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{179047,
        author = {Kondabattula Sai Ram and Dr. Mahmood Ali Mirza and Challa Dileep Kumar and Kasukurthi Praveen Kumar and Katukuri Radha Krishna},
        title = {An Improved Blood Group Detection Using Deep Learning Model},
        journal = {International Journal of Innovative Research in Technology},
        year = {2025},
        volume = {11},
        number = {12},
        pages = {7271-7281},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=179047},
        abstract = {Blood type determination is crucial, particularly in life-threatening situations such as organ transplants, transfusion compatibility, medical crises, diagnostic procedures, and prenatal care. The serological methods used in conventional blood group testing are accurate, but they are intrusive and necessitate laboratory infrastructure. Furthermore, human error may occur during technician-performed manual testing. 
The goal of this research is to employ pre-captured palm photos to create an accurate and effective blood type system in order to overcome these obstacles.
The suggested approach analyzes fingerprint photos and finds distinctive patterns linked to blood group phenotypes by combining cutting-edge image processing methods with machine learning, specifically Convolutional Neural Networks (CNNs). Rapid blood group detection has been increasingly important in the forensic and medical domains in recent years. Conventional techniques are frequently labor-intensive, call for skilled workers, and aren't always feasible in an emergency. This study presents an alternate method for precise and effective blood type identification that combines machine learning techniques—specifically CNNs—with fingerprint image analysis. This approach is based on fingerprint ridge patterns, which have demonstrated possible associations with blood types. A CNN model shows remarkable accuracy in blood group prediction after being trained on a large dataset of labeled fingerprint photos.},
        keywords = {Non-Invasive Medical Diagnostics, Fingerprint images, Deep Learning, Feature Learning, Pattern Recognition, Convolutional Neural Networks (CNNs) Model.},
        month = {May},
        }