2025. [5] D. P. Kingma and J. Ba, "Adam: A method for stochastic optimization," arXiv:1412.6980, 2014. [6] Y. LeCun, L. Bottou, Y. Bengio and P. Haffner, "Gradient-based learning applied to document recognition," Proc. IEEE, vol. 86, no. 11, pp. 2278–2324, 1998. |