Copyright © 2026 Authors retain the copyright of this article. This article 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.

@article{198984,
        author = {B. Jani and Ch. Tharun Teja and G. Abhinay Reddy and D. Suchithra Vennela and S.Shivaprasad},
        title = {A Novel Approach to Predict Blood Group using Fingerprint Map Reading},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {12},
        number = {11},
        pages = {13118-13126},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=198984},
        abstract = {Fingerprint patterns represent the most reliable and unique feature of human identity, remaining un- changed from birth until death. Due to their permanence, they are considered critical evidence in court, as the chance of two individuals sharing the same pat- tern is approximately one in sixty-four thousand million, differing even among twins. This paper investigates a novel application of these unique traits: pre- dicting blood groups non-invasively through fingerprint map reading using Thermal Spectroscopic Photoplethysmographic (PPG) sensors. Unlike standard scans, these sensors capture enriched data including vascular heat patterns and ridge frequency. The methodology employs Gabor filters to extract spatial features and orientation information, utilizing image processing tasks such as binary conversion and thinning for pattern normalization. These features serve as input for a Convolutional Neural Network (CNN) that automatically learns hierarchical representations for classification. Developed using Python 3.7.2, the system achieved a significant pre- diction accuracy of 97% on a diverse dataset. By leveraging advanced biometric imaging and machine learning, this work offers an automated, data-driven alternative to traditional invasive serological tests, potentially transforming medical response in remote or emergency scenarios [1, 2].},
        keywords = {Blood group prediction, Convolutional Neural Network (CNN), Gabor filters, Ther- mal Spectroscopic PPG, non-invasive biometrics, deep learning [3].},
        month = {April},
        }