Applying Deep Learning for Face Anti-Spoofing Share: InData Labs Score Awaiting client review n/a Date Published 11 March 2020 Reading Time 2-Minute Read The Client needed help in face recognition. His business objective was to design and create a robust solution for the prevention of spoofing attacks. The Client The client runs the business in the field of e-commerce and IT services and delivers cloud-based services to conduct financial transactions and needed help with face recognition. His business objective was to design and create a robust solution for the prevention of spoofing attacks. Challenge InData Labs was challenged with the training of a deep learning model for face anti-spoofing. The model had to discern such types of attacks as: Printed attack Digital attack Replay attack Solution Our team had to design the processes of data gathering specifically for that task and collect all the data needed for training. The data for analysis and model training contained short videos taken with mobile phones’ front cameras. We created a dataset of 2500 videos with multiple representations of attacks along with genuine faces. We created a Proof of concept and provided the client with a demo to address all the challenges. The code we delivered could be used to train models on extended data and high-speed models. We also presented several types of models. Technologies and Tools Python, deep learning, face recognition, computer vision, keypoint detection, MTCNN, TensorFlow