A Fast Face Detection Method via Convolutional Neural Network
This work addresses efficiency issues in face detection for applications requiring real-time processing, though it appears incremental as it builds on existing CNN-based methods.
The paper tackles the computational burden of multi-scale feature extraction in face detection by proposing a method using discriminative complete features (DCFs) that enable scale invariance without an image pyramid, resulting in high speed and promising performance.
Current face or object detection methods via convolutional neural network (such as OverFeat, R-CNN and DenseNet) explicitly extract multi-scale features based on an image pyramid. However, such a strategy increases the computational burden for face detection. In this paper, we propose a fast face detection method based on discriminative complete features (DCFs) extracted by an elaborately designed convolutional neural network, where face detection is directly performed on the complete feature maps. DCFs have shown the ability of scale invariance, which is beneficial for face detection with high speed and promising performance. Therefore, extracting multi-scale features on an image pyramid employed in the conventional methods is not required in the proposed method, which can greatly improve its efficiency for face detection. Experimental results on several popular face detection datasets show the efficiency and the effectiveness of the proposed method for face detection.