A Non-Invasive Approach for Detection of Blood Group Using Fingerprint Analysis Based on Deep Learning

In medical practice, accurate blood group type determination is essential, especially in emergency situations where prompt decisions about blood transfusions become critical. Conventional techniques rely on chemical testing, which is dependable but frequently time-consuming and resource-intensive. Other biometric-based strategies have gained popularity as deep learning and computer vision .The use of technologies has become more prevalent. With the ambition of providing a quick, non-invasive solution, this study presents a deep learning-powered solution for blood analysis type detection using fingerprint images. The system uses a convolutional neural network (CNN), which was trained on a large dataset of fingerprint images with blood type annotations. Rh factors are among the ridge characteristics that the model uses to categorize blood groups. Data enhancement methods are utilized to improve model reliability, and evaluation results demonstrate strong accuracy. These findings suggest a potential connection between fingerprint features and specific blood group classifications.