Face recognition is a crucial biometric technology used in various security and identification applications. Ensuring accuracy and reliability in facial recognition systems requires robust feature extraction and secure processing methods. This study presents an accurate facial recognition model using a feature extraction approach within a cloud environment. First, the facial images undergo preprocessing, including grayscale conversion, histogram equalization, Viola-Jones face detection, and resizing. Then, features are extracted using a hybrid approach that combines Linear Discriminant Analysis (LDA) and Gray-Level Co-occurrence Matrix (GLCM). The extracted features are encrypted using the Data Encryption Standard (DES) for security and then sent to the cloud server hosting the deep model. Upon reaching the server, the features are decrypted and fed into the proposed Fuzzy Face Deep Model (FFDM), which incorporates a fuzzy layer to enhance recognition accuracy. The model was evaluated using the MUCT and LFW datasets, demonstrating high accuracy and notable results, with precision of 99.65% and 100% on MUCT and LFW, respectively.