Research and Implementation on Face Detection Approach Based on Cascaded Convolutional Neural Networks

At present, the combination of deep learning and traditional method are used to solve the problem of face detection that caused by image quality, various poses, occlusions, complex facial expressions, illumination and real time detect. In this paper, we use a face detection framework based on cascaded convolutional neural network, which is used to balance the accuracy and running time cost. We use full convolutional neural network (FCN) to extract candidate regions of human face in the first stage, which is more efficient than selective search, Edge Box and other algorithms. Combining with the NMS algorithm and bounding box regression during the whole process, we can get more accurate face position. In order to improve the accuracy and enhance the ability of the algorithm to distinguish the face, we improved the training method, optimized the training set, and used the multi-task learning network. Experiment results show that the framework has higher accuracy and costs shorter time in face detection on FDDB.