An intelligent model-driven fingerprint classification system for gender identification

The creative technique of classifying fingerprints into distinctive patterns was known as fingerprint categorization. The ability to quickly identify and compare images makes this classification useful in a variety of sectors. The objective of this study is to provide a revolutionary optimal neural network algorithm-based intelligent fingerprint system of classification for identifying gender. We proposed an innovative Polar Bear tuned Dynamic Recurrent Neural Network (PB-DRNN) algorithm for effectively identifying the person’s gender through fingerprint. The crucial aspect of attaining high classification effectiveness with the suggested PB-DRNN approach is that the final aim is to precisely identify gender from fingerprint data. We collected fingerprint data from Kaggle dataset to create our classification method. The Gaussian filter (GF) is a pre-processing tool used to remove distortion from the raw, acquired data. The suggested PB-DRNN approach could reliably identify the gender of the data obtained from fingerprints. The categorized material findings are shown through the use of a graphical user interface (GUI). To determine the classification effectiveness of the proposed model, many statistics are evaluated during the outcome validation process. These statistics include accuracy (99.87%), recall (99.50%), and precision (99.84%). The results were compared with other well-used methodologies. Based on data from fingerprints, the experiment findings show that the suggested model works better than conventional methods in accurately determining an individual’s gender.