Abstract
Facial landmarks represent prominent feature points on the face that can be used as anchor points in many face-related tasks. So far, a lot of research has been done with the aim of achieving efficient extraction of landmarks from facial images. Employing a large number of feature points for landmark detection and tracking usually requires excessive processing time. On the contrary, relying on too few feature points cannot accurately represent diverse landmark properties, such as shape. To extract the 68 most popular facial landmark points efficiently, in our previous study, we proposed a model called EMTCNN that extended the multi-task cascaded convolutional neural network for real-time face landmark detection. To improve the detection accuracy, in this study, we augment the EMTCNN model by using two convolution techniques—dilated convolution and CoordConv. The former makes it possible to increase the filter size without a significant increase in computation time. The latter enables the spatial coordinate information of landmarks to be reflected in the model. We demonstrate that our model can improve the detection accuracy while maintaining the processing speed.
Highlights
Facial landmarks such as eyes, nose, and mouth are prominent feature points on the face, and diverse tasks such as face recognition, gaze detection, person tracking, emotion recognition, and virtual makeup have been performed based on facial landmarks [1,2]
Sci. 2020, 10, 2253 time, we proposed an EMTCNN model by extending the original multi-task cascaded convolutional neural network (MTCNN) model [12] which extracts five facial landmark points in real time
MTCNN is a cascaded structure composed of relatively light convolutional neural networks (CNNs) including a proposal network (P-Net), refinement network (R-Net), and output network (O-Net)
Summary
Facial landmarks such as eyes, nose, and mouth are prominent feature points on the face, and diverse tasks such as face recognition, gaze detection, person tracking, emotion recognition, and virtual makeup have been performed based on facial landmarks [1,2]. In an effort to detect such facial landmark points accurately, adding more convolution layers has been attempted, as in Visual Geometry Group Network (VGGNet) [9,10] Even though this produces better results, it requires more computational resources and is not appropriate for real-time processing. Sci. 2020, 10, 2253 time, we proposed an EMTCNN model by extending the original multi-task cascaded convolutional neural network (MTCNN) model [12] which extracts five facial landmark points in real time. CoordConv [17]—to improve the detection accuracy while maintaining the processing speed The former makes it possible to extend the receptive field without increasing the number of parameters.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
