SFCN: Spoon Fully Convolutional Networks for Pulse Localization

Pulse localization is the basic task of the pulse diagnosis with the robot. Using neural network for localization can not only reduce the contact between the machine and the subject, relieve the discomfort of the process, but also reduce the preparation. Since the networks with the coordinate regression directly have large parameters and are not suited for input images with different size. In this paper, we propose a novel method, spoon fully convolutional networks (SFCN) with the landmark fitting method for pulse localization. SFCN includes the fully convolutional networks which are like the spoon while the landmark fitting method finds the pulse in the sub-pixels. The experiments show that our proposed method can locate the pulse with high accuracy and few parameters, which is suitable for application on robots.