Face Recognition with Deep Neural Network in Real-World Scenes

Abstract

The primary aim of this paper is to recognize faces using deep learning models. This method is employed in many areas such as human-computer interaction, automatic image indexing, and ID verification services. Despite its many uses, face recognition still has several difficult features, such as the head position, age, lighting, and facial emotions. In this paper, our method includes three components which are getting the datasets, training the face model, and recognizing faces. Three steps are included in our process. First, the authors introduce the Haar-like features and the first module-get the database by detecting the face, removing the background, and creating the grayscale images of face, then the authors introduce the second module by using LBPH method (Local Binary Patterns Histogram) to detect differences between the model sample face and the detected face. Last, the authors use face recognition predictor to return the recognition result and confidence. Finally, our method successfully recognizes people and show the confidence value at the same time. The experimental results show great potential of our method in face recognition with high accuracy.