Nowadays, digital protection has become greater prominence for daily digital activities. It's far vital for people to keep new passwords in their minds and carry additional playing cards with themselves. Such practices but are getting much less stable and realistic, as a consequence leading to a growing interest in techniques associated with biometrics systems. Biometrics structures keep the bodily residences of humans in electronic surroundings and enable them to be recognized by using the stored electronic records while needed. Several different face recognition and authentication methods had been proposed. However, most of the implementation is done using Principal Component Analysis(PCA) and measuring the recognition costs. In our work we propose a new approach for fast face recognition by applying deep learning techniques. We look at the outcome of recognition subject to the various components of the face and the eyes, mouth, nose, and brow. Distinctive features are extracted from the face, which is achieved using GreyLevel CoOccurrenceMatrix(GLCM). The GLCM method is a useful feature for feature extraction because of its excessive overall stabilizing local comparison. Lastly, dataset training and feature classification of the facial data's are carried out using Multi-Class Artificial neuralnetworks(MCANN) and Adaboost in which every distinctive face within the database is distinguished. Later the facial identification tool is tested on four groups of databases, AT&T, YALE B, VGG, and CASIA. In the end, we will apply analysis to measure accuracy and precision.
