Facial-based Commercial Off-The-Shelf (COTS) systems increase the success rate of spoof attacks to 70% detection accuracy. A spoof attack uses an image, video, or 3D model of a person to gain unauthorized access to a biometric system. Face spoof attacks are mostly based on common spoof vectors, print attacks, and replay attacks. This research aims to improve the detection accuracy of face spoof recognition systems by employing a hybrid model of machine learning and computer vision-based approaches. Differences, including Decision Tree, Nave Bayes, K-nearest Neighbor, Support Vector Machine, Convolutional Neural Network (CCN), and Recurrent Neural Networks are used for face spoof detection. For face spoof detection, the proposed model is a hybrid variant of the CNN-based classifier used in the proposed face spoof detection model. This study improves real-time face fake detection using machine learning and computer vision. The proposed system is based on a CNN-based classification approach with optimized hyper parameters that detect real-time face spoofing attacks using print, video, and repeat attacks, improving detection accuracy. IDIAP, USSA & and MSFD datasets are used in the simulation; the proposed model has achieved a maximum accuracy of 87.5%. Furthermore, the proposed model achieved a high sensitivity score of 92.45%, indicating that it is highly likely to be used for spoof attack detection systems in the future.