A Novel Approach to predict Blood group using fingerprint map reading

Abstract

Fingerprints are considered one of the most reliable methods for identifying individuals. In forensic science and legal investigations, fingerprint evidence is widely regarded as accurate and trustworthy. Two important characteristics make fingerprints effective for identification. First, the ridge patterns formed during fetal development remain stable throughout a person’s life unless the skin is severely damaged or decomposed. Second, fingerprints are unique; no two individuals, not even identical twins, share the same ridge patterns or characteristics. Because of this uniqueness and permanence, fingerprints are often treated as strong evidence in courts of law. This study proposes a novel approach to predict blood groups using fingerprint patterns with machine learning techniques. Fingerprints, known for their distinct and permanent nature, serve as an important biometric feature. In this research, Convolutional Neural Networks (CNNs), a deep learning method, are used to analyze fingerprint images and extract complex ridge features. By learning these patterns, the model attempts to predict an individual’s blood group. This approach highlights the potential of combining biometric identification with artificial intelligence for biomedical and forensic applications.