Semi-Dense U-Net: A Novel U-Net Architecture for Face Detection

Abstract

Face detection and localization has been a major field of study in facial analysis and computer vision. Several convolutional neural network-based architectures have been proposed in the literature such as cascaded approach, singlestage and two-stage architectures. Using image segmentation based technique for object/face detection and recognition have been an alternative approach recently being employed. In this paper, we propose detection of faces by using U-net segmentation architectures. Motivated from DenseNet, a variant of U-net, called Semi-Dense U-Net, is designed in order to improve the binary masks generated by the segmentation model and further post-processed to detect faces. The proposed U-Net model have been trained and tested on FDDB, Wider face and Open Image dataset and compared with state-of-the-art algorithms. We could successfully achieve dice coefficient of 95.68% and average precision of 91.60% on a set of test data from OpenImage dataset.

Automatic segmentation of human ear in the wild

“…The chart topping model U-Net [26] was developed in 2015 by Olaf Ronneberger and his team of researchers for their own purpose of biomedical image segmentation. However, researchers have been using the same or modified version of this model for the purpose of detection and segmentation of regions of interest (ROI) as per their requirements [27], [28]. The model got its name from its unique "U" shape architecture as shown in Figure 4.…”