In biometrics,Face recognition systems are gaining momentum with recent developments in the computer vision.Face recognition is widely used in the identification of an individual’s identity.Unfortunately,recent research work has revealed that face biometrics is vulnerable to spoofing attacks using low-tech equipment such as printed 2D photos attack,3D masking attack and taking videos using smart devices（reply attack）.Therefore,a Liveness Attack Detection（LAD）method is required to enhance the high-level security of face recognition system.Most of the previously proposed LAD methods for face anti-spoofing systems have focused on using the handcrafted image features,which are designed by expert knowledge of designers or researcher.As example Gabor filter,local binary pattern（LBP）,local ternary pattern,and the histogram of oriented gradients（HOG）.As a result,the extracted features reflect limited aspects of the problem,yielding a detection accuracy that is low and varies with the characteristics of presentation attack face images.The deep learning method has developed in the computer vision research community,which is proven to be suitable for automatically training.In this work,we combine the handcrafted features and deep neural network features to design the discriminant face spoofing detection.The handcrafted features were based on Local Binary Pattern（LBP）analysis.We analyze the features information from the luminance and the chrominance channels using Local Binary Pattern（LBP）descriptor.In deep features,we present an approach based on pre-trained convolutional neural network VGG-16 model using only static features to recognize video and printed photo attacks.By combining the two types of image features on our dataset and public databases,we get good results to identify real and attack images feature,called hybrid features,which has stronger discrimination ability to understand spoofing image feature.