Identification and Classification of Fingerprints Using Automated Deep-Learning Techniques

Fingerprint Identification Systems (AFIS) face significant challenges in real-time applications due to the vast number of comparisons required for large fingerprint databases. To address this, we present a deep learning-based fingerprint categorization technique to enhance individual identification efficiency. To address This categorization technique uses deep learning to find specific fingerprint information. Specific fingerprint information, including left-right hand classification, sweat-pore classification, scratch classification, and finger classification, was intended to be distinguished by the suggested method. The fingerprint dataset Scoring was collected from a public fingerprint dataset. The proposed CNN model, implemented in Python and Google Colab, enhances biometric systems effectiveness by using deep learning techniques like Resnet 50, MobileNet, LeNet, and Hybrid model, demonstrating its strengths. The results of the planned research would be helpful for business and for assisting investigators in connecting one crime scene to another involving the same suspect.