Improved Face Detection and Alignment using Cascade Deep Convolutional Network
This work addresses face detection and alignment for computer vision applications, but it appears incremental as it builds on existing cascade CNN methods.
The paper tackles the problem of face detection and alignment under varying poses, lighting, and expressions by proposing a structure to generate higher-quality training data for an end-to-end cascade network, resulting in improved performance over existing models.
Real-world face detection and alignment demand an advanced discriminative model to address challenges by pose, lighting and expression. Illuminated by the deep learning algorithm, some convolutional neural networks based face detection and alignment methods have been proposed. Recent studies have utilized the relation between face detection and alignment to make models computationally efficiency, however they ignore the connection between each cascade CNNs. In this paper, we propose an structure to propose higher quality training data for End-to-End cascade network training, which give computers more space to automatic adjust weight parameter and accelerate convergence. Experiments demonstrate considerable improvement over existing detection and alignment models.