Face detection of migrating learning based on constrained scene

Abstract

Face detection places an important role in face recognition which is a popular choice for biometric systems. To solve the low face detection rate problem of face detection in constrained scenario, an efficient face detection method based on migration learning was proposed in this paper. In the proposed facial detection approach, data-cleaning was firstly used to optimize the face database. Then the Visual Geometry Group 16 (VGG16) deep learning network was improved to realize migration learning by replacing the softmax regression layer with the multi-scale feature detection layer. Finally, the constrained scene face images for testing were detected and labeled by the trained migration learning model. The WIDER FACE dataset was used for experiments. Experiment results showed that the proposed method can successfully perform face detection in the WIDER FACE dataset and obtain more than 90% detection rate.