In recent years, biometric authentication has attracted attention to be utilized in medical applications where a high level of security is required because of their uniqueness and the accuracy with which they enable identification. The use of biometric features in procedures of recognition and verification is growing rapidly. Facial biometry is very precise and has a low intrusiveness level, making it ideal for preserving facial data. There are a variety of biometric methods offered to perform the same purpose, including hand geometry, iris recognition, and fingerprint recognition. Nevertheless, the most effective and extensively used biometric method is facial recognition. Cloud Technology, Social Networks, and Big Data analysis all started with this biometric approach. Effective face identification in a large dataset is a difficult and crucial issue. In this study, we suggested ensemble machine learning techniques (Naïve Bayes (NB), Classification and Regression tree (CART), and Random forest (RF)) are used to perform face identification. The face data samples are initially gathered from the FERET database. Using the Weiner filter, the gathered dataset is preprocessed to remove noise from the images. Linear discriminant analysis is used for feature extraction and preprocessing, and the recognition is handled using our ensemble techniques. The experimental findings show that our ensemble technique is more efficient than other methods. © 2025 Elsevier B.V., All rights reserved.